Skip to content

meta-agent-tools MCP server

br.app.classificado/meta-agent-toolsclassificado.app.brstreamable-httpv1.0.0Scanned

Registry of MCP servers, agent skills and plugins: search, filter, comments, likes, publish.

49 tools: 2 can delete or cancel things, 28 change things and 19 only read.

Tools: 2 delete, 0 irreversible, 28 write, 19 read.
  • Reads private data · 4
  • Reads text others write · 6
  • Can send data out · 5
  • 14 findings

Tools listed without sign-in. Remote posture

Anlyon alternative

30 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

What the meta-agent-tools MCP server can do

The meta-agent-tools MCP server is published by classificado.app.br, a domain the MCP Registry verified. It has 49 tools. It can delete or cancel things (2 tools: unwatch_tool and cancel_plan) and create or change data (28 tools: index_stats, watch_dependency_changes, feed_posts, feed_post and 24 more). 19 tools only read.

4 tools read private data (search_bundles, get_bundle, listing_dependencies and 1 more); 6 tools bring in text other people can write (get_bundle, mcp_index_search, listing_security and 3 more); 5 tools can send data out of your system (feed_posts, feed_post, check_tool and 2 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 14 findings (annotation-conflict and credentials-mention). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.

Last scanned Nov 12, 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.

49 tools

Deletes or cancels 2Claude Code: deny
  • cancel_planCancel the active plan.1 finding

    Why it is in this group

    • The name "cancel_plan" says "cancel": a word for removing or ending something.
    • The server marks it not destructive (destructiveHint: false), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "cancel_plan" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false}; The name "cancel_plan" says "cancel": a word for removing or ending something.

      What this check looks for
    Description, as the server wrote it
    Cancel the active plan. Nothing else is charged; a purchase under 7 days and a paid period that has not started are refunded and end now, and the rest of the paid period stays active until keeps_until. Requires accept_data_removal: true. Send `{ "accept_data_removal": true }`. The monthly card subscription stops. A purchase made less than 7 days ago and a paid period that has not started yet, such as a renewal, go back the same way they were paid (card or Pix) and end now. The rest of the paid period stays active until `keeps_until`; then what the plan added ends (`account.cancel.losses` in `GET /api/plans` says what). A purchase paid with USDC or with credit from another purchase stays active until its end; ask for its refund by e-mail, as the cancellation page says.

    Annotations the server declares

    • title: Cancel plan
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
  • unwatch_toolStop watching a server; its slot becomes free.No findings

    Why it is in this group

    • The description's first verb is "stop": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Stop watching a server; its slot becomes free.

    Annotations the server declares

    • title: Unwatch tool
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
Changes things 28Claude Code: ask
  • api_accessMonthly data package and private purchase status, without charging.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
    Monthly data package and private purchase status, without charging. MAT-only balance; pass prefix mat_. Catalog discovery and ordinary browsing are free. GPTBot, ClaudeBot, CCBot, Meta-ExternalAgent, Amazonbot, AhrefsBot and MJ12bot share a daily allowance of 1,000 reads per crawler family; over it the answer is 402 with the MAT reads package: US$ 1 for 1,000 reads for 30 days, with no automatic renewal. Buy it at POST /api/acesso and send its pass in X-API-Pass. The MAT allowance is separate from the company, address and procurement indexes.

    Annotations the server declares

    • title: API access
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • api_access_buyBuy 1,000 basic data reads for US$1, valid for 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.
    Description, as the server wrote it
    Buy 1,000 basic data reads for US$1, valid for 30 days. Requires explicit payment. MAT-only balance; pass prefix mat_. Catalog discovery and ordinary browsing are free. GPTBot, ClaudeBot, CCBot, Meta-ExternalAgent, Amazonbot, AhrefsBot and MJ12bot share a daily allowance of 1,000 reads per crawler family; over it the answer is 402 with the MAT reads package: US$ 1 for 1,000 reads for 30 days, with no automatic renewal. Buy it at POST /api/acesso and send its pass in X-API-Pass. The MAT allowance is separate from the company, address and procurement indexes.

    Annotations the server declares

    • title: API access buy
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
  • api_indexSelf-describing index: the whole API surface, with quota and quickstart.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
    Self-describing index: the whole API surface, with quota and quickstart.

    Annotations the server declares

    • title: API index
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • api_usageRemaining MAT read credits, without consuming credit.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
    Remaining MAT read credits, without consuming credit.

    Annotations the server declares

    • title: API usage
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • briefings_topicsWhich engineering topics have curated briefings, how many links each has and the newest links across all of them.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
    Which engineering topics have curated briefings, how many links each has and the newest links across all of them. Each link comes with its source, source type and a two-line summary. Topics are public bookmark folders (CUDA, inference, RAG, agents…). Each item is a post someone saved, its main source, the source type and a two-line summary in English and Portuguese. `?resumo=1` returns only `total` and each topic's `slug` and `total`. 404 until the first publication.

