# com.agentalog/meta-agent-tools (remote · agentalog.com) Registry of MCP servers, agent skills and plugins: search, filter, comments, likes, publish. - Trust score: 80/100 (high trust) - Change this week: +11 - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-10-02 ## Components - remote · `agentalog.com`: 80/100 (this document), [markdown](https://verifymcp.io/servers/com-agentalog-meta-agent-tools/agentalog.md), [page](https://verifymcp.io/servers/com-agentalog-meta-agent-tools/agentalog) ## Channel facts - Endpoint: `https://agentalog.com/mcp` - Transports: `streamable-http` - Auth: `none` - Version: `1.0.0` ## Trust breakdown How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog) Scored 2026-10-02. - **Endpoint Security**: 74/100 - The endpoint's TLS certificate is valid, in date, and uses a strong key. - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. - HTTPS is enforced; there's no plaintext access path. - HSTS check failed: the Strict-Transport-Security header is absent. - DNSSEC check failed: this domain isn't protected by DNSSEC. - **Transport & Reachability**: 100/100 - Verified streamable-http transport via a live MCP handshake. - **Schema Quality & AI Usability**: 63/100 - AI-judged instruction clarity (good). - Context-footprint check failed: tool/resource definitions use about 6001 tokens (~181/item across 33 items; 33 tools + 0 resources), over budget; trim descriptions and params. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 90/100 - Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses. - **Tool Coverage**: 100/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 99% of tool parameters carry a description. - **Tool Safety**: 100/100 - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured. - We read all 33 captured tool definition(s), and no name or description among them implies an irreversible operation. - An AI judge read all 34 captured unit(s) of tool text and found none that tries to manipulate the model reading it. - **Capabilities**: 60/100 - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. ## Install ### How do I install the com.agentalog/meta-agent-tools MCP server? com.agentalog/meta-agent-tools is a hosted endpoint at https://agentalog.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation. ### Claude ```bash claude mcp add --transport http com-agentalog-meta-agent-tools 'https://agentalog.com/mcp' ``` ### Cursor ```json { "mcpServers": { "com-agentalog-meta-agent-tools": { "url": "https://agentalog.com/mcp" } } } ``` ### VS Code ```json { "servers": { "com-agentalog-meta-agent-tools": { "type": "http", "url": "https://agentalog.com/mcp" } } } ``` ### Codex ```toml [mcp_servers.com-agentalog-meta-agent-tools] url = "https://agentalog.com/mcp" ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "com-agentalog-meta-agent-tools": { "type": "remote", "url": "https://agentalog.com/mcp", "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add com-agentalog-meta-agent-tools --url 'https://agentalog.com/mcp' --transport streamable-http ``` ### Hermes ```yaml mcp_servers: com-agentalog-meta-agent-tools: url: "https://agentalog.com/mcp" ``` ### Netclaw ```json { "McpServers": { "com-agentalog-meta-agent-tools": { "Transport": "http", "Url": "https://agentalog.com/mcp" } } } ``` ### Vellum ```bash assistant mcp add com-agentalog-meta-agent-tools -t streamable-http -u 'https://agentalog.com/mcp' ``` ### Other ```json { "mcpServers": { "com-agentalog-meta-agent-tools": { "type": "http", "url": "https://agentalog.com/mcp" } } } ``` The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs. ## Changelog Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims. ### 2026-10-02 (score 80, 0) - [functional] Server version: 4cf168eb → b25850a2 ### 2026-10-01 (score 80, +1) - [functional] Server version: 749f2fa7 → 4cf168eb ### 2026-09-30 (score 79, 0) - [functional] Server version: a3b67856 → 749f2fa7 ### 2026-09-29 (score 79, +1) - [security] Tool “create_listing” rewrote its description, which is the text the model reads - [security] Tool “listing_status” rewrote its description, which is the text the model reads - [functional] Server version: 4f1d9997 → a3b67856 - [functional] New tool “briefings_links” - [functional] New tool “briefings_topics” ### 2026-09-28 (score 78, +19) - [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server ### 2026-09-27 (score 59, −10) - [security regression] Judged manipulation: pass → unverified - [security] Tool “feed_post” rewrote its description, which is the text the model reads - [functional regression] Schema quality: good → unverified - [functional] Server version: 0eb961c7 → 83f9a8e7 ### 2026-09-26 (score 69, 0) - [functional regression] Schema quality: 4965 → 5732 - [functional] Server version: 1e78ad2b → 0eb961c7 - [functional] New tool “a2a_agent” - [functional] New tool “a2a_agent_search” ### 2026-09-25 (score 