Skip to content

Siren MCP server

ai.mysiren/sirenmysiren.aistreamable-httpv1.1.1Scanned

Deterministic visual marketing engine. Your agent plans, renders, and posts on-brand campaigns.

70 tools: 9 can delete or cancel things, 1 do something that can't be undone, 38 change things and 22 only read.

Tools: 9 delete, 1 irreversible, 38 write, 22 read.
  • Reads private data · 1
  • Reads text others write · 15
  • Can send data out · 9
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

9 tools here can delete or cancel things and 1 does something that can't be undone. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Siren MCP server can do

The Siren MCP server is published by mysiren.ai, a domain the MCP Registry verified. It has 70 tools. It can delete or cancel things (9 tools: post_run, schedule_post, delete_product_screen, delete_person and 5 more), do things that cannot be undone, such as sending, paying or publishing (send_ads_to_platform) and create or change data (38 tools: create_campaign, clarify_brief, render_asset, upload_media and 34 more). 22 tools only read.

1 tool reads private data (studio_get); 15 tools bring in text other people can write (get_account, post_run, schedule_post and 12 more); 9 tools can send data out of your system (create_campaign, render_asset, upload_media and 6 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed 3 times since Anlyon Radar first saw them.

Last scanned Nov 20, 2026, version 1.1.1.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

70 tools

Deletes or cancels 9Claude Code: deny
  • delete_brand_videoRemove a clip from Brand DNA, file and poster included.No findings

    Why it is in this group

    • The name "delete_brand_video" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Remove a clip from Brand DNA, file and poster included.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: false
  • delete_mediaDelete one photo or video uploaded with upload_media.No findings

    Why it is in this group

    • The name "delete_media" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Delete one photo or video uploaded with upload_media. Only this workspace's uploads; a film that already rendered keeps its copy.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: false
  • delete_personRemove a face from the people library.No findings

    Why it is in this group

    • The name "delete_person" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Remove a face from the people library.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: false
  • delete_product_screenRemove a product screenshot from Brand DNA.No findings

    Why it is in this group

    • The name "delete_product_screen" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Remove a product screenshot from Brand DNA. Does not delete Brand Memory.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: false
  • delete_webhookStop a standing webhook.No findings

    Why it is in this group

    • The name "delete_webhook" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Stop a standing webhook.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: false
  • go_live_ad_campaignTurn a campaign on: real ad money starts.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Turn a campaign on: real ad money starts. Always two calls. The first returns status needs_confirm and a summary (per day, the most this month, the caps): show it to the human word for word. Only when they say yes, call again with the confirm code. Inside the caps only.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
  • post_runPost a finished run's assets to the workspace's CONNECTED SOCIAL ACCOUNT.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "post_run" says "post": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe name "post_run" says "post": it sends or publishes something to other people.
    Description, as the server wrote it
    Post a finished run's assets to the workspace's CONNECTED SOCIAL ACCOUNT. This is live, public distribution on the customer's channel — always confirm with the user before calling. Only works if the grant was authorised with posting allowed. Pass `caption` to own the words; it goes out verbatim. The call queues the post behind a short publish window (about two minutes, cancellable) rather than firing inline: poll get_run after that and read `posts[].url` for the live permalink and the caption that went out.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
  • schedule_postSchedule a finished run to post at scheduled_at (ISO-8601).Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "schedule_post" says "schedule": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe name "schedule_post" says "schedule" and "post": it writes something other people read.
    Description, as the server wrote it
    Schedule a finished run to post at scheduled_at (ISO-8601). Shows in the customer's local timezone. platforms: x, instagram, tiktok, linkedin, youtube, or everything. Posts fire sequentially. Requires Allow posting. Prefer this over post_run when the user names a time. On create_campaign you can pass scheduled_at instead.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
  • studio_scheduleRender a Studio card then queue a ScheduledPost at scheduled_at.Reads text others writeNo findings

    Why it is in this group

    • The name "studio_schedule" says "schedule": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Render a Studio card then queue a ScheduledPost at scheduled_at.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
Can't be undone 1Claude Code: ask
  • send_ads_to_platformSend a ready draft to its platform: campaign, ad set and ads are created PAUSED.Can send data outNo findings

    Why it is in this group

    • The name "send_ads_to_platform" says "send": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • outboundThe name "send_ads_to_platform" says "send": it sends or publishes something to other people.
    Description, as the server wrote it
    Send a ready draft to its platform: campaign, ad set and ads are created PAUSED. Nothing spends until go_live_ad_campaign. Poll get_ad_campaign: launching, then paused (or draft with launch_error).

