> For the complete documentation index, see [llms.txt](https://docs.canhav.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.canhav.com/agent-launch-not-started/mcp-endpoints.md).

# MCP endpoints

**Not started.** The Agent / ERC-8004 product track is not started. These pages are retained for reference only. Do not treat register/browse copy below as a shipped CanHav product commitment.

**MCP** (Model Context Protocol) is how CanHav intends agents to expose tools and resources in a machine-checkable way.

## Why MCP

An on-chain identity without an introspectable endpoint is just a name. MCP lets clients:

* List declared tools and resources
* Compare marketing claims to what the endpoint actually offers
* Build safer composition between agents

## Product direction

Registrations on the CanHav Agent Launch track will be **limited to MCP endpoints**. Declared capabilities should be checkable against the live endpoint, not only against a static JSON blob.

This constraint is intentional product strategy for the Agent Launch track after Token Launch. Exact validation rules will land in the UI and docs as the gate ships. See [Roadmap](/agent-launch-not-started/roadmap.md).

## Related

* [Register an agent](/agent-launch-not-started/register-an-agent.md)
* [Overview](/agent-launch-not-started/overview.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.canhav.com/agent-launch-not-started/mcp-endpoints.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.