69, +1) - [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server ## MCP tools (33) ### `search_bundles` (~424 tokens) Search bundles 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. Input parameters: - `concept` (string): Text in the indexed root content, including listed concept names and summaries (first 1000 characters); up to 80 characters. - `concepts` (string): Number of entries listed by the root. Up to 5 comma-separated bands: 0,1-5,6-20,21-100,101+. - `language` (string): Only bundles whose repository language is one of these; comma-separated, up to 5 (GitHub bundles). - `license` (string): Repository license. Up to 5 comma-separated values, 40 characters each. - `limit` (integer): Bundles per page, at most 100. - `offset` (integer): How many bundles to skip. Use `next_offset` from the previous response; the list ends at 1000. - `origin` (string): Provenance: found by the GitHub sweep, or submitted by a domain. - `q` (string): Free text over name, tagline, description and origin identifier. - `repo` (string): Only bundles of one repository, `owner/repo` (case-insensitive). - `sort` (string): Result order: arrival, last content change, name or repository stars. - `type` (string): Type declared by the root, not the types of every concept. Up to 5 comma-separated values, 40 characters each. - `version` (string): Only bundles declaring one of these `okf_version` values; comma-separated, up to 5. ### `get_bundle` (~70 tokens) Get bundle 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. Input parameters: - `id` (string, required): Bundle id, the `id` of every item in the list. ### `index_stats` (~20 tokens) Index stats Size of the index by provenance and when it last changed. ### `feed_find` (~201 tokens) Feed find 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 (`recentes`) 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. Input parameters: - `api_pass` (string): MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying. - `dominio` (string, required): Domain, with no scheme: example.com - `retry_key` (string): Optional retry key, up to 80 ASCII characters; same read for five minutes. ### `feed_posts` (~219 tokens) Feed posts 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. `lido_em` says when we read it. Empty list when the feed has not been read yet. Input parameters: - `api_pass` (string): MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying. - `id` (string, required): Feed id, prefix fd_. - `retry_key` (string): Optional retry key, up to 80 ASCII characters; same read for five minutes. ### `feed_post` (~238 tokens) Feed post Read one post whole: the body in Markdown (`conteudo`) and the author's formatting as safe HTML (`conteudo_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: `conteudo_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 `conteudo` 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. Input parameters: - `api_pass` (string): MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying. - `id` (string, required): Feed id, prefix fd_. - `ord` (integer, required): Position of the post in the feed; 0 is the newest. - `retry_key` (string): Optional retry key, up to 80 ASCII characters; same read for five minutes. ### `feed_search` (~309 tokens) Feed search Search the feed index by text and filters: format, audio/video, community, namespace and year of the newest item. 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 (`recentes`) 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. Input parameters: - `api_pass` (string): MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying. - `comunidade` (string): fediverse, indieweb, mastodon, friendica, wordpress, funkwhale. - `limit` (integer): Feeds per page, 1-50. - `midia` (string): audio, video. - `origem` (string): index, blogroll, bridge. - `q` (string): Free text over name, description and domain. - `recurso` (string): content, itunes, podcast, media, slash, wfw, georss. - `retry_key` (string): Optional retry key, up to 80 ASCII characters; same read for five minutes. - `tipo` (string): rss2, rss1, atom, json (comma-separated = OR). ### `mcp_index_signals` (~187 tokens) MCP index signals 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. Input parameters: - `api_pass` (string): MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying. - `listing` (string, required): Listing id from list_listings. - `retry_key` (string): Optional retry key, up to 80 ASCII characters; same read for five minutes. ### `mcp_index_search` (~224 tokens) MCP index search Browse what independent MCP indexes measured, including servers this catalog does not list yet (casou=0). Newest change first. `casou=0` is what the indexes know and the catalog does not — the list to look at before submitting a server. Filters are AND'd. Input parameters: - `api_pass` (string): MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying. - `casou` (string): 1 matched