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
Changes things 38Claude Code: ask
  • ad_account_balanceWhat each ad account has spent, its spending limit, what's left under it, and the platform's billing link.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    What each ad account has spent, its spending limit, what's left under it, and the platform's billing link. No app can add money to an ad account: to top up, give the human billing_url.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • ad_alertsWhat needs the human now (rejected ads, spend spikes, account problems, cap pauses), and what cleared in the last 30 days.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    What needs the human now (rejected ads, spend spikes, account problems, cap pauses), and what cleared in the last 30 days.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • ad_audiencesThe customer list and lookalike audiences on Meta: how many people Siren knows, each audience's size and status.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    The customer list and lookalike audiences on Meta: how many people Siren knows, each audience's size and status. Read only; the human makes audiences on the Ads page.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • ad_autopilotWhether autopilot is on, what it may do by itself (pause a weak ad, move a budget by up to 20%, inside the caps, once every 3 days per campaign) and whether the plan allows it (Sca…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Whether autopilot is on, what it may do by itself (pause a weak ad, move a budget by up to 20%, inside the caps, once every 3 days per campaign) and whether the plan allows it (Scale). Read only: the human turns it on or off on the Ads page under Caps, never an agent.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • ad_conversionsSales tracking: whether the Siren tag has been seen on the site, events this week, the Meta pixel, other platforms it sends to, Stripe, and money made back in 30 days (minor units)…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Sales tracking: whether the Siren tag has been seen on the site, events this week, the Meta pixel, other platforms it sends to, Stripe, and money made back in 30 days (minor units). Read only.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • ad_performanceHow the ads did: totals, each campaign and each ad with spend, impressions, clicks, results, click-through rate, cost per click and cost per result.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    How the ads did: totals, each campaign and each ad with spend, impressions, clicks, results, click-through rate, cost per click and cost per result. Money is in minor units (cents).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • ad_testsSplit tests: the ones running with each version's numbers, and every verdict so far (the winner, its rate, how sure).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Split tests: the ones running with each version's numbers, and every verdict so far (the winner, its rate, how sure).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • add_personAdd a face to the people library.No findings

    Why it is in this group

    • The name "add_person" says "add": a word for a change.
    Description, as the server wrote it
    Add a face to the people library. Siren crops it round in a few seconds (status cropping, then ready). Only upload people who agreed.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • ads_overviewThe workspace's ads at a glance: spend today and this month against the caps, live campaigns, connected ad accounts, every campaign with its status and budget, and how many of Sire…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    The workspace's ads at a glance: spend today and this month against the caps, live campaigns, connected ad accounts, every campaign with its status and budget, and how many of Siren's suggestions are open. Call first for anything about ads. Ads need Pro and the owner's ads switch for this agent; a 403 `scope_ads` says where they turn it on.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • boost_postBoost any post Siren made: it becomes a Meta ad with its own picture or video and caption, sent PAUSED.Can send data outNo findings

    Why it is in this group

    • The name "boost_post" says "post": a word for a change.

    What it can reach

    • outboundThe name "boost_post" says "post": it sends or publishes something to other people.
    Description, as the server wrote it
    Boost any post Siren made: it becomes a Meta ad with its own picture or video and caption, sent PAUSED. No credits; nothing spends until go_live_ad_campaign and the human's yes. Pass the run_id, or a post_id from list_posts (each row says boosted_campaign_id once it is). With neither it lists the posts that did best lately so you can pick one with the human. A post boosted before answers with that campaign.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • buy_creditsGet a Stripe checkout link for more credits.1 finding

    Why it is in this group

    • The description's first verb is "get": a word for reading.
    • The server marks it as not read-only (readOnlyHint: false).

    Findings

    • Warn

      The server marks "buy_credits" as not read-only (readOnlyHint: false), and its words say it reads.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The description's first verb is "get": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Get a Stripe checkout link for more credits. Give the link to the human; they pay on Stripe and the credits land in about a minute. Nothing is charged by this call. Read the balance on get_account.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • clarify_briefAsk Siren's clarifier whether a brief is specific enough to generate from.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Ask Siren's clarifier whether a brief is specific enough to generate from. Returns ready=true/false plus follow-up questions. Use before create_campaign when the user's request is vague.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • create_campaignCreate a Siren campaign from a plain-language brief — the full pipeline: plan, on-brand copy, deterministic render, verify.Can send data outNo findings

    Why it is in this group

    • The name "create_campaign" says "create": a word for a change.

    What it can reach

    • outboundThe input takes a destination (input.channel): what the tool writes goes there.
    • outboundThe input takes a URL (input.callback_url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Create a Siren campaign from a plain-language brief — the full pipeline: plan, on-brand copy, deterministic render, verify. Returns the run; pass callback_url to be pinged when it ends, or poll get_run until it finishes. Spends credits (image 10, an ad set of 3 images 20, video 25; voice or music-only is the same 25). Pass output_type to pin a film (list_films has the catalog); omit it and Siren picks. Optional scheduled_at (ISO-8601) queues a sequential post (X → Instagram → TikTok, or platforms you pass) when the render succeeds — requires Allow posting. Fails with a 402 upgrade message if the plan or balance can't cover it. FILM KNOBS: voiceover (true narrated / false music only), direction (mood, pace, motion, music in one line), music (a bed id), media (upload_media URLs the film shows). Images ignore the film knobs: Siren writes and paints them from the brief and Brand DNA. ANY BRAND: pass `brand` to make it for a brand that is not this workspace's own, e.g. brand={"name": "Acme", "site": "acme.com", "logo_url": "https://acme.com/logo.png", "primary": "#FF4400"}. Nothing of this workspace's identity leaks in. The exact same request within 24 hours returns the run it already started, as it is now, with replayed=true and no new charge. Change the brief to make another.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • create_mascotStart the brand mascot: from a description (note, kind) or from a reference picture.No findings

