radius-mcp-server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@radius-mcp-server search the docs for how to deploy a container"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
radius-mcp-server
A local MCP (Model Context Protocol) server that gives AI assistants everything they need to know about Radius:
Docs — full-text search and page reads over the official documentation (docs.radapp.io), sourced from a local cache of radius-project/docs.
Source — full-text search and file reads over radius-project/radius: Go source, architecture docs, design notes, specs, and TypeSpec/Bicep type definitions.
It needs no local setup: on first use it clones shallow, read-only caches of both repos for itself (see Data sources below).
Tools
Tool | Description |
| Full-text search over the Radius docs |
| Read one docs page (by URL, URL path, or slug) as clean markdown |
| Browse doc sections / list pages in a section |
| Refresh the local docs cache from GitHub |
| Full-text (or regex) search over the Radius source repo |
| Read a file from the Radius source repo |
| List a directory in the Radius source repo |
| Refresh the managed source cache from GitHub |
Related MCP server: directory-indexer
Quick start (once published to npm)
Most MCP clients just need to be told to run npx -y radius-mcp-server. See Connecting it to an MCP client for exact config per tool. Requires Node.js 18+ and git on PATH.
Data sources
Source | Local cache | |
Docs |
|
|
Source |
|
|
Both are shallow (--depth 1) clones made on first use and left in place across runs; call radius_docs_sync / radius_source_sync to pull the latest.
If you already have a local radius-project/radius checkout you'd rather use instead of a managed clone — e.g. you're working in it directly — point RADIUS_REPO_PATH at it (or run this server from a directory with a sibling radius/ folder, which is auto-detected). When set, that checkout is treated as yours to manage; radius_source_sync becomes a no-op and the tools just read from it as-is.
Connecting it to an MCP client
All of these assume the package is published; swap npx -y radius-mcp-server for node /absolute/path/to/radius-mcp-server/dist/index.js to point at a local build instead (see Development).
Claude Code
claude mcp add radius -- npx -y radius-mcp-serverOr add manually to .mcp.json (project-scoped) or ~/.claude.json (user-scoped):
{
"mcpServers": {
"radius": {
"command": "npx",
"args": ["-y", "radius-mcp-server"]
}
}
}Restart Claude Code (or run /mcp to check connection status) and the radius_* tools will be available.
Claude Desktop
Add the same block to your Claude Desktop config
(~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"radius": {
"command": "npx",
"args": ["-y", "radius-mcp-server"]
}
}
}Restart Claude Desktop to pick up the new server.
VS Code (GitHub Copilot Chat)
Add to .vscode/mcp.json in your workspace (or via "MCP: Open User Configuration" for a user-wide install). Note the top-level key is servers, not mcpServers:
{
"servers": {
"radius": {
"command": "npx",
"args": ["-y", "radius-mcp-server"]
}
}
}VS Code will prompt to start the server the first time it's used; check its status via the MCP Servers view.
GitHub Copilot coding agent
In the repository's Settings → Copilot → Coding agent → MCP configuration, add:
{
"mcpServers": {
"radius": {
"type": "local",
"command": "npx",
"args": ["-y", "radius-mcp-server"],
"tools": ["*"]
}
}
}type and tools are required by Copilot coding agent's schema (unlike the other clients above). See GitHub's MCP docs if you want to allowlist specific tools instead of ["*"].
Other clients (Cursor, Windsurf, ...)
Most other MCP-capable tools follow the same mcpServers convention as Claude Desktop above — check the client's docs for the exact config file location.
Publishing to npm
To publish a new version (maintainers only):
npm login # once, if not already logged in
npm run build # or rely on the prepublishOnly hook
npm version patch # or minor / major — bumps package.json + tags
npm publish # prepublishOnly runs the build automatically
git push --follow-tagsnpm publish is public and effectively permanent (npm blocks re-publishing a given version, and unpublishing after 72h is restricted) — double-check package.json's version and the tarball contents (npm pack --dry-run) before running it.
Development
npm install
npm run build # one-off build
npm run dev # tsc --watch
npm start # run the built server directly on stdio (Ctrl+C to stop)Re-run npm run build (or use npm run dev in the background) after editing anything in src/, then restart the server in your MCP client to pick up changes.
Available Tools
4 toolsradius_docs_syncRefresh the local Radius documentation cacheA
Pulls the latest changes from the radius-project/docs GitHub repo (the source of https://docs.radapp.io/) into the local cache. Call this if answers seem stale; otherwise the cache is reused as-is across calls.
Inputs: no named parameters.
radius_source_readRead a file from the Radius source repoA
Reads the full content of one file from a checkout of radius-project/radius by its path relative to the repo root, e.g. "pkg/recipes/engine/engine.go" or "docs/architecture/README.md".
Inputs: path (required).
radius_source_searchSearch the Radius source repoA
Full-text search over a checkout of radius-project/radius: Go source (pkg/, cmd/), architecture docs and design notes (docs/architecture, eng/design-notes), specs, TypeSpec/Bicep type definitions, and more. If no local checkout is configured, this server clones a shallow copy itself on first use (may take a bit the first time). Use this for implementation details, resource-provider internals, or design rationale that isn't covered in the published docs.
Inputs: query (required), limit, useRegex, pathPrefix.
radius_source_syncRefresh the local Radius source cacheA
Pulls the latest changes from radius-project/radius into this server's managed cache. Only applies when no external checkout was configured (RADIUS_REPO_PATH unset and no sibling radius/ directory); otherwise this is a no-op since your checkout is yours to manage.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: searching source code, reading a specific file, syncing source cache, and syncing docs cache. No overlap in functionality.
All tools follow a consistent 'radius_{source|docs}_{action}' pattern with snake_case. The verb 'sync' is used for both sync tools, maintaining uniformity.
Four tools is well-scoped for accessing source code and documentation. It covers search, read, and sync operations without unnecessary bloat.
The set covers search, read, and cache management, but lacks a directory listing tool. However, search can be used to find files by name, mitigating the gap.
Related MCP Connectors
Versioned documentation registry and semantic search for AI tools and coding assistants.
Ingest, manage, and retrieve documents for RAG-powered AI applications
Read-only search over the aidata.stream documentation, blog, changelog, pricing and FAQ.
Securely search and manage workspace context files for AI agents and teams.
Related MCP Servers
- AlicenseAqualityDmaintenanceProvides tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their responses with relevant documentation context.71MIT
- AlicenseNot gradedqualityBmaintenanceProvides AI assistants with semantic search and read access to local files and directories, enabling knowledge retrieval from indexed content.19 npm17MIT
- AlicenseNot gradedqualityDmaintenanceProvides semantic search over markdown documentation using RAG, allowing natural language queries and integration with MCP clients.1MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to explore, search, and read codebase repositories and API specifications efficiently, with support for file searching, content search via ripgrep, and reading API specs.ISC