to a listing, 0 not in the catalog. - `estado` (string): vivo, fora, parado, abandonado, apagado, desconhecido. - `fonte` (string): One index: wellknown, agent_tools, nerq, truespar, neuronto, paygent, hultra. - `limit` (integer): Signals per page, 1-50. - `q` (string): Substring of name, URL or repository. - `retry_key` (string): Optional retry key, up to 80 ASCII characters; same read for five minutes. ### `a2a_agent_search` (~580 tokens) A2a agent search Find A2A agents — agents that publish an AgentCard — by text, health, protocol version, registry, skill tag or publisher. Each row carries the key for a2a_agent and the license of every registry that lists it. Collected from public A2A registries and served as it comes — no review queue hides a record; quality is the order, never visibility. One row per agent, merged across the registries that list it: `fontes` says which, and `creditos` carries each one's license, which travels with the data. Values inside one parameter are OR'd, different parameters are AND'd. Cached for 60 seconds. A MAT catalog read, served by the index host `https://api.agentalog.com`; this host forwards the call there. Input parameters: - `api_pass` (string): MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying. - `fonte` (string): Only agents listed by this registry. Comma-separated values are OR'd (up to 12, each up to 200 characters). - `limit` (integer): Items per page, 1–50; more is capped at 50, anything else means 20. - `offset` (integer): Offset, capped at 20000 (a larger value reads as 20000). Prefer `_links.next`. - `protocolo` (string): A2A protocol version as normalized (`0.3`, `1.0`…); `/api/a2a/facets` lists the ones present. Comma-separated values are OR'd (up to 12, each up to 200 characters). - `publicador` (string): Exact publisher, as `publicador` shows it. Comma-separated values are OR'd (up to 12, each up to 200 characters). - `q` (string): Substring of the name, description, key, publisher or the card's skills, in any letter case (`%` and `_` are taken literally); up to 80 characters. - `retry_key` (string): Optional retry key, up to 80 ASCII characters; same read for five minutes. - `saude` (string): Health the registries measured: `sim` answered, `nao` did not, `sem_medida` never measured. Comma-separated values are OR'd (up to 12, each up to 200 characters). - `skills` (string): `1` keeps only agents whose card lists at least one skill. - `tag` (string): Exact tag of the card's skills, case-sensitive; `/api/a2a/facets` lists the 40 most used. Comma-separated values are OR'd (up to 12, each up to 200 characters). ### `a2a_agent` (~187 tokens) A2a agent 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. Input parameters: - `api_pass` (string): MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying. - `chave` (string, required): Agent key (`chave`) from a2a_agent_search, usually the card's domain. - `retry_key` (string): Optional retry key, up to 80 ASCII characters; same read for five minutes. ### `briefings_topics` (~116 tokens) Briefings topics 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. ### `briefings_links` (~123 tokens) Briefings links Curated engineering links filtered by topic and source type (paper, repo, model, dataset, demo, video, docs, article, post), 20 per page, with the count of each filter value. Values inside one parameter are OR'd; the two parameters are AND'd. Unknown values are ignored. Follow `_links.next` to walk everything. Input parameters: - `page` (integer): Page, from 1. - `tipo` (string): Source types, comma-separated. - `topico` (string): Topic slugs, comma-separated (from briefings_topics). ### `api_index` (~24 tokens) API index Self-describing index: the whole API surface, with quota and quickstart. ### `health` (~27 tokens) Health Liveness and the commit deployed right now — it is how the smoke waits for its own deploy. ### `create_guest` (~62 tokens) Create guest 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. ### `list_listings` (~522 tokens) List listings Public mosaic of live MCP servers, skills, plugins and OKF knowledge bundles. `live` listings first 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`. Input parameters: - `api_pass` (string): MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying. - `category` (string): Category declared by whoever published. - `interpret` (string): `0` disables query understanding and searches the raw string. - `kind` (string): Which kind of resource to fetch. - `low` (string): `0` leaves the `low` tail out; by default it comes after the `live` listings in every order. - `q` (string): Free text over the name, the tagline, the description, the origin identifier and the README excerpt: every word (up to six, 2+ letters, accents ignored) must match; ranked by bm25 with the name weigh… - `retry_key` (string): Optional retry key, up to 80 ASCII characters; same read for five