    Why it is in this group

    • The name "create_mascot" says "create": a word for a change.
    Description, as the server wrote it
    Start the brand mascot: from a description (note, kind) or from a reference picture. Paid plans; 100 credits. Siren paints a hero in about a minute; poll get_mascot, show the human, then mascot_step keep (build the pose sheet) or retry (paint again, 3 tries). One mascot per workspace.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • decide_ad_suggestionApply or dismiss one of Siren's suggestions.No findings

    Why it is in this group

    • The description's first verb is "apply": a word for a change.
    Description, as the server wrote it
    Apply or dismiss one of Siren's suggestions. One that raises spend answers needs_confirm first, like set_ad_budget.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • edit_assetEdit a finished ad creative in place.No findings

    Why it is in this group

    • The name "edit_asset" says "edit": a word for a change.
    Description, as the server wrote it
    Edit a finished ad creative in place. Only what the instruction names changes; faces, layout, lettering and every other pixel are kept, so you can chain edits (hair pink, then tail teal, then add a sign) without the picture drifting. About 15 seconds. 3 credits; an instruction that asks for a whole new look ("make it a comic", "make it cinematic") repaints at 10. Returns the NEW run: poll get_run until it is terminal and show the human the new image. Films are not edited this way: re-render them with render_asset. Every earlier version stays, so the human can go back to any of them.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • make_adsMake the plan's ads: a draft campaign per platform, and Siren renders each ad (spends credits like any video or ad creative; tell the human first).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Make the plan's ads: a draft campaign per platform, and Siren renders each ad (spends credits like any video or ad creative; tell the human first). Nothing reaches the platform yet. Poll get_ad_campaign.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • mascot_stepMove the mascot on: keep the hero, paint it again, or add a pose.No findings

    Why it is in this group

    • The description's first verb is "move": a word for a change.
    Description, as the server wrote it
    Move the mascot on: keep the hero, paint it again, or add a pose. Ask the human before keep, since it builds the whole sheet.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • pause_ad_campaignPause (turn off) a campaign now.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Pause (turn off) a campaign now. Always allowed: it only stops spend.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • plan_adsSiren drafts an ad plan from one prompt: goal, audience, budget inside the caps, platforms and the ads to make (shape, hook, headline, text).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Siren drafts an ad plan from one prompt: goal, audience, budget inside the caps, platforms and the ads to make (shape, hook, headline, text). Nothing is made or spent. Show the human the plan, then make_ads. With test, the versions split one budget and the verdict rule is set before any spend.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • render_assetRender films from pre-formed SirenSeed bodies (advanced).Can send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • outboundThe input takes a URL (input.callback_url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Render films from pre-formed SirenSeed bodies (advanced). FILMS ONLY: images are painted from a brief, so for any image, ad or creative call create_campaign with asset_type=card (a still here returns 422 stills_use_a_brief). Each item: {output_type, channel, seed_body, archetype?, family?, surface?, caption?, voice_id?, music?, direction?, brand_override?}. Prefer create_campaign unless the user has concrete seed JSON. Returns run ids, `estimated_seconds` and `poll_after_seconds`; wait that long, then get_run, or pass callback_url and Siren pings it once per run when each ends. THE DIRECTOR: every film body is edited against Brand DNA before it renders. It keeps the film and your brand-specific lines, rewrites empty, generic or reference-body copy, and never touches media. `director` in the response says what changed. `direction` is a free line ("dark, club energy, fast") that steers words, pace and music. A film that cannot use what you sent returns 422 film_does_not_fit with a `fix` and `films_that_fit`. ANY BRAND: put brand_override={"name": "Acme", "site": "acme.com", "logo_url": "https://acme.com/logo.png", "primary": "#FF4400", "accent": "#111111"} on an item to render it for a brand that is not this workspace's own. With a name it is a clean slate: none of this workspace's logo, mascot, font, handle, screenshots or stills are used. Media slots take only URLs you uploaded with upload_media.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • set_ad_budgetChange a campaign's daily budget, inside the caps.No findings

    Why it is in this group

    • The name "set_ad_budget" says "set": a word for a change.
    Description, as the server wrote it
    Change a campaign's daily budget, inside the caps. Lowering applies now. Raising a live campaign answers needs_confirm first: show the human the summary, then call again with the code.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • set_webhookRegister a standing webhook: Siren POSTs every run event in this workspace to the URL, so no agent has to poll.Can send data outNo findings

    Why it is in this group

    • The name "set_webhook" says "set": a word for a change.

