
Capabilities Txt Registry
io.github.capabilityhostprotocolPublished by GitHub account capabilityhostprotocolv0.1.0Updated Oct 24, 2026
Discover what websites across the agentic web can do — query the capabilities.txt registry.
Overview
A remote MCP server that lets an assistant query the capabilities.txt registry to discover what websites across the agentic web can do.
- What you can do
- Query the capabilities.txt registry to discover what hosts across the agentic web declare they can do, based on the public capabilities.txt convention and its structured JSON form. The manifest lists no individual tools, so the exact query operations are not documented here. The registry is a discovery layer only: it advertises capabilities and points to an MCP server, HTTP API or other endpoint for the actual invocation.
- When to use it
- Use it when an assistant needs to find out which websites or hosts offer a given capability, such as creating a support ticket or checking inventory, before deciding how to call them. It suits discovery and lookup rather than performing the actions themselves.
- Requirements
- A remote streamable HTTP endpoint at capabilitiestxt.org; no packages, environment variables, headers or authentication are declared, and the manifest marks it web executable.
Installation
In SourceWeft
- Open Capabilities Txt Registry in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.capabilityhostprotocol%2Fcapabilities-txt-registry/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"capabilities-txt-registry": {
"type": "http",
"url": "https://capabilitiestxt.org/api/mcp"
}
}
}README
capabilities.txt
A simple, open convention for a website to declare what it can do — the capabilities an agent can discover and invoke — at a well-known location.
The web taught machines to read in layers. robots.txt says what a crawler may
access. sitemap.xml says what exists. llms.txt says what's worth reading.
Each answers one narrow question for an automated reader.
None of them answers the question agents now ask: what can this host actually do?
Agents have stopped only reading the web and started acting on it. An agent that lands on your site can summarize your docs — but it has no standard way to discover that you expose a "create support ticket" capability, a "check inventory" capability, or "start a return," and how to call them. Today that happens through bespoke, one-vendor-at-a-time integrations.
capabilities.txt is the missing layer: a public, well-known file where a host
declares the capabilities it offers, so any agent can discover what it can do.
It is deliberately small. llms.txt worked because you could adopt it in an
afternoon. capabilities.txt follows the same rule.
The two forms
A host publishes one or both:
/capabilities.txt— human- and agent-readable markdown: capabilities grouped by category, each with an id, version, and one-line description./.well-known/capabilities.json— the structured form: an array of capability references, each resolvable to a full descriptor.
The markdown form is for discovery and reading. The JSON form is for machines that want structure. Publishing the markdown form alone is a perfectly good start.
Format (/capabilities.txt)
Rules, kept minimal:
- Line 1 is
# capabilities.txt. - A blockquote (
>) summary follows: one sentence on what the host offers, plus optional links (the JSON form, docs, an invocation endpoint). ##headings group capabilities by category (free-form, your choice).###headings name a group, optionally with a stable(group-id).- Each capability is a list item: a stable
capability-id, an optional(v<version>), and a short— description. - It's just markdown. If a human can read it and an agent can parse it, it's valid.
Structured form (/.well-known/capabilities.json)
Each entry is a reference; descriptor (optional) points to a full machine-readable
description of inputs, permissions, and how to invoke.
Where it sits among the standards
It is not a replacement for MCP or an API spec. The Model Context Protocol is a
stateful connection-and-invocation protocol; OpenAPI describes an HTTP API.
capabilities.txt is the layer before invocation — a static, public, crawlable
advertisement an agent (or a search engine) can read with no live connection, that
points to your MCP server, HTTP API, or other endpoint for the actual call.
Discovery and invocation are different jobs. capabilities.txt does discovery; it
hands off invocation.
Adopt it
Fastest (no spec): copy the prompt at capabilitiestxt.org/implement
and hand it to your AI coding agent — it writes your capabilities.txt from your code.
Have an OpenAPI spec? Generate it in your browser (paste the URL) — or keep it current automatically in CI with the GitHub Action:
Then check it at capabilitiestxt.org/submit for a grade, fixes, and a badge — and it’s discoverable in the directory + map.
By hand:
- List the capabilities your site exposes (or could).
- Write them into
/capabilities.txtusing the format above. - Optionally publish
/.well-known/capabilities.json. - Add yourself to
adopters.mdwith a pull request.
Already have an OpenAPI spec? Generate it — no manual authoring:
Working references — a real, live capabilities.txt plus illustrative templates
across markets (e-commerce, support, banking, healthcare, dev platform) — are in
examples/. The tools in tools/ generate and validate files.
Where this goes next
Discovery is the first step. Once an agent knows what you can do, the next
questions are may I, what happened, and can I prove it — invocation,
governance, and evidence. Those are defined by the
Capability Host Protocol (CHP), an open
protocol for which capabilities.txt is the natural public face. You can adopt
capabilities.txt on its own; CHP is where it leads if you need the rest.
Status & license
This is a proposal with a working reference, not a finished standard — and it's better for your feedback. Open an issue or PR.
- Specification & site text (
README.md,index.html,SPEC.md): CC BY 4.0 — seeLICENSE-DOCS. - Tooling (
tools/): Apache-2.0 — seeLICENSE. - "capabilities.txt" is a free, open convention — use it freely. (No trademark.)
Copyright © 2026 Project Auxo, Inc. and contributors.
Source: README.md at commit 1f62cab
Tools
0Version history
1- v0.1.0LatestSep 16, 2026
Score
40% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declaredRequired10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Declare a license in the repository or the registry entry.