minutes. - `sort` (string): Result order. Without it, a query is ranked by relevance — bm25 over the full-text index (name 10, tagline 5, identifier 3, description 2, README excerpt 1) multiplied by 1 + 0.05·ln(1 + stars) + 0.1… ### `list_mcp_servers` (~185 tokens) List MCP servers MCP subregistry (GET /v0.1/servers). Only live kind=mcp. Only `kind=mcp` and only `live`. It is the route a generic MCP client knows how to read 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. Input parameters: - `api_pass` (string): MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying. - `cursor` (string): Opaque cursor of the next page, from `metadata.next_cursor`. - `limit` (number): Servers per page. - `retry_key` (string): Optional retry key, up to 80 ASCII characters; same read for five minutes. - `search` (string): Free text over the server's name and description. ### `get_listing` (~92 tokens) Get listing One listing's page. The owner sees their own even when pending or hidden. Input parameters: - `api_pass` (string): MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying. - `id` (string, required): Listing ID, from `Anuncio.id`. - `retry_key` (string): Optional retry key, up to 80 ASCII characters; same read for five minutes. ### `get_listing_readme` (~163 tokens) Get listing readme README collected for a listing (R2). Only when get_listing carries readme_api; 404 when none 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. Input parameters: - `api_pass` (string): MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying. - `id` (string, required): Listing ID, from `Anuncio.id`. - `retry_key` (string): Optional retry key, up to 80 ASCII characters; same read for five minutes. ### `listing_history` (~184 tokens) Listing history Timeline of the listing's repository: last events (abandono = no push for 12 months, sumiu, renomeado, readme_mudou, manifesto_mudou), newest first; empty when nothing changed since the series began. The listing page carries the same list as `historico`; updates may be cached for up to 15 minutes. An empty list means no change since the series began — the listing still exists. Stale means no push for 12 months. Reading this endpoint does not refresh the record. Input parameters: - `api_pass` (string): MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying. - `id` (string, required): Listing ID, from `Anuncio.id`. - `retry_key` (string): Optional retry key, up to 80 ASCII characters; same read for five minutes. ### `go_listing` (~71 tokens) Go listing 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. Input parameters: - `id` (string, required): ID of the listing to visit. ### `like_listing` (~50 tokens) Like listing Likes the listing; DELETE undoes it. Calling again does not add up: the counter counts people. Input parameters: - `guest_token` (string, required) - `id` (string, required): ID of the listing to like. ### `list_comments` (~43 tokens) List comments Comments on a live listing. With a credential on the call, each comment of yours comes with `mine: true`. Input parameters: - `id` (string, required): ID of the listing. ### `create_listing` (~318 tokens) Create listing Registers an MCP server, skill or plugin (human session free; agent without session = 402 $0.10). 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. Two doors to the same action. Human with a session: free, 1 per day, at most 3 in the queue. Agent (with or without a guest): **402 with `accepts[]`**, $0.10 — pay and repeat. For a skill, the `SKILL.md` URL is enough; the rest is checked. **Validates before charging:** a refused body (400) and an exhausted quota (429) come BEFORE the 402, so no payment settles for a listing already known not to get in. A valid body without payment keeps receiving the 402 with the price. Input parameters: - `body` (string): Long description, optional. - `category` (string): Category so the listing shows up under the right filter. - `kind` (string, required): What is being registered. - `name` (string): Display name; without it, taken from the source. - `tagline` (string): One line saying what it is for. - `url` (string, required): MCP endpoint, SKILL.md URL, the plugin's repository or the OKF bundle's `index.md`. For an OKF bundle on a domain you control, `POST /api/okf/ping` is free. ### `listing_status` (~185 tokens) Listing status 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`. A bounded automatic review approves clear, low-risk MCP listings; uncertain cases stay 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. Input parameters: - `id` (string, required): Listing ID, from the `id` of the `POST /api/listings` response. ### `submit_okf` (~330 tokens) Submit OKF Submits OKF bundles from a host you control (IndexNow protocol: key file proves ownership, 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:///.