    What it can reach

    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Register a standing webhook: Siren POSTs every run event in this workspace to the URL, so no agent has to poll. For one run only, pass callback_url to create_campaign or render_asset instead. Each POST is JSON {type, run_id, workspace_id, timestamp, data: {status, asset_url, caption, error, output_type, campaign_id}} signed with the secret: Standard Webhooks headers (webhook-id, webhook-timestamp, webhook-signature) plus X-Signature-256 (hex HMAC-SHA256 of the raw body). The secret is shown once; keep it.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • siren_helpLook up Siren itself: where something is in the app (pages, tabs, buttons), how a feature works, plans, prices, credits and policies.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Look up Siren itself: where something is in the app (pages, tabs, buttons), how a feature works, plans, prices, credits and policies. Returns up to 3 sections, each with its docs link and its place in the app (e.g. Ads → Sales). Call it before telling the human where to click or what something costs; if it returns nothing, say you're not sure and point to https://mysiren.ai/docs. Read only.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • studio_automateCreate a Studio profile on this API key.No findings

    Why it is in this group

    • The description's first verb is "create": a word for a change.
    Description, as the server wrote it
    Create a Studio profile on this API key. Returns generate curl and inbound hook URLs (Stripe, GitHub, Uptime Kuma, Product Hunt, generic). Passing delivery.social_account_ids turns on social delivery for the profile — that publishes, so it requires Allow posting.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • studio_cardRender a Studio data card from a type + body.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Render a Studio data card from a type + body. Deterministic React, no paint. Optional live post after render. Returns run_id, image url, and post url when posted.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • studio_design_packThe design tokens behind a Studio design, for building in the same language: palette, fonts, radius and shadow as `tokens`; `css` (custom properties plus a Tailwind v4 @theme block…Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    The design tokens behind a Studio design, for building in the same language: palette, fonts, radius and shadow as `tokens`; `css` (custom properties plus a Tailwind v4 @theme block); `tailwind` (a v3 theme); and `skill_md`, a short rules file to drop into the project so the agent keeps to it. Call it once the version has been exported, so `screens` carries the rendered proofs and `exported` is true. Free and read-only: it reads a design, it does not render one. Honest about scope: palette, fonts, radius and shadow; no type scale or spacing ramp yet.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • studio_editChange a Studio video by asking, as the human would in the chat.Reads text others writeNo findings

    Why it is in this group

    • The name "studio_edit" says "edit": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Change a Studio video by asking, as the human would in the chat. Only what the ask names changes; Siren replies with what it changed (before and after) and the new version number. Waits up to about 25 seconds for the reply. No credits are spent until studio_export. A greeting or a question gets an answer and no new version.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • studio_exportRender a Studio design or video to files.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Render a Studio design or video to files. Spends credits like any render: a video 25 (platinum 50), a card 10, a set 10 a slide (an App Store set of 6 is 60), charged once. A card or a set waits for the render (about a minute) and returns every file in `asset_urls`, slide 1 first; a video returns the run id: poll get_run until it is terminal, then show the human the file or post it with post_run.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • studio_startStart a video in Siren Studio from a description.Reads text others writeNo findings

    Why it is in this group

    • The name "studio_start" says "start": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Start a video in Siren Studio from a description. Siren composes the first take (about 10 to 20 seconds) and replies with what it made; nothing is rendered or charged until studio_export. Returns the thread and Siren's reply. The human sees the same thread in Studio and can keep editing it there, or you can with studio_edit.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • studio_threadsThe workspace's Studio videos, newest first: title, shelf, current version, and whether a human or an agent started it.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    The workspace's Studio videos, newest first: title, shelf, current version, and whether a human or an agent started it.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • tracking_setupThe whole Sales tracking setup as one Markdown brief for the site's developer: the tag with this workspace's key (before </head> on every page), the sign-up and purchase calls, con…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    The whole Sales tracking setup as one Markdown brief for the site's developer: the tag with this workspace's key (before </head> on every page), the sign-up and purchase calls, consent, how to check it on Ads → Sales, and where the tag goes in Next.js, React/Vite, Webflow, Framer, WordPress and Shopify. Read only. Hand `markdown` over as it is, or save it as SIREN-TRACKING.md.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • update_brand_dnaPatch Brand DNA.No findings

    Why it is in this group

    • The name "update_brand_dna" says "update": a word for a change.
    Description, as the server wrote it
    Patch Brand DNA. Send only keys to change. Nested bags (offer, product_map, icp) merge. Examples: {tagline, overview, offer: {product_name, one_liner, features, who_its_for, primary_cta}, product_map: {offerings, how_we_work}, icp: {who_buys, pains}, colour_use: {primary, secondary, accent} (when each colour should be the ground, e.g. {"accent": "loud ads that must stop the scroll"}), mark_faces: right | left | none (which way the logo looks)}. Does not read or write Brand Memory.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • update_product_screenEdit an existing brand asset: name, description, kind, use_when, and the screenshot tags (screen_type, device, theme).No findings

    Why it is in this group

    • The name "update_product_screen" says "update": a word for a change.
    Description, as the server wrote it
    Edit an existing brand asset: name, description, kind, use_when, and the screenshot tags (screen_type, device, theme).

