此 MCP 可以做什么
Indexes and searches MCP servers, agent skills, plugins, feeds, and knowledge bundles, with listing, commenting, and publishing functions.
功能
工具
33
工具
a2a_agent
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.
只读
幂等
输入模式
{'type': 'object', 'required': ['chave'], 'properties': {'chave': {'type': 'string', 'description': "Agent key (`chave`) from a2a_agent_search, usually the card's domain."}, 'api_pass': {'type': 'string', 'description': 'MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying.'}, 'retry_key': {'type': 'string', 'description': 'Optional retry key, up to 80 ASCII characters; same read for five minutes.'}}}
a2a_agent_search
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.
只读
幂等
输入模式
{'type': 'object', 'properties': {'q': {'type': 'string', 'description': "Substring of the name, description, key, publisher or the card's skills, in any letter case (`%` and `_` are taken literally); up to 80 characters."}, 'tag': {'type': 'string', 'description': "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)."}, 'fonte': {'enum': ['a2a_registry', 'a2a_global', 'agenstry'], 'type': 'string', 'description': "Only agents listed by this registry. Comma-separated values are OR'd (up to 12, each up to 200 characters)."}, 'limit': {'type': 'integer', 'default': 20, 'description': 'Items per page, 1–50; more is capped at 50, anything else means 20.'}, 'saude': {'enum': ['sim', 'nao', 'sem_medida'], 'type': 'string', 'description': "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)."}, 'offset': {'type': 'integer', 'default': 0, 'description': 'Offset, capped at 20000 (a larger value reads as 20000). Prefer `_links.next`.'}, 'skills': {'enum': ['1'], 'type': 'string', 'description': '`1` keeps only agents whose card lists at least one skill.'}, 'api_pass': {'type': 'string', 'description': 'MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying.'}, 'protocolo': {'type': 'string', 'description': "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)."}, 'retry_key': {'type': 'string', 'description': 'Optional retry key, up to 80 ASCII characters; same read for five minutes.'}, 'publicador': {'type': 'string', 'description': "Exact publisher, as `publicador` shows it. Comma-separated values are OR'd (up to 12, each up to 200 characters)."}}}
api_access
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.
只读
幂等
输入模式
{'type': 'object', 'properties': {'api_pass': {'type': 'string', 'description': 'MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying.'}}, 'additionalProperties': False}
api_access_buy
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.
输入模式
{'type': 'object', 'required': ['api_pass'], 'properties': {'payment': {'type': 'string', 'description': 'Signed x402 payload, after authorizing the quote.'}, 'api_pass': {'type': 'string', 'description': 'MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying.'}, 'transaction': {'type': 'string', 'description': 'Base transaction hash to reconcile an uncertain payment with the same pass and original payload.'}, 'credit_token': {'type': 'string', 'description': 'Existing prepaid credit token.'}}, 'additionalProperties': False}
api_index
API index
Self-describing index: the whole API surface, with quota and quickstart.
只读
幂等
输入模式
{'type': 'object', 'properties': {}}
api_usage
API usage
Remaining MAT read credits, without consuming credit.
只读
幂等
输入模式
{'type': 'object', 'required': ['api_pass'], 'properties': {'api_pass': {'type': 'string', 'description': 'MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying.'}}, 'additionalProperties': False}
billing
Billing
x402 configuration in force and the agent prices for contact and publishing.
只读
幂等
输入模式
{'type': 'object', 'properties': {}}
briefings_links
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.
只读
幂等
输入模式
{'type': 'object', 'properties': {'page': {'type': 'integer', 'default': 1, 'description': 'Page, from 1.'}, 'tipo': {'enum': ['paper', 'repo', 'model', 'dataset', 'demo', 'video', 'docs', 'article', 'post'], 'type': 'string', 'description': 'Source types, comma-separated.'}, 'topico': {'type': 'string', 'description': 'Topic slugs, comma-separated (from briefings_topics).'}}}
briefings_topics
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.
只读
幂等
输入模式
{'type': 'object', 'properties': {}}
contact
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.