    Annotations the server declares

    • title: Briefings topics
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • buy_planBuy a plan: vaga (1 more tool), equipe (50 more tools and up to 10 private projects), empresa (500 more tools and up to 10 private projects).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
    Buy a plan: vaga (1 more tool), equipe (50 more tools and up to 10 private projects), empresa (500 more tools and up to 10 private projects). Each purchase lasts 30 days, with no automatic renewal. Answers 402 with the price; pay with x402 or prepaid credit and repeat. Each purchase lasts 30 days, with no automatic renewal. Without payment, the answer is 402 with the price. Pay with prepaid credit (`X-Credito`) or x402 (`PAYMENT-SIGNATURE` v2 or `X-PAYMENT` v1). Without an account, the verified paying wallet owns the purchase. Use wallet agent authentication to read its plan, or claim it after account sign-in. The `compra` mark prevents repeat credit debits. An x402 nonce can settle only once; keep the receipt after a delivery error.

    Annotations the server declares

    • title: Buy plan
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
  • check_toolBefore installing a remote MCP server, check its address: signals from the address itself (consumer tunnel, no TLS), the catalog listings with that address or host and their securi…Can send data out1 finding

    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

    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Findings

    • Info

      The input schema at properties.url.description mentions "credentials".

      Matched text

      inputSchema.properties.url.description: "...(s) endpoint of the MCP server, without credentials."

      What this check looks for
    Description, as the server wrote it
    Before installing a remote MCP server, check its address: signals from the address itself (consumer tunnel, no TLS), the catalog listings with that address or host and their security level, and facts about its domain. Never visits the address. Send the endpoint URL. The answer never contacts that address: it reads what our weekly visits measured and what our domain data knows. `address_signals` comes from the address alone (consumer tunnel, `http://` without TLS). `records` lists the catalog listings with this exact address first (`exato: true`), then up to 20 others on the same host, each with its level and signals; `same_host` counts them all. `domain` has the facts about the host's domain. An address outside the catalog answers `no_catalogo: false` and `register`: submit it to get it reviewed. Cached for 5 minutes.

    Annotations the server declares

    • title: Check tool
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • claude_code_allowlistThe watch list as Claude Code managed settings (allowedMcpServers, deniedMcpServers) and claude mcp add commands.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 watch list as Claude Code managed settings (allowedMcpServers, deniedMcpServers) and claude mcp add commands. `managed_settings` goes into a Claude Code managed settings source (see `docs`). `allowManagedMcpServersOnly` restricts user-added servers to this list. Checked servers rated as `risk` go to `deniedMcpServers`. The exact URL and that URL followed by `?*` permit the checked route with optional query parameters. Expired or unchecked items stay out. `commands` has one quoted `claude mcp add` command per allowed server.

    Annotations the server declares

    • title: Claude Code allowlist
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • contactWrite to the people behind the product: a question, or a sponsorship/partnership/advertising proposal.No findings

    Why it is in this group

    • The description's first verb is "write": a word for a change.
    Description, as the server wrote it
    Write to the people behind the product: a question, or a sponsorship/partnership/advertising proposal. Free, no captcha and no payment; one message every 10 s per network (one that arrives sooner waits its turn). One route for a question and for a sponsorship, partnership or ad proposal (`type`, with the placements of `GET /api/partners`). No captcha, no account, no payment. One message every 10 seconds per network: one that arrives sooner waits its turn and then goes out — no error. The message reaches the team by e-mail, with `email` as the reply address. For voice, send multipart/form-data: `dados` is this JSON (up to 32 KiB), and `audio` is one WebM, Ogg or M4A audio file (up to 2 MB). Audio can replace message. The browser records up to two minutes. Audio is attached to the owner's e-mail.

    Annotations the server declares

    • title: Contact
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
  • create_guestCreates a guest mr_… Asks for no e-mail.No findings

    Why it is in this group

    • The name "create_guest" says "create": a word for a change.
    Description, as the server wrote it
    Creates a guest mr_… Asks for no e-mail. Publishing a listing is what requires an account (or a payment). At most 20 new guests per network per hour; a browser that already has one gets it back from the `mr_guest` cookie.

    Annotations the server declares

    • title: Create guest
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
  • create_listingSubmit an MCP server, skill or plugin for review.Can send data out1 finding

    Why it is in this group

    • The name "create_listing" says "create": 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.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...pi` (`GET /api/listings/:id/status`, no credential) to learn the decision. A person or age..."

      What this check looks for
    Description, as the server wrote it
    Submit an MCP server, skill or plugin for review. Free with an account; US$ 0.10 without one. Limit: one submission a day and three in the queue per owner. Automatic review approves supported low-risk MCP listings; uncertain cases wait for a person. Poll `status_api` (`GET /api/listings/:id/status`, no credential) to learn the decision. A person or agent can submit without an account for US$ 0.10, paid through x402 or prepaid credit; with an account, it is free. Each owner can submit once a day and keep up to three submissions in the queue. For a skill, provide its SKILL.md URL. The service checks the body and quota before charging. An invalid body returns 400; an exhausted quota returns 429.