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • upload_brand_videoAdd a product demo, walkthrough or footage to Brand DNA.Can send data outNo findings

    Why it is in this group

    • The name "upload_brand_video" says "upload": a word for a change.

    What it can reach

    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Add a product demo, walkthrough or footage to Brand DNA. With only the file, Gemini reads frames across the clip and writes what it shows, when to use it, tags and the best moments (scan_status scanning, then ready in about 15 seconds; poll list_brand_videos). Films play it when a brief names it ("launch film with our checkout demo"). Videos are for films; stills are painted from pictures.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • upload_mediaStore a photo or video the human wants in a post, from an https URL or base64.Can send data outNo findings

    Why it is in this group

    • The name "upload_media" says "upload": a word for a change.

    What it can reach

    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Store a photo or video the human wants in a post, from an https URL or base64. Returns a workspace-owned URL to put in any media slot of a film body (describe_film lists the slots) — the renderer reads it directly. Images: PNG/JPG/WebP up to 15 MB. Videos: MP4/MOV/WebM up to 200 MB. The same bytes are stored once (content-hashed).

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • upload_product_screenUpload a brand asset (product photo, app screenshot, packaging) into Brand DNA and store it on R2.No findings

    Why it is in this group

    • The name "upload_product_screen" says "upload": a word for a change.
    Description, as the server wrote it
    Upload a brand asset (product photo, app screenshot, packaging) into Brand DNA and store it on R2. Pass image_url (https PNG/JPG/WebP) or image_base64. Two ways to file it: - Send `description` (and optionally kind, use_when, tags, name): Siren trusts your words and files the asset as-is. No read. - Send only the file: Gemini reads the picture and writes name, kind, description, use_when, tags itself. scan_status goes scanning → ready in about 8 seconds; poll list_product_screens. kind is free text ("product photo", "dashboard screenshot", "packaging"), there is no fixed list. A brief that names an asset ("advertise the pink handbag") pulls that file into the still. screen_type / device / theme only matter for device-framed screenshot masters.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
Only reads 22Show 22 read-only tools
  • describe_filmThe full contract for one film: what it is and when to hire it, its body JSON Schema, a reference body, the seed envelope, media slots (which fields take image/video URLs), the bra…No findings

    Why it is in this group

    • The name "describe_film" says "describe": a word for reading.
    Description, as the server wrote it
    The full contract for one film: what it is and when to hire it, its body JSON Schema, a reference body, the seed envelope, media slots (which fields take image/video URLs), the brand prefills (colours, logo, screens) and the override rules. Call it before writing a render_asset body.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_accountGet the connected Siren workspace: plan, key scopes, auto-post setting, and daily limit.Reads text others writeNo findings

    Why it is in this group

    • The name "get_account" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "get" and "post": it reads posts, which other people can write.
    Description, as the server wrote it
    Get the connected Siren workspace: plan, key scopes, auto-post setting, and daily limit. Call this first to learn what the account can do before generating. Empty asset_types / channels / connected_accounts lists mean UNRESTRICTED, not missing — never stop on them. Films render on every plan; credits are the only meter.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_ad_campaignOne ad campaign: its plan, the Page it runs as, and each ad with its creative (asset_url), shape, copy and status.No findings

    Why it is in this group

    • The name "get_ad_campaign" says "get": a word for reading.
    Description, as the server wrote it
    One ad campaign: its plan, the Page it runs as, and each ad with its creative (asset_url), shape, copy and status. Poll this after make_ads until every ad is ready, and after send_ads_to_platform until it is paused.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_ad_capsThe spend caps every change must fit (a day and a month, across all platforms), what's spent this month and the room left.No findings

    Why it is in this group

    • The name "get_ad_caps" says "get": a word for reading.
    Description, as the server wrote it
    The spend caps every change must fit (a day and a month, across all platforms), what's spent this month and the room left. Caps are raised only by the human on the Ads page, never by an agent.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_brand_dnaGet this workspace's Brand DNA: brand_name, brand_kind, overview, tagline, offer, features, products, audience, palette, logos, plus `checks`: what to fix before rendering (thin Br…No findings

    Why it is in this group

    • The name "get_brand_dna" says "get": a word for reading.
    Description, as the server wrote it
    Get this workspace's Brand DNA: brand_name, brand_kind, overview, tagline, offer, features, products, audience, palette, logos, plus `checks`: what to fix before rendering (thin Brand DNA, a typed accent the brand's own work does not use). Call right after get_account; fix thin DNA first with update_brand_dna and upload_product_screen, or ask the human for the site. Not Brand Memory.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_mascotThe workspace mascot: status (hero, keeping, frames, ready), the hero picture, tries left, and every pose frame with its URL.No findings