输入模式
{'type': 'object', 'required': ['name', 'email', 'message'], 'properties': {'name': {'type': 'string', 'description': 'What to call the person writing.'}, 'site': {'type': 'string', 'description': 'Website of who is proposing.'}, 'tipo': {'enum': ['patrocinio', 'parceria', 'anuncio'], 'type': 'string', 'description': 'Proposal: `patrocinio`, `parceria` or `anuncio`. Turns on the fields below.'}, 'email': {'type': 'string', 'description': 'Where to reply.'}, 'espaco': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Placement ids from `GET /api/partners`, up to 6.'}, 'duracao': {'enum': ['30', '90', '365'], 'type': 'string', 'description': 'Exposure in days: `30`, `90` or `365`.'}, 'empresa': {'type': 'string', 'description': 'Who is proposing, when it is a company.'}, 'message': {'type': 'string', 'description': 'What you want to say.'}, 'orcamento': {'enum': ['ate_100', '100_500', '500_2000', '2000_mais', 'a_combinar'], 'type': 'string', 'description': '`ate_100`, `100_500`, `500_2000`, `2000_mais` or `a_combinar`.'}, 'pagamento': {'enum': ['usdc', 'deposito', 'a_combinar'], 'type': 'string', 'description': '`usdc`, `deposito` or `a_combinar`.'}}}
create_guest
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.
输入模式
{'type': 'object', 'properties': {}}
create_listing
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.
输入模式
{'type': 'object', 'required': ['kind', 'url'], 'properties': {'url': {'type': 'string', 'description': "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."}, 'body': {'type': 'string', 'description': 'Long description, optional.'}, 'kind': {'enum': ['mcp', 'skill', 'plugin', 'okf'], 'type': 'string', 'description': 'What is being registered.'}, 'name': {'type': 'string', 'description': 'Display name; without it, taken from the source.'}, 'tagline': {'type': 'string', 'description': 'One line saying what it is for.'}, 'category': {'type': 'string', 'description': 'Category so the listing shows up under the right filter.'}}}
feed_find
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.
只读
幂等
输入模式
{'type': 'object', 'required': ['dominio'], 'properties': {'dominio': {'type': 'string', 'description': 'Domain, with no scheme: example.com'}, 'api_pass': {'type': 'string', 'description': 'MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying.'}, 'retry_key': {'type': 'string', 'description': 'Optional retry key, up to 80 ASCII characters; same read for five minutes.'}}}
feed_post
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.
只读
幂等
输入模式
{'type': 'object', 'required': ['id', 'ord'], 'properties': {'id': {'type': 'string', 'description': 'Feed id, prefix fd_.'}, 'ord': {'type': 'integer', 'description': 'Position of the post in the feed; 0 is the newest.'}, 'api_pass': {'type': 'string', 'description': 'MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying.'}, 'retry_key': {'type': 'string', 'description': 'Optional retry key, up to 80 ASCII characters; same read for five minutes.'}}}
feed_posts
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.
只读
幂等
输入模式
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Feed id, prefix fd_.'}, 'api_pass': {'type': 'string', 'description': 'MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying.'}, 'retry_key': {'type': 'string', 'description': 'Optional retry key, up to 80 ASCII characters; same read for five minutes.'}}}
feed_search
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.