    Annotations the server declares

    • title: Create listing
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
  • feed_postRead one post whole: the body in Markdown (`content`) and the author's formatting as safe HTML (`content_html`), plus the link to the original.Can send data out1 finding

    Why it is in this group

    • The name "feed_post" says "post": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • outboundThe name "feed_post" says "post": it sends or publishes something to other people.

    Findings

    • Warn

      The server marks "feed_post" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true}; The name "feed_post" says "post": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Read one post whole: the body in Markdown (`content`) and the author's formatting as safe HTML (`content_html`), plus the link to the original. `ord` comes from feed_posts; 0 is the newest. Two bodies for the same post, both from the copy we stored when we READ the feed — a request never fetches the site: `content_html` keeps the author's formatting through an allowlist (only known tags and attributes survive; script, style, iframe and event handlers are dropped with their content), and `content` is the same text as Markdown — the shape an agent usually wants. Neither can carry script. 404 when the feed or the position is unknown.

    Annotations the server declares

    • title: Feed post
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • feed_postsWhat has this feed published?Can send data out1 finding

    Why it is in this group

    • The name "feed_posts" says "post": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • outboundThe name "feed_posts" says "post": it sends or publishes something to other people.

    Findings

    • Warn

      The server marks "feed_posts" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true}; The name "feed_posts" says "post": a word for a change.

      What this check looks for
    Description, as the server wrote it
    What has this feed published? The posts of one feed as our queue read them — title, date, author, summary, categories and enclosure, without the body. Find the feed first (feed_find or feed_search); this takes an id from this index, never a URL. Up to 40 posts, in the order the feed publishes them, WITHOUT the body — the body of one post comes from `/items/:ord`. It is OUR copy, read on our own schedule — not the live feed and not a proxy: the only thing this endpoint accepts is an id from this index, never a URL. `read_at` says when we read it. Empty list when the feed has not been read yet.

    Annotations the server declares

    • title: Feed posts
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • get_api_x402_checkChecks an MCP server address for an agent, paid per call: what we measured, the catalog listings and the domain facts.Reads text others writeCan send data out2 findings

    Why it is in this group

    • The name "get_api_x402_check" says "get": a word for reading.
    • The server marks it as not read-only (readOnlyHint: false).

    What it can reach

    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Findings

    • Info

      The input schema at properties.url.description mentions "credentials".

      Matched text

      inputSchema.properties.url.description: "...(s) endpoint of the MCP server, without credentials."

      What this check looks for
    • Warn

      The server marks "get_api_x402_check" as not read-only (readOnlyHint: false), and its words say it reads.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false}; The name "get_api_x402_check" says "get": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Checks an MCP server address for an agent, paid per call: what we measured, the catalog listings and the domain facts. The answer of `GET /api/check`, sold per call to agents, with no account and no allowance before. A request without payment gets the 402 with the price; a paid one gets the check in the same response, with the payment in `cobranca`. The check never visits the address. When the check is unavailable, the answer is 503 and nothing is charged.

    Annotations the server declares

    • title: Get API X402 check
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
  • go_listing302 hop to the listing's origin (counts a visit).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
    302 hop to the listing's origin (counts a visit). Counts at most 1 visit per owner per day. The `X-Visit-Counted` header says whether this call counted — it is how the client knows without counting twice. A remote MCP server goes to its repository; without one, to the listing page `/l/:id`, which shows the endpoint to copy, and no visit counts.

    Annotations the server declares

    • title: Go listing
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • healthLiveness and the commit deployed right now — it is how the smoke waits for its own deploy.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
    Liveness and the commit deployed right now — it is how the smoke waits for its own deploy.

    Annotations the server declares

    • title: Health
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • index_statsSize of the index by provenance and when it last changed.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
    Size of the index by provenance and when it last changed.

    Annotations the server declares

    • title: Index stats
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • like_listingLikes the listing; DELETE undoes it.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
    Likes the listing; DELETE undoes it. Calling again does not add up: the counter counts people.

    Annotations the server declares

    • title: Like listing
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
  • list_commentsComments on a live listing.Reads text others write2 findings

    Why it is in this group

    • The name "list_comments" says "list": a word for reading.
    • The description's first verb is "comment": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe name "list_comments" says "list" and "comment": it reads comments, which other people can write.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "Comments on a live listing. With a credential on the call, each comment of yours come..."

      What this check looks for
    • Warn

      The server marks "list_comments" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true}; The name "list_comments" says "list": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Comments on a live listing. With a credential on the call, each comment of yours comes with `mine: true`.