    Why it is in this group

    • The name "get_mascot" says "get": a word for reading.
    Description, as the server wrote it
    The workspace mascot: status (hero, keeping, frames, ready), the hero picture, tries left, and every pose frame with its URL. Null mascot = none yet.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_performanceHow the posts did: totals (impressions, engagement, replies, engagement rate) and the top posts with views, likes and replies.Reads text others writeNo findings

    Why it is in this group

    • The name "get_performance" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "post": it reads posts, which other people can write.
    Description, as the server wrote it
    How the posts did: totals (impressions, engagement, replies, engagement rate) and the top posts with views, likes and replies.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • get_runGet one run by id — full status, output text, asset URLs, caption, and any error.No findings

    Why it is in this group

    • The name "get_run" says "get": a word for reading.
    Description, as the server wrote it
    Get one run by id — full status, output text, asset URLs, caption, and any error. Poll this after create_campaign or render_asset until status is terminal. Wait `poll_after_seconds` between polls; `progress` and `eta_seconds` say how far along it is. A finished film carries `film_check`, advice only: when `ok` is false, show the human the video and the findings and let them decide. Re-render at most once, and only for a defect you can name in what you sent (a missing image, a wrong name). `notices` are plain-words notes on the request (e.g. it asked for a mood the brand's look does not wear): the asset is made as asked; pass the note to the human. A finished run carries `caption`: the post caption Siren wrote in the run's brand (or yours, if you passed one); show it with the asset. After post_run, `posts[]` carries each platform's status and, once it fires, the live URL and the caption that went out.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_ad_campaignsEvery ad campaign: platform, status (draft, launching, paused, active), daily budget, spend, clicks and results so far, plus the caps.No findings

    Why it is in this group

    • The name "list_ad_campaigns" says "list": a word for reading.
    Description, as the server wrote it
    Every ad campaign: platform, status (draft, launching, paused, active), daily budget, spend, clicks and results so far, plus the caps.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_ad_suggestionsSiren's open suggestions from its daily review (pause an ad with no clicks, cut a costly one, give a winner more), each with its reason.Reads text others writeNo findings

    Why it is in this group

    • The name "list_ad_suggestions" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
    Description, as the server wrote it
    Siren's open suggestions from its daily review (pause an ad with no clicks, cut a costly one, give a winner more), each with its reason.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_brand_videosThe brand's own clips in Brand DNA: name, what each shows, when to use it, tags, best moments with timestamps, poster and scan_status.No findings

    Why it is in this group

    • The name "list_brand_videos" says "list": a word for reading.
    Description, as the server wrote it
    The brand's own clips in Brand DNA: name, what each shows, when to use it, tags, best moments with timestamps, poster and scan_status.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_filmsThe film library, one ranked page at a time.No findings

    Why it is in this group

    • The name "list_films" says "list": a word for reading.
    Description, as the server wrote it
    The film library, one ranked page at a time. Films sit on job shelves; pass job and the human's goal and hire from the top of the page. Each film says what it is, when to hire it, its length and shapes, fits_this_brand (with what is missing) and made_recently (this brand already got it: prefer another film on the shelf unless the human asked for that one). Page on with next_page. Want it all at once? all=true, or fetch the catalog file (https://api.mysiren.ai/api/v1/films.md, every film by shelf, also .txt/.json) and read it in steps. search= finds films by word. Then describe_film for the body. Videos are on every plan; credits are the only limit. Every film here is 25 credits. Platinum films (50 credits) are not in these pages: the answer's platinum section flags them, and list_platinum_films has the shelf.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_mediaPhotos and videos uploaded with upload_media, newest first, with their URLs.No findings

    Why it is in this group

    • The name "list_media" says "list": a word for reading.
    Description, as the server wrote it
    Photos and videos uploaded with upload_media, newest first, with their URLs. Reuse a URL in create_campaign media or a film body.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_peopleThe people library: team faces Siren can put in stills (name, role, team, status cropping or ready, round crop URL).No findings

    Why it is in this group

    • The name "list_people" says "list": a word for reading.
    Description, as the server wrote it
    The people library: team faces Siren can put in stills (name, role, team, status cropping or ready, round crop URL).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_platinum_filmsThe platinum shelf: studio-grade films that match a top motion studio's craft, told as the brand's own story.No findings

    Why it is in this group

    • The name "list_platinum_films" says "list": a word for reading.
    Description, as the server wrote it
    The platinum shelf: studio-grade films that match a top motion studio's craft, told as the brand's own story. Each costs 50 credits, every time (a normal film is 25). Offer one only when the human is making a big launch they genuinely want to go far; everyday posts and normal budgets use list_films. Say the price before you render. Ids end in -plt. Platinum needs a paid plan or a credit top-up: a complimentary plan sees it but gets 402 platinum_needs_paid_plan. voice MM = motion and music only (no voice-over question, no narration); MVM = motion, voice and music. Then describe_film for the body, same as any film.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_postsEvery post Siren sent or queued: platform, status, live URL, time, and counts by status (posted, queued, failed).Reads text others writeNo findings

