LLM integrations

Mochi offers several ways to give an LLM up-to-date documentation. We recommend either the Agent skill or the MCP server. You can also use the older llms.txt format.

Agent skill (recommended)

Mochi publishes a SKILL.md that tells a coding assistant to fetch the relevant docs and demos from /llms.txt before writing framework code. Pull the latest copy into your project with the CLI:

bunx mochi-framework update-skill [agent]

This fetches https://mochi.fast/SKILL.md and writes it into your project. Run it again whenever you upgrade the framework.

The optional agent argument controls where the skill is written (default: claude-code):

MCP Server (recommended)

Mochi runs an official remote MCP server at https://mochi.fast/mcp (HTTP transport). It exposes the same docs and demos as the skill — get_documentation_sections to list everything and get_section to read specific pages. Add it to your tool of choice below.

claude mcp add -t http -s project mochi https://mochi.fast/mcp

experimental_use_rmcp_client = true
[mcp_servers.mochi]
url = "https://mochi.fast/mcp"

{ "mcpServers": { "mochi": { "url": "https://mochi.fast/mcp" } } }

{ "mcpServers": { "mochi": { "type": "http", "serverUrl": "https://mochi.fast/mcp" } } }

{ "mcpServers": { "mochi": { "type": "http", "serverUrl": "https://mochi.fast/mcp" } } }

{ "mcpServers": { "mochi": { "url": "https://mochi.fast/mcp" } } }

{ "mcpServers": { "mochi": { "type": "http", "url": "https://mochi.fast/mcp", "tools": ["*"] } } }

llms.txt

/llms.txt is the index: a title, a one-line summary, and a linked list of every doc (## Docs), demo (## Examples), and blog post (## Blog), each pointing at its own plain-text file. The concatenated bundles below are linked under ## Optional.

All docs concatenated

The full set of docs, concatenated in reading order, is served at /llms-recommended.txt. Use it when you want the model to have the complete API in one paste.

Docs + demo source

/llms-full.txt includes everything in /llms-recommended.txt plus the source of every demo, every blog post, and the changelog. Use it when the model needs both the API and working examples.

Per-document text

Each doc is reachable as plain text at /docs/<slug>/llms.txt, for example /docs/intro/llms.txt. The “Copy as llms.txt” button on each doc page emits just that page.

The changelog is served the same way at /docs/changelog/llms.txt, and reads as a page at /docs/changelog/. Mochi fetches it from GitHub, so both return 503 (not 404) when that fetch is unavailable.

Per-post text

Each published blog post is reachable as raw markdown at /blog/<slug>/llms.txt, for example /blog/mochi-0-8-0/llms.txt.

Per-demo source

Each demo’s source is reachable as plain text alongside its demo page, usually /demos/<slug>/llms.txt. It is the exact source /llms-full.txt bundles for that demo, scoped to one demo:

• /demos/hello-world/llms.txt
• /demos/chat/llms.txt

Machine-readable index

/llms.json returns a JSON index of every doc, blog post, and demo, each with its title, description, and an absolute url to its llms.txt.

{
  "docs": [{ "title": "Welcome", "description": "…", "url": "https://mochi.fast/docs/intro/llms.txt" }],
  "posts": [{ "title": "Mochi 0.8.0", "description": "2026-07-21 — …", "url": "https://mochi.fast/blog/mochi-0-8-0/llms.txt" }],
  "demos": [{ "title": "Hello World", "description": "…", "url": "https://mochi.fast/demos/hello-world/llms.txt" }]
}