    Annotations the server declares

    • title: List comments
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • listing_toolsThe tools and instructions a remote MCP server announced at its last check, with what they mention doing and any suspicious 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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    The tools and instructions a remote MCP server announced at its last check, with what they mention doing and any suspicious text. 404 tools_not_read when the server was not read yet. The announced manifest, normalized: each tool's name, title, description (up to 4,000 characters), input schema (null above 8,000 characters) and protocol annotations, plus the server instructions. `capabilities` and `suspicions` come from the current rules, applied when you read. Reading this endpoint never contacts the server. Cached for 5 minutes.

    Annotations the server declares

    • title: Listing tools
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • listing_updatesRefresh up to 100 selected listings in one batch instead of opening each listing.1 finding

    Why it is in this group

    • The name "listing_updates" says "update": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "listing_updates" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true}; The name "listing_updates" says "update": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Refresh up to 100 selected listings in one batch instead of opening each listing. The catalog stores the values seen at the last real change of a listing; counters and package versions change over time. After a search, use this batch or MCP listing_updates before comparing versions. These values may be cached for up to 15 minutes; `generated_at` is the slice generation date, not a check date for each record. Listings without a record are unknown and simply absent. `GET /api/listings/:id` already applies these values on top of the record.

    Annotations the server declares

    • title: Listing updates
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • mcp_index_signalsDoes this MCP server still answer, with which access, and is its repository alive?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
    Does this MCP server still answer, with which access, and is its repository alive? What independent MCP indexes measured about one listing of this catalog, each credited with its license. Take the id from list_listings. A signal belongs to a listing only when it is the SAME object: the name in the official MCP registry, the exact remote endpoint URL or the GitHub `owner/repo`, in that order. A shared domain never matches — two servers on one host are different products. Up to 20 signals, one per index and record.

    Annotations the server declares

    • title: MCP index signals
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • pricingx402 configuration in force and the agent prices for contact and publishing.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
    x402 configuration in force and the agent prices for contact and publishing.

    Annotations the server declares

    • title: Pricing
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • submit_okfSubmits OKF bundles from a host you control (IndexNow protocol: a key file proves ownership, with no account).No findings

    Why it is in this group

    • The name "submit_okf" says "submit": a word for a change.
    Description, as the server wrote it
    Submits OKF bundles from a host you control (IndexNow protocol: a key file proves ownership, with no account). No charge. Answers 202 — the key is checked by the collector before anything is read. No account, no payment: ownership is proved by a key file on the host, exactly as IndexNow does it. Host `https://<host>/<key>.txt` containing the key (or point `keyLocation` at another path on the SAME host), then send the bundle URLs. We answer **202**: the key has not been checked yet. Verification and reading happen on our collector, never at the edge — so nothing is published, and no URL of yours is fetched, before the key matches. Re-sending a URL is how you say the bundle changed; it goes back in line to be re-read. At most 100 URLs per request and 200 per host per UTC day. The same queue is served by `POST https://okfindex.com/api/ping`, the index's own home — search, bundle cards and statistics live there.

    Annotations the server declares

    • title: Submit OKF
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
  • watch_alertsThe changes in the watched tools, oldest first, 100 per page.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 changes in the watched tools, oldest first, 100 per page. Pass the cursor of the last call in `depois` to get only what is new. The same changes the account e-mail reports, while each tool was watched. Without `depois`, the last 30 days. Up to 100 per page: repeat with `depois` set to the `cursor` of the last response while `mais` is `true`. With nothing new, the answer keeps the same cursor, so poll with the last one. `email: true` means the account also gets these changes by e-mail.

    Annotations the server declares

    • title: Watch alerts
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • watch_dependency_changesFollow package, publisher, repository and domain changes of a tool in your watchlist.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
    Follow package, publisher, repository and domain changes of a tool in your watchlist. Uses an existing paid watch pass and never purchases one. The listing must already be in your watchlist. No separate purchase. Sources refresh every six hours through shared caches. Source quotas can defer a check. History records before, after, source and observation date. Domain expiry alerts use 30, 15 and 7 days when the registry publishes a date. Missing dates and source failures remain unverified. Account holders receive operational e-mail; wallet owners read API history. No account-recovery or takeover attempt is made.

    Annotations the server declares

    • title: Watch dependency changes
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
  • watch_toolWatch a remote MCP or supported SKILL.md.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
    Watch a remote MCP or supported SKILL.md. Daily schedule, subject to source quota; account e-mail for changes. Skills cover text and review signals, not execution. 3 free slots per owner; 402 for more. Unsupported sources are rejected before payment. We collect and compare the supported sources daily. Your agent reads the changes without maintaining its own watch process. Catalog signals and change notices are not a security audit or proof that remote code is safe. Local hooks do not freeze remote MCP code.

    Annotations the server declares

    • title: Watch tool
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
Only reads 19Show 19 read-only tools
  • a2a_agentRead one A2A agent: every skill its card declares, capabilities, protocol version, health, documentation and the registries that list it, with their licenses.No findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.
    Description, as the server wrote it
    Read one A2A agent: every skill its card declares, capabilities, protocol version, health, documentation and the registries that list it, with their licenses. Take the key from a2a_agent_search. The same row as the list plus what the card declares: every skill, the `capabilities` object, the protocol version as written, the documentation and icon URLs, and when we first saw it. Cached for 60 seconds; a MAT catalog read, like the list.