    Why it is in this group

    • The name "list_posts" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe name "list_posts" says "list" and "post": it reads posts, which other people can write.
    • untrusted-inputThe description's first sentence says "post": it reads posts, which other people can write.
    Description, as the server wrote it
    Every post Siren sent or queued: platform, status, live URL, time, and counts by status (posted, queued, failed).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_product_screensList the brand assets in Brand DNA: product photos, app screenshots, packaging.No findings

    Why it is in this group

    • The name "list_product_screens" says "list": a word for reading.
    Description, as the server wrote it
    List the brand assets in Brand DNA: product photos, app screenshots, packaging. Each row has name, kind, description, use_when, tags, scan_status (scanning / ready / failed), device, theme, url.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_runsList the workspace's generation runs (newest first): status, brief, channel, asset URLs, and caption.No findings

    Why it is in this group

    • The name "list_runs" says "list": a word for reading.
    Description, as the server wrote it
    List the workspace's generation runs (newest first): status, brief, channel, asset URLs, and caption. Page with offset to see them all.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_stylesThe still style library, one ranked page at a time.No findings

    Why it is in this group

    • The name "list_styles" says "list": a word for reading.
    Description, as the server wrote it
    The still style library, one ranked page at a time. Every painted still (an ad creative, poster, release card, App Store frame, thumbnail) is one style; Siren picks one when you don't. Styles sit on section shelves; pass section and the human's goal and take one from the top. made_recently = this brand already got that look, prefer another. To paint in a style, put its id in the create_campaign brief (asset_type card). The whole library as one file: https://api.mysiren.ai/api/v1/styles.md (also .txt/.json).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_webhooksThis workspace's standing webhooks: URL, events, and the last delivery's status.Reads text others writeNo findings

    Why it is in this group

    • The name "list_webhooks" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    This workspace's standing webhooks: URL, events, and the last delivery's status. Secrets are never shown again.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • studio_getOne Studio video: the chat so far (who said what, with diffs), every version, and which version is current.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "studio_get" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "chat": it reads messages.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "chat": it reads messages, which other people can write.
    Description, as the server wrote it
    One Studio video: the chat so far (who said what, with diffs), every version, and which version is current.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • studio_templatesList Siren Studio's 33 React data-card types with family, description, and body schema.No findings

    Why it is in this group

    • The description's first verb is "list": a word for reading.
    Description, as the server wrote it
    List Siren Studio's 33 React data-card types with family, description, and body schema. Use this before studio_card so the body matches.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

135 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write15
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out9
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__siren__studio_get"
    ]
  }
}

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:26 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
48
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://mcp.mysiren.ai/.well-known/oauth-protected-resource/mcp
Authorization servers
https://mcp.mysiren.ai
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 48 tools that change things (9 destructive, 1 irreversible, 38 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.mysiren.ai/mcp: tools/list returned 70 tools to an anonymous client, including post_run (destructive), schedule_post (destructive), delete_product_screen (destructive), delete_person (destructive), delete_webhook (destructive) and 43 more

    What this check looks for

Posture changes

  1. Nov 20, 2026
    • Tools that change things, listed without credentials: 46 to 48
  2. Nov 6, 2026
    • Tools that change things, listed without credentials: 28 to 46
  3. Oct 29, 2026
    • Tools that change things, listed without credentials: 27 to 28

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "buy_credits" as not read-only (readOnlyHint: false), and its words say it reads.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The description's first verb is "get": a word for reading.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. PostureRemote posture changed. Tools that change things, listed without credentials: 46 -> 48.View diff
    • Tools that change things, listed without credentials: 46 to 48
  2. Tools3 added, 4 changed.+3 added~4 changedView diff
  3. Tools22 added, 1 changed.+22 added~1 changedView diff
  4. PostureRemote posture changed. Tools that change things, listed without credentials: 28 -> 46.View diff
    • Tools that change things, listed without credentials: 28 to 46
  5. PostureRemote posture changed. Tools that change things, listed without credentials: 27 -> 28.View diff
    • Tools that change things, listed without credentials: 27 to 28
  6. Tools1 added.+1 addedView diff

