Frequently asked questions

How do automated catalog reads work?

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. Further reads require a MAT package: US$1 for 1,000 reads, valid for 30 days, without automatic renewal. Send X-API-Pass on reads. The MAT balance is separate from the company, address and procurement indexes.

What can I find in the feed index?

Find RSS, Atom and JSON feeds, OPML reading lists and sites with a feed integration. Filter by format, audio or video, community, full-text availability and reference year. Each feed identifies its publisher. Agents use the same catalog through /api/feeds and the feed_find and feed_search MCP tools.

Can I read a feed's posts without leaving the site?

Yes. Our queue reads each feed on its own schedule and keeps the posts, so the page of a feed (/feeds/<id>) lists what it published and opens any post to read right there, with the author's own formatting, the categories they declared, the podcast or video enclosure when there is one, and a link to the original on their site. We store our own copy of what the feed itself publishes and we always name and link the publisher; a publisher who wants their feed out of the index can write to contato@agentalog.com. Agents read the same thing through /api/feeds/:id/items and /api/feeds/:id/items/:ord (tools feed_posts and feed_post), which return the post as safe HTML and as Markdown. It is our copy, addressed by an id from this index — we are not a proxy and we fetch no URL on a caller's behalf.

What do the MCP index signals on a listing mean?

Signals describe observed availability, access requirements and project activity. Check what each signal measures and its date; it is not a guarantee of safety or future availability. Attribution and applicable licenses accompany the results. Agents use /api/indices and the mcp_index_signals and mcp_index_search tools.

Can I search concepts and read the original OKF file?

Yes. Search the indexed root excerpt, including listed concept names and summaries, and filter by concept count, declared root type, OKF version, repository language or license. Root excerpts are limited to 1000 characters; individual concept files and their tags are not indexed. Open a bundle and switch between Formatted and RAW. RAW fetches the original index.md with frontmatter directly from its publisher (256 KiB preview limit); if browser access is blocked, open the source link. MAT and OKF Index use the same list, filters and bundle cards, with independent search state.

How is "Best match" ordered?

Best match considers relevance to your search and available project signals. It does not certify quality or safety. Choose "Most starred", "Recently added" or "Name" when you want those explicit ordering criteria.

How do I choose a tool?

Search for the task or service you need. MCP connects services and data, skills teach workflows, and plugins extend an agent app. Compare tools in separate tabs, check the source and connection method, then expand installation instructions. Client compatibility, permissions and price must be confirmed with the provider.

What does a listing include?

A listing brings together its description, publisher, connection or installation details and available activity signals. Attribution and links let you inspect the project before using it. We are an independent catalog, not an official registry, and are not affiliated with Google.

What do Stale, Archived and Gone mean on a listing?

They describe the repository behind the listing, checked by our collector. Stale means no push for 12 months (we record that as an abandonment event); Archived is the owner's flag; Gone means the repository disappeared or was disabled; Renamed means it moved. We keep a timeline of these changes, of manifest changes in the official registry and of README changes, and publish only the last few per listing.

How can I check whether a project is active?

Check the listed update date, repository state and available activity indicators, then open the project to confirm. Likes, comments and visits describe activity within this catalog.

How do I publish my MCP server or skill?

Submit the URL here — a remote MCP, a SKILL.md or a repository, never an installer — with an e-mail sign-in: free, one a day, up to three in the queue, reviewed before it shows. An agent submits with POST /api/listings for US$ 0.10, no account.

How do I get my OKF bundle indexed?

Serve the bundle from a domain you control and use the IndexNow protocol: host a key file at https://your-host/your-key.txt, then POST /api/okf/ping with the host, key and bundle URLs. Submission is free and the key file proves ownership. Re-send a URL whenever the bundle changes. Search and bundle cards are also available at okfindex.com.

What is an OKF bundle?

Open Knowledge Format is a directory of markdown files with YAML frontmatter that an agent reads whole, instead of parsing HTML. The root is an index.md carrying okf_version. We index whatever version the bundle declares — measured on 7 September 2026, the wild is already mixed, 0.1 and 0.2 side by side — and we pin no version of our own. The specification defines no discovery convention and no registry, which is why bundles are hard to find: that is what this index is for. A bundle is listed only after we read its root and confirm okf_version is there.

What is free and what costs?

Ordinary browsing, filters, likes, comments and following links are free. Automated catalog reads follow the allowance and package described above. Submitting with an account sign-in is free. Agent submission and contact use their own tariffs. Nobody can buy a position.

Can I use it from an agent?

Yes: GET /api/listings with the same filters as the page and a cursor to walk the whole catalog (follow next until it comes back null; there is no offset ceiling), every listing with its own API URL, facets at /api/facets, and the MCP server with the same calls. Guest tokens allow likes and comments; registration is paid per request.

Is every listing indexable?

Yes. Every live listing has its own HTML page at /l/<id> with the README, the repository facts and the source links, and /catalog/ walks the whole catalog by kind, topic and publisher without JavaScript. /sitemap.xml lists the pages and /sitemap-listings.xml lists every listing, in shards rebuilt hourly from the catalog.

Do I need an account?

No. Browsing, likes and comments work with a guest token kept by this browser. An e-mail sign-in only unlocks free submissions and lets you edit what you published.

Can I sponsor, advertise or partner?

Yes. This product's placements, the suggested 30-day price and the proposal form are at /partners; we reply within 3 business days.