    Annotations the server declares

    • title: A2a agent
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • dependency_changesRead your watched tool's before/after evidence, dates and sources.No findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.
    Description, as the server wrote it
    Read your watched tool's before/after evidence, dates and sources. Continue through history_next.

    Annotations the server declares

    • title: Dependency changes
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • feed_findDoes this site publish a feed?No findings

    Why it is in this group

    • The name "feed_find" says "find": a word for reading.
    Description, as the server wrote it
    Does this site publish a feed? Answers with every feed known for a domain — the question a reader or an agent actually asks. Find feeds by text, format, language and availability. Filter and text search run in the SAME full-text query: values inside one parameter are OR'd, different parameters are AND'd. Without `q` the order is by newest in the index (`recent`) and `next_cursor` is a keyset — follow `next` to walk everything. With `q` the order is relevance and paging is by `offset`. We index and link; the feeds belong to whoever publishes them.

    Annotations the server declares

    • title: Feed find
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • get_bundleOne bundle's card: root index.md URL, version, concept count, provenance and repository signal.Reads private dataReads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe description's first sentence says "repository": it reads repositories.
    • untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    One bundle's card: root index.md URL, version, concept count, provenance and repository signal. `live` and `low` (example or fixture bundles kept out of the search) both answer here.

    Annotations the server declares

    • title: Get bundle
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • get_listingOne listing's page.No findings

    Why it is in this group

    • The name "get_listing" says "get": a word for reading.
    Description, as the server wrote it
    One listing's page. The owner sees their own even when pending or hidden.

    Annotations the server declares

    • title: Get listing
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • get_listing_readmeCollected project documentation.No findings

    Why it is in this group

    • The name "get_listing_readme" says "get": a word for reading.
    Description, as the server wrote it
    Collected project documentation. Available when get_listing includes readme_api; 404 when no copy was stored. The text lives in R2 (`mural-coleta`). This call does not write and does not fetch GitHub. Same visibility as the listing page. Call it only when the listing page carries `readme_api`: a page without it has no README collected, and this route answers 404.

    Annotations the server declares

    • title: Get listing readme
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • get_listing_sealsVerification seals of a listing: code, DNS, IP, TLS and domain, each checked daily against the reference the publisher approved.No findings

    Why it is in this group

    • The name "get_listing_seals" says "get": a word for reading.
    Description, as the server wrote it
    Verification seals of a listing: code, DNS, IP, TLS and domain, each checked daily against the reference the publisher approved. Public seal status for a listing. The owner also sees the proof, the approved and current readings, the selected seals and the available cancellation details.

    Annotations the server declares

    • title: Get listing seals
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • list_listingsPublic mosaic of live MCP servers, skills, plugins and OKF knowledge bundles.No findings

    Why it is in this group

    • The name "list_listings" says "list": a word for reading.
    Description, as the server wrote it
    Public mosaic of live MCP servers, skills, plugins and OKF knowledge bundles. MCP servers with an active verification seal first (`verified`); `trusted=1` lists only them, and `warning` marks a page with listings that Agentalog does not check every day. Then `live` listings and the `low` tail (few stars or no clear license) after them in every order — `low=0` leaves the tail out. To walk everything, follow `next`: without `q` it is a cursor (`next_cursor`, keyset on the order's index) and has no ceiling; every listing also has an HTML page at `/l/:id` and the shards of `/sitemap-listings.xml` list them all. `q` runs on a full-text index (FTS5, bm25) kept in the same transaction as every text write. With `q` and `low=0`, `low_count` says how many `low` listings the filter left out — LIKE with a cap of 200. The query is mapped onto kind/topic/transport filters unless `interpret=0`.

    Annotations the server declares

    • title: List listings
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • list_mcp_serversMCP subregistry (GET /v0.1/servers).No findings

    Why it is in this group

    • The name "list_mcp_servers" says "list": a word for reading.
    Description, as the server wrote it
    MCP subregistry (GET /v0.1/servers). Only live kind=mcp, verified servers first, seals in _meta. Only `kind=mcp` and only `live`, verified servers first, each with its seals in `_meta`. A generic MCP client reads it without knowing this product. `GET /v0/servers` is an alias of the same resource, kept for whoever already pointed there — this is the canonical URL.

    Annotations the server declares

    • title: List MCP servers
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • list_plansThe plans for sale, with price and term, and the account's active plan.1 finding

    Why it is in this group

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

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...c renewal. Without an account or wallet credential, `account` is `null`."

      What this check looks for
    Description, as the server wrote it
    The plans for sale, with price and term, and the account's active plan. Each purchase lasts 30 days, with no automatic renewal. Each purchase lasts 30 days, with no automatic renewal. Without an account or wallet credential, `account` is `null`.