只读
幂等
输入模式
{'type': 'object', 'properties': {'q': {'type': 'string', 'description': 'Free text over name, description and domain.'}, 'tipo': {'enum': ['rss2', 'rss1', 'atom', 'json', 'rss'], 'type': 'string', 'description': 'rss2, rss1, atom, json (comma-separated = OR).'}, 'limit': {'type': 'integer', 'default': 20, 'description': 'Feeds per page, 1-50.'}, 'midia': {'enum': ['audio', 'video'], 'type': 'string', 'description': 'audio, video.'}, 'origem': {'enum': ['index', 'blogroll', 'bridge'], 'type': 'string', 'description': 'index, blogroll, bridge.'}, 'recurso': {'enum': ['content', 'itunes', 'podcast', 'media', 'slash', 'wfw', 'georss'], 'type': 'string', 'description': 'content, itunes, podcast, media, slash, wfw, georss.'}, 'api_pass': {'type': 'string', 'description': 'MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying.'}, 'retry_key': {'type': 'string', 'description': 'Optional retry key, up to 80 ASCII characters; same read for five minutes.'}, 'comunidade': {'enum': ['fediverse', 'indieweb', 'mastodon', 'friendica', 'wordpress', 'funkwhale', 'blogroll'], 'type': 'string', 'description': 'fediverse, indieweb, mastodon, friendica, wordpress, funkwhale.'}}}
get_bundle
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.
只读
幂等
输入模式
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Bundle id, the `id` of every item in the list.'}}}
get_listing
Get listing
One listing's page. The owner sees their own even when pending or hidden.
只读
幂等
输入模式
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Listing ID, from `Anuncio.id`.'}, 'api_pass': {'type': 'string', 'description': 'MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying.'}, 'retry_key': {'type': 'string', 'description': 'Optional retry key, up to 80 ASCII characters; same read for five minutes.'}}}
get_listing_readme
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.
只读
幂等
输入模式
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Listing ID, from `Anuncio.id`.'}, 'api_pass': {'type': 'string', 'description': 'MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying.'}, 'retry_key': {'type': 'string', 'description': 'Optional retry key, up to 80 ASCII characters; same read for five minutes.'}}}
go_listing
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.
只读
幂等
输入模式
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'ID of the listing to visit.'}}}
health
Health
Liveness and the commit deployed right now — it is how the smoke waits for its own deploy.
只读
幂等
输入模式
{'type': 'object', 'properties': {}}
index_stats
Index stats
Size of the index by provenance and when it last changed.
只读
幂等
输入模式
{'type': 'object', 'properties': {}}
like_listing
Like listing
Likes the listing; DELETE undoes it. Calling again does not add up: the counter counts people.
输入模式
{'type': 'object', 'required': ['id', 'guest_token'], 'properties': {'id': {'type': 'string', 'description': 'ID of the listing to like.'}, 'guest_token': {'type': 'string'}}}
list_comments
List comments
Comments on a live listing. With a credential on the call, each comment of yours comes with `mine: true`.
只读
幂等
输入模式
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'ID of the listing.'}}}
listing_history
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.
只读
幂等
输入模式
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Listing ID, from `Anuncio.id`.'}, 'api_pass': {'type': 'string', 'description': 'MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying.'}, 'retry_key': {'type': 'string', 'description': 'Optional retry key, up to 80 ASCII characters; same read for five minutes.'}}}
listing_status
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.
只读
幂等
输入模式
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'Listing ID, from the `id` of the `POST /api/listings` response.'}}}
list_listings
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`.
只读
幂等
输入模式
{'type': 'object', 'properties': {'q': {'type': 'string', 'description': '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 weighing most (10), then tagline (5), identifier (3), description (2), README excerpt (1); ties by stars. Kind, topic and transport words become filters. The `low` tail is in the same index.'}, 'low': {'enum': ['0'], 'type': 'string', 'description': '`0` leaves the `low` tail out; by default it comes after the `live` listings in every order.'}, 'kind': {'enum': ['mcp', 'skill', 'plugin'], 'type': 'string', 'description': 'Which kind of resource to fetch.'}, 'sort': {'enum': ['relevancia', 'recent', 'stars', 'likes', 'visits', 'nome'], 'type': 'string', 'default': 'relevancia when q is set, recent otherwise', 'description': '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 if pushed in the last 180 days + 0.1 if a README was collected; ties by stars — and a plain listing by arrival.'}, 'api_pass': {'type': 'string', 'description': 'MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying.'}, 'category': {'type': 'string', 'description': 'Category declared by whoever published.'}, 'interpret': {'enum': ['0'], 'type': 'string', 'description': '`0` disables query understanding and searches the raw string.'}, 'retry_key': {'type': 'string', 'description': 'Optional retry key, up to 80 ASCII characters; same read for five minutes.'}}}
list_mcp_servers
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.