Install

Pinned to version 1.1.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http siren https://mcp.mysiren.ai/mcp
claude mcp add --transport http siren https://mcp.mysiren.ai/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__siren__get_account",
      "mcp__siren__list_runs",
      "mcp__siren__get_run",
      "mcp__siren__list_films",
      "mcp__siren__list_platinum_films",
      "mcp__siren__list_styles",
      "mcp__siren__describe_film",
      "mcp__siren__get_brand_dna",
      "mcp__siren__list_product_screens",
      "mcp__siren__get_mascot",
      "mcp__siren__list_people",
      "mcp__siren__list_webhooks",
      "mcp__siren__list_media",
      "mcp__siren__get_performance",
      "mcp__siren__list_posts",
      "mcp__siren__list_ad_campaigns",
      "mcp__siren__get_ad_campaign",
      "mcp__siren__get_ad_caps",
      "mcp__siren__list_ad_suggestions",
      "mcp__siren__list_brand_videos",
      "mcp__siren__studio_templates",
      "mcp__siren__studio_get"
    ],
    "ask": [
      "mcp__siren__create_campaign",
      "mcp__siren__clarify_brief",
      "mcp__siren__render_asset",
      "mcp__siren__upload_media",
      "mcp__siren__edit_asset",
      "mcp__siren__update_brand_dna",
      "mcp__siren__upload_product_screen",
      "mcp__siren__update_product_screen",
      "mcp__siren__upload_logo",
      "mcp__siren__create_mascot",
      "mcp__siren__mascot_step",
      "mcp__siren__add_person",
      "mcp__siren__set_webhook",
      "mcp__siren__buy_credits",
      "mcp__siren__ads_overview",
      "mcp__siren__ad_performance",
      "mcp__siren__ad_account_balance",
      "mcp__siren__ad_autopilot",
      "mcp__siren__siren_help",
      "mcp__siren__ad_conversions",
      "mcp__siren__tracking_setup",
      "mcp__siren__ad_audiences",
      "mcp__siren__ad_tests",
      "mcp__siren__ad_alerts",
      "mcp__siren__boost_post",
      "mcp__siren__plan_ads",
      "mcp__siren__make_ads",
      "mcp__siren__send_ads_to_platform",
      "mcp__siren__pause_ad_campaign",
      "mcp__siren__set_ad_budget",
      "mcp__siren__decide_ad_suggestion",
      "mcp__siren__upload_brand_video",
      "mcp__siren__studio_card",
      "mcp__siren__studio_automate",
      "mcp__siren__studio_start",
      "mcp__siren__studio_edit",
      "mcp__siren__studio_design_pack",
      "mcp__siren__studio_threads",
      "mcp__siren__studio_export"
    ],
    "deny": [
      "mcp__siren__post_run",
      "mcp__siren__schedule_post",
      "mcp__siren__delete_product_screen",
      "mcp__siren__delete_person",
      "mcp__siren__delete_webhook",
      "mcp__siren__go_live_ad_campaign",
      "mcp__siren__delete_brand_video",
      "mcp__siren__delete_media",
      "mcp__siren__studio_schedule"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as siren. Review it before you use it.

Capability tags behind 22 rules
  • mcp__siren__get_account untrusted-input
  • mcp__siren__create_campaign outbound
  • mcp__siren__render_asset outbound
  • mcp__siren__upload_media outbound
  • mcp__siren__post_run untrusted-input, outbound
  • mcp__siren__schedule_post untrusted-input, outbound
  • mcp__siren__set_webhook outbound
  • mcp__siren__list_webhooks untrusted-input
  • mcp__siren__get_performance untrusted-input
  • mcp__siren__list_posts untrusted-input
  • mcp__siren__list_ad_suggestions untrusted-input
  • mcp__siren__boost_post outbound
  • mcp__siren__send_ads_to_platform outbound
  • mcp__siren__go_live_ad_campaign untrusted-input
  • mcp__siren__upload_brand_video outbound
  • mcp__siren__studio_schedule untrusted-input
  • mcp__siren__studio_start untrusted-input
  • mcp__siren__studio_edit untrusted-input
  • mcp__siren__studio_get private-data, untrusted-input
  • mcp__siren__studio_design_pack untrusted-input
  • mcp__siren__studio_threads untrusted-input
  • mcp__siren__studio_export untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/ai.mysiren/siren/verify?hash=bb618250b551194bd1dd9664e7e74445013efd5aa95178c2a7cb647d6b3cf00c" | jq -e '.changed == false'

Pinned hash bb618250b551, from Nov 20, 2026, 10:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/ai.mysiren/siren/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for ai.mysiren/siren
[![Anlyon Radar](https://radar.anlyon.com/badge/ai.mysiren/siren.svg)](https://radar.anlyon.com/servers/ai.mysiren/siren)

Source: MCP Registry · repository. Synced Nov 20, 2026, 10:17 UTC.

Siren MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Siren MCP server safe?

No scan can promise that. What its definitions show: 70 tools, 48 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Siren MCP server delete data?

Yes. 9 tools can delete, cancel or revoke something: post_run, schedule_post, delete_product_screen, delete_person, delete_webhook, go_live_ad_campaign and 3 more.

Can the Siren MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: send_ads_to_platform.

What tools does the Siren MCP server have?

70 tools: 9 destructive, 1 irreversible, 38 write, 22 read. post_run, schedule_post, delete_product_screen, delete_person, delete_webhook, go_live_ad_campaign, delete_brand_video, delete_media and 62 more.

Does the Siren MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Siren MCP server send data to outside services?

9 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): create_campaign, render_asset, upload_media, post_run, schedule_post, set_webhook and 3 more.

Has the Siren MCP server changed its tools?

Yes, 3 times since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.