    Annotations the server declares

    • title: List plans
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • list_watched_toolsThe MCP servers and skills the account watches, with their review level, slots and plans.Reads text others writeNo findings

    Why it is in this group

    • The name "list_watched_tools" 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
    The MCP servers and skills the account watches, with their review level, slots and plans. Daily checks cover MCP tools, state, level, country and version. Supported skills cover changes in SKILL.md text and review signals. Source quotas can delay a check; read proxima_em and verificado_em. The e-mail goes to the verified account address and includes an unsubscribe link. Wallet-only owners read the changes in `GET /api/me/vigia/avisos`.

    Annotations the server declares

    • title: List watched tools
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • listing_dependenciesRead a tool's declared package/repository/domain chain and cached public source evidence.Reads private dataNo findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "read" and "repository": it reads repositories.
    Description, as the server wrote it
    Read a tool's declared package/repository/domain chain and cached public source evidence. No purchase or collection. Repeated registry, repository, registration and DNS lookups, comparison code and an alert process that must keep running after the conversation. A declaration does not prove ownership. Source failures and missing dates remain unknown. Collected PyPI provenance is not independently verified. No measured token or money saving is claimed.

    Annotations the server declares

    • title: Listing dependencies
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • listing_historyRead up to five recorded repository events, newest first.Reads private dataNo findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "read" and "repository": it reads repositories.
    Description, as the server wrote it
    Read up to five recorded repository events, newest first. The listing page carries the same available events as `history`; updates may be cached for up to 15 minutes. An empty list means no events are available, not proof that nothing changed or that collection covered the requested period. `generated_at` is the slice generation date, not a per-repository check date; it is empty when no slice was read. Stale means no push for 12 months. Reading does not refresh the source.

    Annotations the server declares

    • title: Listing history
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • listing_securityRead a remote MCP server or SKILL.md review before installing.Reads text others write1 finding

    Why it is in this group

    • The description's first verb is "read": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "read" and "review": it reads comments, which other people can write.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...`initialize` and `tools/list`, without credentials or tool calls, again 7 days after a suc..."

      What this check looks for
    Description, as the server wrote it
    Read a remote MCP server or SKILL.md review before installing. MCP: server, domain, tools and measured signals. Skill: static findings with file, line, excerpt and context; no command execution or referenced-script review. Unread skills stay unchecked. Read the limits in aviso. Take the id from list_listings. We visit remote MCP servers: `initialize` and `tools/list`, without credentials or tool calls, again 7 days after a success. A failure needs a second check. MCP signals: dns_morto, sem_https, tls_invalido, tunel, nao_responde, nao_mcp, texto_suspeito, redireciona_fora, repo_arquivado, repo_parado, dominio_recente, login, bloqueado. For skills, `tipo: skill` identifies a static SKILL.md review. It flags secret reads, download-and-execute commands, external uploads, invisible characters, long encoded text and broad allowed-tools. `revisao.achados` supplies the path, original line, excerpt and context. Examples and prohibitions do not raise the level. Excerpts hide sensitive values. The review does not run commands or follow references. Supported source: public raw.githubusercontent.com SKILL.md. Watched, visited, starred and new skills get priority within the shared GitHub governor and a daily cap. Unread or unsupported skills remain explicitly unchecked. Local MCP servers and plugins answer `not_remote`. No request fetches a third-party source. Cached for 5 minutes.

    Annotations the server declares

    • title: Listing security
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • listing_statusModeration state of a listing (pending / live / low / hidden / blocked) — poll it after create_listing.1 finding

    Why it is in this group

    • The name "listing_status" says "status": a word for reading.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...ked) — poll it after create_listing. No credential; only the decision comes back. Every su..."

      What this check looks for
    Description, as the server wrote it
    Moderation state of a listing (pending / live / low / hidden / blocked) — poll it after create_listing. No credential; only the decision comes back. Every submission is born `pending`. An automatic safety check looks for concrete signs of fraud, malware or data theft. Listings without these signs can be approved. A risk finding or an unreadable source keeps the listing private for a person to review. This is the receipt you poll after `POST /api/listings` (its response carries this URL as `status_api`). Only the decision comes back, never the unreviewed content: the id (`lst_…`, unguessable) is all it takes, and the page itself keeps its rule — owner only until it is public. Answers are cached for 60 s per point of presence: poll every few minutes, not every second.

    Annotations the server declares

    • title: Listing status
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
  • search_bundlesSearch the index of OKF bundles: free text over name, tagline, description and origin; filter by provenance (github|domain), repository, version, language, license, root type or co…Reads private dataNo findings

    Why it is in this group

    • The name "search_bundles" says "search": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "search" and "repository": it reads repositories.
    • private-dataThe input names a repo (input.repo), and the tool reads: it reads repositories.
    Description, as the server wrote it
    Search the index of OKF bundles: free text over name, tagline, description and origin; filter by provenance (github|domain), repository, version, language, license, root type or concept count; search root concept text. Paginate with limit/offset. Only `live` bundles. Free text matches the name, the tagline, the description and the origin identifier (`owner/repo:path` or the bundle URL). No `total` on purpose: `GET /api/okf/stats` has it.

