mcpField
C
capawesome

capawesome

Remote
capawesome.ioDeveloper Tools2Updated 7w ago

About capawesome

capawesome is the official MCP server for Capawesome, giving AI assistants searchable documentation for its plugins, Capawesome Cloud, and CLI. With an API token, it also exposes tools to manage Capawesome Cloud apps, channels, builds, and deployments.

Key features

  1. 01Search documentation and retrieve pages
  2. 02List blog posts
  3. 03Manage Capawesome Cloud apps
  4. 04Manage channels, builds, and deployments
  5. 05Configure toolsets and read-only access

Use cases

  1. 01Find Capawesome plugin documentation
  2. 02Look up Capawesome Cloud and CLI guidance
  3. 03Manage cloud apps through an AI assistant
  4. 04Restrict operations to read-only tools

MCP support

The hosted endpoint supports remote MCP clients over HTTP, and an npx package provides a stdio proxy. Documentation tools require no token; Capawesome Cloud management tools require an API token.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.capawesome.io/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Packages
npm@capawesome/mcp0.0.2

Tools

3
ParameterTypeRequiredDescription
limitintegerNoThe maximum number of results to return, e.g. 5. Defaults to 10, maximum 25.
querystringYesThe search terms, e.g. "live update rollback" or "biometrics android setup". Plain keywords work best; no search operators are supported.
sectionenumNoRestrict the search to one part of the documentation: "sdks" (plugin references and guides), "cloud" (Capawesome Cloud), "insiders" (Capawesome Insiders) or "blog" (articles and release notes). Defaults to searching everything.sdks | cloud | blog | insiders

Details

From the project README

Capawesome MCP Server

The official MCP server for Capawesome. It gives AI assistants the current Capawesome documentation — plugins, Capawesome Cloud, Capawesome Insiders and the CLI — and, with an API token, the Capawesome Cloud management API for apps, channels, builds, deployments and more.

Maintained by Capawesome.

Endpoint

The server is hosted and ready to use:

https://mcp.capawesome.io/mcp

The documentation tools need no account and no token. The Capawesome Cloud tools are only available when the request carries an API token — see Authentication.

Installation

Claude Code

For the documentation tools, no token is needed:

claude mcp add --transport http capawesome https://mcp.capawesome.io/mcp

To add the Capawesome Cloud tools, pass your API token as a bearer header and select the toolsets:

claude mcp add --transport http capawesome "https://mcp.capawesome.io/mcp?toolsets=all" \
  --header "Authorization: Bearer YOUR_TOKEN"
Claude Desktop / Claude.ai

Go to Settings → Connectors → Add custom connector and enter:

  • Name: Capawesome
  • URL: https://mcp.capawesome.io/mcp
Cursor

Install in Cursor

Or add .cursor/mcp.json to your project:

{
  "mcpServers": {
    "capawesome": {
      "url": "https://mcp.capawesome.io/mcp"
    }
  }
}
VS Code

Install in VS Code

Or add .vscode/mcp.json to your project:

{
  "servers": {
    "capawesome": {
      "type": "http",
      "url": "https://mcp.capawesome.io/mcp"
    }
  }
}
Windsurf

Add the server to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "capawesome": {
      "serverUrl": "https://mcp.capawesome.io/mcp"
    }
  }
}
Zed

Add the server to your Zed settings.json:

{
  "context_servers": {
    "capawesome": {
      "url": "https://mcp.capawesome.io/mcp"
    }
  }
}
Any client via npx

Clients that cannot connect to a remote server over HTTP can run this package, which proxies stdio to the hosted server:

{
  "mcpServers": {
    "capawesome": {
      "command": "npx",
      "args": ["-y", "@capawesome/mcp"],
      "env": {
        "CAPAWESOME_TOKEN": "your-token"
      }
    }
  }
}

Requires Node.js 22 or later. Omit env to use the documentation tools only.

Authentication

Create an API token in the Capawesome Cloud Console and pass it to the server.

When connecting over HTTP, send it as an Authorization: Bearer <token> header. When running this package, set the CAPAWESOME_TOKEN environment variable and the proxy sends the header for you.

Without a token, only the documentation tools are registered — the Capawesome Cloud tools are absent, not merely hidden.

Configuration

These environment variables configure the proxy. They apply to this package only; over HTTP, use the equivalent header and query parameters.

VariablePurpose
CAPAWESOME_TOKENAPI token, sent as Authorization: Bearer. Optional; without it only the documentation tools are available.
CAPAWESOME_MCP_TOOLSETSComma-separated toolsets to register, sent as ?toolsets=. Use cloud for every Capawesome Cloud toolset or all for everything. Defaults to docs.
CAPAWESOME_MCP_READONLYSet to true to skip every tool that writes or deletes, sent as ?readonly=true.
CAPAWESOME_MCP_URLOverride the endpoint. For development only.

Tools

The server exposes the documentation tools (search_docs, get_doc_page, list_blog_posts) plus the cloud_* tools for the Capawesome Cloud management API, grouped into toolsets.

See the MCP documentation for the full tool and toolset reference.

Rate limits

The endpoint is limited to 100 requests per minute per IP. Requests over the limit are answered with 429 Too Many Requests; retry after a short wait.

Privacy

Your IP address is processed for rate limiting only. Queries and tool arguments are not stored, not logged beyond Cloudflare's standard edge logs, and never used for training. Your API token is used to authenticate against the Capawesome Cloud API on your behalf and is not stored by the server. See the Privacy Policy for details.

Related

Development

npm install
npm run build
npm test

Set CAPAWESOME_MCP_URL to point the proxy at a local server instead of the hosted one:

CAPAWESOME_MCP_URL=http://localhost:8787/mcp node dist/index.js

Release

Releases are managed by release-please. Merging its release pull request tags the version, publishes the package to npm and then publishes server.json to the MCP Registry. The version in server.json is bumped by release-please together with package.json, so it never has to be edited by hand. To publish to the registry manually, install mcp-publisher, run mcp-publisher login dns --domain=capawesome.io --private-key=<key> with the Ed25519 private key from the password manager and then mcp-publisher publish.

License

See LICENSE.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.