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. Input parameters: - `host` (string, required): The host that owns the bundles. - `key` (string, required): 8 to 128 characters of [a-zA-Z0-9-]. - `keyLocation` (string): Where the key file lives. Defaults to `https:///.txt`; must be on `host`. - `urlList` (array, required): Bundle `index.md` URLs. https, on `host`, ending in .md. No fixed path: the spec defines no discovery convention. ### `billing` (~21 tokens) Billing x402 configuration in force and the agent prices for contact and publishing. ### `contact` (~324 tokens) Contact 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 (`tipo`, 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. Input parameters: - `duracao` (string): Exposure in days: `30`, `90` or `365`. - `email` (string, required): Where to reply. - `empresa` (string): Who is proposing, when it is a company. - `espaco` (array): Placement ids from `GET /api/partners`, up to 6. - `message` (string, required): What you want to say. - `name` (string, required): What to call the person writing. - `orcamento` (string): `ate_100`, `100_500`, `500_2000`, `2000_mais` or `a_combinar`. - `pagamento` (string): `usdc`, `deposito` or `a_combinar`. - `site` (string): Website of who is proposing. - `tipo` (string): Proposal: `patrocinio`, `parceria` or `anuncio`. Turns on the fields below. ### `api_access` (~151 tokens) API access 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 429 until the next day. Billing is off for now: there is no package to buy and reads need no X-API-Pass. The MAT allowance is separate from the company, address and procurement indexes. Input parameters: - `api_pass` (string): MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying. ### `api_access_buy` (~215 tokens) API access buy 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 429 until the next day. Billing is off for now: there is no package to buy and reads need no X-API-Pass. The MAT allowance is separate from the company, address and procurement indexes. Input parameters: - `api_pass` (string, required): MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying. - `credit_token` (string): Existing prepaid credit token. - `payment` (string): Signed x402 payload, after authorizing the quote. - `transaction` (string): Base transaction hash to reconcile an uncertain payment with the same pass and original payload. ### `api_usage` (~46 tokens) API usage Remaining MAT read credits, without consuming credit. Input parameters: - `api_pass` (string, required): MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying. ### `pricing` (~17 tokens) Pricing Current public prices and free allowances; no charge. ## Diagnostics Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-agentalog-meta-agent-tools/agentalog#diagnostics ## Score history - 2026-10-02: 80 - 2026-10-01: 80 - 2026-09-30: 79 - 2026-09-29: 79 - 2026-09-28: 78 - 2026-09-27: 59 - 2026-09-26: 69 - 2026-09-25: 69 - 2026-09-24: 68 - 2026-09-23: 64 - 2026-09-22: 63 - 2026-09-21: 63 - 2026-09-20: 62 - 2026-09-19: 62 - 2026-09-18: 61 - 2026-09-17: 61 - 2026-09-16: 60 - 2026-09-15: 60 - 2026-09-14: 59 - 2026-09-13: 59 - 2026-09-12: 58 - 2026-09-11: 58 - 2026-09-10: 57 - 2026-09-09: 57 - 2026-09-08: 56 - 2026-09-07: 55 - 2026-09-06: 50 - 2026-09-05: 50 ## Common questions ### What is the com.agentalog/meta-agent-tools MCP server? com.agentalog/meta-agent-tools is an MCP server listed in the public MCP registry as com.agentalog/meta-agent-tools. Registry of MCP servers, agent skills and plugins: search, filter, comments, likes, publish. This page covers its hosted endpoint (https://agentalog.com/mcp). ### Is the com.agentalog/meta-agent-tools MCP server safe to use? com.agentalog/meta-agent-tools scores 80 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm. ### What tools does the com.agentalog/meta-agent-tools MCP server expose? com.agentalog/meta-agent-tools exposes 33 tools: search_bundles, get_bundle, index_stats, feed_find, feed_posts, and 28 more. Their descriptions and schemas cost roughly 5,928 tokens of context every time the server is loaded. ### Does the com.agentalog/meta-agent-tools MCP server require authentication? No. We connected to com.agentalog/meta-agent-tools without credentials and it answered, so anything it exposes is reachable by anyone who knows the address. ### Is the com.agentalog/meta-agent-tools MCP server still maintained? com.agentalog/meta-agent-tools is still listed as active in the MCP registry. We last reached this channel on 2 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced. ## Links - Remote endpoint: https://agentalog.com/mcp - Website: https://agentalog.com/ - Changelog RSS feed: https://verifymcp.io/servers/com-agentalog-meta-agent-tools/agentalog.xml - Changelog JSON feed: https://verifymcp.io/servers/com-agentalog-meta-agent-tools/agentalog.json - HTML version of this page: https://verifymcp.io/servers/com-agentalog-meta-agent-tools/agentalog