Use Tavo.js with AI coding agents

Tavo.js MCP gives an AI coding agent a structured, searchable view of Tavo.js. The agent can discover Framework APIs, Tavo.js UI components, semantic tokens, and task-oriented guides instead of relying on generic framework assumptions.

Local mode can also inspect and verify a Tavo.js application through its project-local CLI. Model Context Protocol (MCP) is the connection between the AI client and Tavo.js; it does not replace the AI client or edit source code itself.

For instant documentation access, connect your MCP client to the public Tavo.js Streamable HTTP endpoint:

texthttps://mcp.tavojs.dev/mcp

Clients that accept JSON server definitions can use this common configuration shape. The filename and settings location depend on your client; merge the tavo entry into any existing server list:

json{
  "mcpServers": {
    "tavo": {
      "url": "https://mcp.tavojs.dev/mcp"
    }
  }
}

Reload the client's MCP connections after saving. Ask it to search Tavo.js documentation for “pages and layouts” and return the guide link. A successful tool response confirms the connection. Opening this URL in a browser is not an MCP connection test; the endpoint expects protocol requests from a compatible client.

Tavo.js MCP runs through npm without a global installation. Add the following server definition to the configuration used by your MCP client:

json{
  "mcpServers": {
    "tavo": {
      "command": "npx",
      "args": [
        "--yes",
        "@tavojs/mcp",
        "--project",
        "/absolute/path/to/tavo-app"
      ]
    }
  }
}

MCP client configuration formats differ, but the command and arguments are portable. Replace the example path with an absolute path to the target application. The application must provide a project-local @tavojs/cli package, which exposes the tavo binary.

Omit --project and its path to keep the local server documentation-only.

bash# Run from the application directory before enabling project tools.
node --version
npm install
npx tavo --version
npx tavo verify --no-project-scripts --json

Restart the MCP connection after changing the project path. Ask the client to read tavo://status: local project mode should report project.configured: true. Compare the installed package versions with the documentation snapshot before using a new API. A mismatch is a signal to verify the installed API; it does not automatically update your project or select a different documentation snapshot.

Use local stdio for coding work because it can align guidance with the installed Tavo.js version and actual project structure. The npm package also includes a stateless HTTP transport for operators who want to host public documentation access. HTTP mode never accepts a project path or exposes project tools.

Local transport describes where the MCP process runs. Your AI client may send returned source excerpts and diagnostics to its model provider according to its own settings. For self-hosting instructions, see the MCP deployment guide.

Start with a focused task so the agent can retrieve the relevant guide, then inspect only the files that need to change. These prompts can be used in sequence with a local project connection:

• Read tavo://status and report any package-version mismatch. Search the Tavo.js docs for a form with validation and summarize the documented pattern with links.

• Get project context for adding a settings form. Inspect the existing route and its related components, then explain the files and state changes needed.

• After the code has been changed through my coding client, verify the changed project-relative files with verify_tavo_project and explain every diagnostic.

Pass route targets as the patterns reported by tavo routes, such as /projects/:id, and file targets relative to the configured application such as src/pages/projects/[id].tsx. The absolute path belongs only in the server's --project configuration. A successful restricted verify result covers Tavo.js diagnostics; run your project's typecheck, tests, and production build separately to validate the feature.

A normal project typecheck script is arbitrary project code: despite its name, it can write files, access the network, or perform another side effect.

The adapter rejects incompatible Framework CLI versions rather than silently falling back to verification that could execute project scripts. Documentation compatibility is reported alongside project tool results.

The server bundles a validated public documentation snapshot and never reads the Tavo.js Website repository at runtime:

textTavo.js Website editorial source
  → export a validated public documentation manifest
  → bundle and index the snapshot in @tavojs/mcp
  → expose version and content hash to the MCP client

Documentation updates require a new validated snapshot and MCP release. The runtime needs neither Website source nor Website credentials.