SocialShot AI MCP server
ai.socialshot/socialshotsocialshot.aistreamable-httpv1.0.0Scanned
AI product photos for ecommerce: turn product images into studio, lifestyle and on-model photos.
5 tools: 1 change things and 4 only read.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here changes things. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
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 SocialShot AI MCP server can do
The SocialShot AI MCP server is published by socialshot.ai, a domain the MCP Registry verified. It has 5 tools. It can create or change data (1 tool: create_photoshoot_batch), but cannot delete data. 4 tools only read.
2 tools bring in text other people can write (create_photoshoot_batch and get_job).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 9, 2026, version 1.0.0.
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.
5 tools
Changes things 1Claude Code: ask
create_photoshoot_batchCOSTS MONEY: every successful submission spends real, paid credits from the account's SocialShot balance (about credits_estimated in the result; higher tier / output_quality cost m…Reads text others writeNo findings
Why it is in this group
- The name "create_photoshoot_batch" says "create": 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 COSTS MONEY: every successful submission spends real, paid credits from the account's SocialShot balance (about credits_estimated in the result; higher tier / output_quality cost more). Only call it when the user has asked for images to be generated, and check get_account (credits, dailyCap) first. Queues AI product-photoshoot generation for 1-50 publicly reachable product image URLs (one output each) and returns batch_id, total and credits_estimated immediately; poll with wait_for_job or get_job. Identical inputs never charge twice: they reuse an idempotency_key derived from the inputs, so the server replays the ORIGINAL batch (idempotent_replay: true) and no new images are made. Pass force_new: true only when the user explicitly wants a new, separately charged run of the same inputs.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 4Show 4 read-only tools
get_accountShop metadata, plan, credit balance and dailyCap {used, limit, resetsAt} (the rolling 24-hour API credit cap) for this API key.No findings
Why it is in this group
- The name "get_account" says "get": a word for reading.
Description, as the server wrote it Shop metadata, plan, credit balance and dailyCap {used, limit, resetsAt} (the rolling 24-hour API credit cap) for this API key. Free; call before spending credits.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_jobStatus of a photoshoot batch: per-item status and output_url.Reads text others writeNo findings
Why it is in this group
- The name "get_job" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "status" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Status of a photoshoot batch: per-item status and output_url. The batch is done when `settled` >= `expected_total`. `total` only counts rows written so far, so it can lag while the queue drains.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
list_optionsCatalog of accepted generation options (currently the output tiers).No findings
Why it is in this group
- The name "list_options" says "list": a word for reading.
Description, as the server wrote it Catalog of accepted generation options (currently the output tiers). Free.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
wait_for_jobPoll a batch (backoff 2s up to 10s) until every item is completed or failed, or until timeout.No findings
Why it is in this group
- The name "wait_for_job" says "wait": a word for reading.
Description, as the server wrote it Poll a batch (backoff 2s up to 10s) until every item is completed or failed, or until timeout. Pass expected_total (the `total` from create_photoshoot_batch) until the server reports its own. On timeout returns done=false with the latest status; call again to keep waiting.
Annotations the server declares
- readOnlyHint: 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.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
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.
Looked at Nov 17, 2026, 15:20 UTC, unchanged since Nov 10, 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
- 1
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.socialshot.ai/mcp: tools/list returned 5 tools to an anonymous client, including create_photoshoot_batch (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http socialshot https://api.socialshot.ai/mcp --header 'Authorization: <your-authorization>'claude mcp add --transport http socialshot https://api.socialshot.ai/mcp --header 'Authorization: <your-authorization>'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.
{
"permissions": {
"allow": [
"mcp__socialshot__get_account",
"mcp__socialshot__list_options",
"mcp__socialshot__get_job",
"mcp__socialshot__wait_for_job"
],
"ask": [
"mcp__socialshot__create_photoshoot_batch"
],
"deny": []
}
}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 socialshot. Review it before you use it.
Capability tags behind 2 rules
- mcp__socialshot__create_photoshoot_batch untrusted-input
- mcp__socialshot__get_job 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.socialshot/socialshot/verify?hash=c493b4afba8b87d4c49884a8cef4db092f91d27303abc8e58be11439706a60a4" | jq -e '.changed == false'Pinned hash c493b4afba8b, from Nov 9, 2026, 21:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.socialshot/socialshot/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.socialshot/socialshot)Source: MCP Registry. Synced Nov 9, 2026, 21:17 UTC.
SocialShot AI MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the SocialShot AI MCP server safe?
- No scan can promise that. What its definitions show: 5 tools, 1 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the SocialShot AI MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the SocialShot AI MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the SocialShot AI MCP server have?
- 5 tools: 1 write, 4 read. create_photoshoot_batch, get_account, list_options, get_job and wait_for_job.
Does the SocialShot AI MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the SocialShot AI MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the SocialShot AI MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 9, 2026.