    Annotations the server declares

    • title: Search bundles
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true

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.

120 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 4 private-data tools breaks every one.

Reads private data4
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write6
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out5
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__meta-agent-tools__get_bundle",
      "mcp__meta-agent-tools__listing_dependencies",
      "mcp__meta-agent-tools__listing_history",
      "mcp__meta-agent-tools__search_bundles"
    ]
  }
}

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, 18:31 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
10
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://classificado.app.br/.well-known/oauth-protected-resource/mcp
Authorization servers
https://agentalog.com/connect
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
yes
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 10 tools that change things (10 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://classificado.app.br/mcp: tools/list returned 19 tools to an anonymous client, including check_tool (write), listing_tools (write), watch_tool (write), watch_alerts (write), api_index (write) and 5 more

    What this check looks for

Posture changes

  1. Nov 20, 2026
    • Tools that change things, listed without credentials: 30 to 10
  2. Nov 6, 2026
    • Tools that change things, listed without credentials: 22 to 30
    • Authorization servers: https://agentalog.com to https://agentalog.com/connect
  3. Oct 29, 2026
    • Tools that change things, listed without credentials: 21 to 22

Findings

Matches of fixed checks, with the text they matched.

7 warn7 info
  • The server marks "feed_posts" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true}; The name "feed_posts" says "post": a word for a change.

    What this check looks for
  • The server marks "feed_post" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true}; The name "feed_post" says "post": a word for a change.

    What this check looks for
  • The server marks "cancel_plan" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false}; The name "cancel_plan" says "cancel": a word for removing or ending something.

    What this check looks for
  • The server marks "briefings_links" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true}; The name "briefings_links" says "link": a word for a change.

    What this check looks for
  • The server marks "listing_updates" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true}; The name "listing_updates" says "update": a word for a change.

    What this check looks for
  • The server marks "list_comments" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true}; The name "list_comments" says "list": a word for reading.

    What this check looks for
Show 8 more findings
  • The server marks "get_api_x402_check" as not read-only (readOnlyHint: false), and its words say it reads.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false}; The name "get_api_x402_check" says "get": a word for reading.

    What this check looks for
  • The input schema at properties.url.description mentions "credentials".

    Matched text

    inputSchema.properties.url.description: "...(s) endpoint of the MCP server, without credentials."

    What this check looks for
  • The description mentions "credentials".

    Matched text

    description: "...`initialize` and `tools/list`, without credentials or tool calls, again 7 days after a suc..."

    What this check looks for
  • The description mentions "credential".

    Matched text

    description: "...c renewal. Without an account or wallet credential, `account` is `null`."

    What this check looks for
  • The description mentions "credential".

    Matched text

    description: "Comments on a live listing. With a credential on the call, each comment of yours come..."

    What this check looks for
  • The description mentions "credential".

    Matched text

    description: "...pi` (`GET /api/listings/:id/status`, no credential) to learn the decision. A person or age..."

    What this check looks for
  • The description mentions "credential".

    Matched text

    description: "...ked) — poll it after create_listing. No credential; only the decision comes back. Every su..."

    What this check looks for
  • The input schema at properties.url.description mentions "credentials".

    Matched text

    inputSchema.properties.url.description: "...(s) endpoint of the MCP server, without credentials."

    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: 30 -> 10.View diff
    • Tools that change things, listed without credentials: 30 to 10
  2. Tools13 added, 22 changed.+13 added~22 changedView diff
  3. PostureRemote posture changed. Tools that change things, listed without credentials: 22 -> 30; Authorization servers: https://agentalog.com -> https://agentalog.com/connect.View diff
    • Tools that change things, listed without credentials: 22 to 30
    • Authorization servers: https://agentalog.com to https://agentalog.com/connect
  4. Tools1 added, 2 changed.+1 added~2 changedView diff
  5. PostureRemote posture changed. Tools that change things, listed without credentials: 21 -> 22.View diff
    • Tools that change things, listed without credentials: 21 to 22