只读
幂等
输入模式
{'type': 'object', 'properties': {'limit': {'type': 'number', 'default': 30, 'description': 'Servers per page.'}, 'cursor': {'type': 'string', 'description': 'Opaque cursor of the next page, from `metadata.next_cursor`.'}, 'search': {'type': 'string', 'description': "Free text over the server's name and description."}, 'api_pass': {'type': 'string', 'description': 'MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying.'}, 'retry_key': {'type': 'string', 'description': 'Optional retry key, up to 80 ASCII characters; same read for five minutes.'}}}
mcp_index_search
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.
只读
幂等
输入模式
{'type': 'object', 'properties': {'q': {'type': 'string', 'description': 'Substring of name, URL or repository.'}, 'casou': {'enum': ['0', '1'], 'type': 'string', 'description': '1 matched to a listing, 0 not in the catalog.'}, 'fonte': {'enum': ['wellknown', 'agent_tools', 'nerq', 'truespar', 'neuronto', 'paygent', 'hultra'], 'type': 'string', 'description': 'One index: wellknown, agent_tools, nerq, truespar, neuronto, paygent, hultra.'}, 'limit': {'type': 'integer', 'default': 20, 'description': 'Signals per page, 1-50.'}, 'estado': {'enum': ['vivo', 'fora', 'parado', 'abandonado', 'apagado', 'desconhecido'], 'type': 'string', 'description': 'vivo, fora, parado, abandonado, apagado, desconhecido.'}, 'api_pass': {'type': 'string', 'description': 'MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying.'}, 'retry_key': {'type': 'string', 'description': 'Optional retry key, up to 80 ASCII characters; same read for five minutes.'}}}
mcp_index_signals
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.
只读
幂等
输入模式
{'type': 'object', 'required': ['listing'], 'properties': {'listing': {'type': 'string', 'description': 'Listing id from list_listings.'}, 'api_pass': {'type': 'string', 'description': 'MAT-only private pass: mat_<32 random hex>_<64 random hex>. Generate and save before buying.'}, 'retry_key': {'type': 'string', 'description': 'Optional retry key, up to 80 ASCII characters; same read for five minutes.'}}}
pricing
Pricing
Current public prices and free allowances; no charge.
只读
幂等
输入模式
{'type': 'object', 'properties': {}, 'additionalProperties': False}
search_bundles
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.
只读
幂等
输入模式
{'type': 'object', 'properties': {'q': {'type': 'string', 'description': 'Free text over name, tagline, description and origin identifier.'}, 'repo': {'type': 'string', 'description': 'Only bundles of one repository, `owner/repo` (case-insensitive).'}, 'sort': {'enum': ['recent', 'updated', 'name', 'stars'], 'type': 'string', 'default': 'recent', 'description': 'Result order: arrival, last content change, name or repository stars.'}, 'type': {'type': 'string', 'description': 'Type declared by the root, not the types of every concept. Up to 5 comma-separated values, 40 characters each.'}, 'limit': {'type': 'integer', 'default': 24, 'description': 'Bundles per page, at most 100.'}, 'offset': {'type': 'integer', 'default': 0, 'description': 'How many bundles to skip. Use `next_offset` from the previous response; the list ends at 1000.'}, 'origin': {'enum': ['github', 'domain'], 'type': 'string', 'description': 'Provenance: found by the GitHub sweep, or submitted by a domain.'}, 'concept': {'type': 'string', 'description': 'Text in the indexed root content, including listed concept names and summaries (first 1000 characters); up to 80 characters.'}, 'license': {'type': 'string', 'description': 'Repository license. Up to 5 comma-separated values, 40 characters each.'}, 'version': {'type': 'string', 'description': 'Only bundles declaring one of these `okf_version` values; comma-separated, up to 5.'}, 'concepts': {'type': 'string', 'description': 'Number of entries listed by the root. Up to 5 comma-separated bands: 0,1-5,6-20,21-100,101+.'}, 'language': {'type': 'string', 'description': 'Only bundles whose repository language is one of these; comma-separated, up to 5 (GitHub bundles).'}}}
submit_okf
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://<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.