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http meta-agent-tools https://classificado.app.br/mcp
claude mcp add --transport http meta-agent-tools https://classificado.app.br/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__meta-agent-tools__search_bundles",
      "mcp__meta-agent-tools__get_bundle",
      "mcp__meta-agent-tools__listing_dependencies",
      "mcp__meta-agent-tools__dependency_changes",
      "mcp__meta-agent-tools__feed_find",
      "mcp__meta-agent-tools__feed_search",
      "mcp__meta-agent-tools__mcp_index_search",
      "mcp__meta-agent-tools__listing_security",
      "mcp__meta-agent-tools__list_watched_tools",
      "mcp__meta-agent-tools__list_plans",
      "mcp__meta-agent-tools__a2a_agent_search",
      "mcp__meta-agent-tools__a2a_agent",
      "mcp__meta-agent-tools__list_listings",
      "mcp__meta-agent-tools__get_listing_seals",
      "mcp__meta-agent-tools__list_mcp_servers",
      "mcp__meta-agent-tools__get_listing",
      "mcp__meta-agent-tools__get_listing_readme",
      "mcp__meta-agent-tools__listing_history",
      "mcp__meta-agent-tools__listing_status"
    ],
    "ask": [
      "mcp__meta-agent-tools__index_stats",
      "mcp__meta-agent-tools__watch_dependency_changes",
      "mcp__meta-agent-tools__feed_posts",
      "mcp__meta-agent-tools__feed_post",
      "mcp__meta-agent-tools__mcp_index_signals",
      "mcp__meta-agent-tools__check_tool",
      "mcp__meta-agent-tools__listing_tools",
      "mcp__meta-agent-tools__watch_tool",
      "mcp__meta-agent-tools__buy_plan",
      "mcp__meta-agent-tools__claude_code_allowlist",
      "mcp__meta-agent-tools__watch_alerts",
      "mcp__meta-agent-tools__briefings_topics",
      "mcp__meta-agent-tools__briefings_links",
      "mcp__meta-agent-tools__api_index",
      "mcp__meta-agent-tools__health",
      "mcp__meta-agent-tools__create_guest",
      "mcp__meta-agent-tools__listing_updates",
      "mcp__meta-agent-tools__go_listing",
      "mcp__meta-agent-tools__like_listing",
      "mcp__meta-agent-tools__list_comments",
      "mcp__meta-agent-tools__create_listing",
      "mcp__meta-agent-tools__submit_okf",
      "mcp__meta-agent-tools__pricing",
      "mcp__meta-agent-tools__contact",
      "mcp__meta-agent-tools__api_access",
      "mcp__meta-agent-tools__api_access_buy",
      "mcp__meta-agent-tools__api_usage",
      "mcp__meta-agent-tools__get_api_x402_check"
    ],
    "deny": [
      "mcp__meta-agent-tools__unwatch_tool",
      "mcp__meta-agent-tools__cancel_plan"
    ]
  }
}

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 meta-agent-tools. Review it before you use it.

Capability tags behind 13 rules
  • mcp__meta-agent-tools__search_bundles private-data
  • mcp__meta-agent-tools__get_bundle private-data, untrusted-input
  • mcp__meta-agent-tools__listing_dependencies private-data
  • mcp__meta-agent-tools__feed_posts outbound
  • mcp__meta-agent-tools__feed_post outbound
  • mcp__meta-agent-tools__mcp_index_search untrusted-input
  • mcp__meta-agent-tools__check_tool outbound
  • mcp__meta-agent-tools__listing_security untrusted-input
  • mcp__meta-agent-tools__list_watched_tools untrusted-input
  • mcp__meta-agent-tools__listing_history private-data
  • mcp__meta-agent-tools__list_comments untrusted-input
  • mcp__meta-agent-tools__create_listing outbound
  • mcp__meta-agent-tools__get_api_x402_check untrusted-input, outbound

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/br.app.classificado/meta-agent-tools/verify?hash=13ea115e963b487167cd2b12890b7b809bc0ae63d16693ed28ce6ea2e5d5caf5" | jq -e '.changed == false'

Pinned hash 13ea115e963b, from Nov 12, 2026, 06:17 UTC.

Watch

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

https://radar.anlyon.com/servers/br.app.classificado/meta-agent-tools/changes.xml

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

Badge

Anlyon Radar badge for br.app.classificado/meta-agent-tools
[![Anlyon Radar](https://radar.anlyon.com/badge/br.app.classificado/meta-agent-tools.svg)](https://radar.anlyon.com/servers/br.app.classificado/meta-agent-tools)

Source: MCP Registry. Synced Oct 21, 2026, 17:46 UTC.

meta-agent-tools MCP server: questions and answers

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

Is the meta-agent-tools MCP server safe?

No scan can promise that. What its definitions show: 49 tools, 30 of which can change, send or delete something, and 14 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 meta-agent-tools MCP server delete data?

Yes. 2 tools can delete, cancel or revoke something: unwatch_tool and cancel_plan.

Can the meta-agent-tools 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 meta-agent-tools MCP server have?

49 tools: 2 destructive, 28 write, 19 read. unwatch_tool, cancel_plan, index_stats, watch_dependency_changes, feed_posts, feed_post, mcp_index_signals, check_tool and 41 more.

Does the meta-agent-tools MCP server need sign-in or OAuth?

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

Does the meta-agent-tools MCP server send data to outside services?

5 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): feed_posts, feed_post, check_tool, create_listing and get_api_x402_check.

Has the meta-agent-tools MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 12, 2026. Every change is on this page and in its Atom feed.