输入模式
{'type': 'object', 'required': ['host', 'key', 'urlList'], 'properties': {'key': {'type': 'string', 'description': '8 to 128 characters of [a-zA-Z0-9-].'}, 'host': {'type': 'string', 'description': 'The host that owns the bundles.'}, 'urlList': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Bundle `index.md` URLs. https, on `host`, ending in .md. No fixed path: the spec defines no discovery convention.'}, 'keyLocation': {'type': 'string', 'description': 'Where the key file lives. Defaults to `https://<host>/<key>.txt`; must be on `host`.'}}}
历史
近期工具变更
已更改
pricing
2026年9月29日 03:01
已更改
api_usage
2026年9月29日 03:01
已更改
api_access_buy
2026年9月29日 03:01
已更改
api_access
2026年9月29日 03:01
已更改
contact
2026年9月29日 03:01
已更改
billing
2026年9月29日 03:01
已更改
submit_okf
2026年9月29日 03:01
已更改
listing_status
2026年9月29日 03:01
已更改
create_listing
2026年9月29日 03:01
已更改
list_comments
2026年9月29日 03:01
已更改
like_listing
2026年9月29日 03:01
已更改
go_listing
2026年9月29日 03:01
已更改
listing_history
2026年9月29日 03:01
已更改
get_listing_readme
2026年9月29日 03:01
已更改
get_listing
2026年9月29日 03:01
已更改
list_mcp_servers
2026年9月29日 03:01
已更改
list_listings
2026年9月29日 03:01
已更改
create_guest
2026年9月29日 03:01
已更改
health
2026年9月29日 03:01
已更改
api_index
2026年9月29日 03:01
已添加
briefings_links
2026年9月29日 03:01
已添加
briefings_topics
2026年9月29日 03:01
已更改
a2a_agent
2026年9月29日 03:01
已更改
a2a_agent_search
2026年9月29日 03:01
已更改
mcp_index_search
2026年9月29日 03:01
已更改
mcp_index_signals
2026年9月29日 03:01
已更改
feed_search
2026年9月29日 03:01
已更改
feed_post
2026年9月29日 03:01
已更改
feed_posts
2026年9月29日 03:01
已更改
feed_find
2026年9月29日 03:01
发现
类似的 MCP 服务器
AI 代理人任務中樞
dev.workers.panda198271.agent-hub-tw/agent-hub
Provides an agent hub with Taiwan-focused tools for AI pricing, creator compliance, crypto data, games, health, technology resear…
x711 — Universal Agent Gas Station
io.github.0580iris-lang/x711-gas-station
Provides agents with web observation and interaction, search and retrieval, sandboxed computation, inter-agent communication, col…
Pipeworx
io.github.pipeworx-io/pipeworx-catalog
Acts as a gateway and catalog for discovering and calling thousands of structured data tools across many sources, with citations …
Bold Systems
io.github.pipeworx-io/bold-systems
Provides a routed interface to thousands of structured data tools and includes dedicated BOLD Systems tools for DNA barcode seque…
Data Va
io.github.pipeworx-io/data-va
Provides Socrata access to Virginia open datasets, including catalog search, metadata retrieval, and SoQL queries, alongside Pipe…
Data Orlando
io.github.pipeworx-io/data-orlando
Provides Socrata access to Orlando open datasets, including catalog search, metadata retrieval, and SoQL queries, alongside Pipew…
Data Ua
io.github.pipeworx-io/data-ua
Provides CKAN access to Ukraine open datasets, including dataset metadata and DataStore resource queries, alongside Pipeworx tool…
Data Oregon
io.github.pipeworx-io/data-oregon
Provides Socrata access to Oregon state open datasets across agencies, health, environment, business, and other domains, alongsid…