TanStack 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., "@TanStack MCP Server search the TanStack Query docs for cache invalidation examples"
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.
@g7aro/tanstack-mcp
MCP server that wraps the TanStack CLI to provide programmatic access to TanStack documentation, libraries, add-ons, ecosystem partners, and project scaffolding.
Built as a drop-in replacement after TanStack removed the built-in MCP server from @tanstack/cli.
Tools
Tool | Description |
| List all available TanStack Start add-ons for a given framework |
| Get detailed info about a specific add-on (files, deps, options, routes) |
| Scaffold a new TanStack Start app with add-ons and options |
| List all TanStack libraries with descriptions and links |
| Fetch the full content of a TanStack documentation page |
| Search across TanStack documentation |
| List TanStack ecosystem partners with optional filters |
Related MCP server: Salt MCP
Quick Install
Auto-detect installed AI clients and register the MCP server in one command:
npx @g7aro/tanstack-mcp --installThis will detect and configure all supported clients on your machine.
Options
npx @g7aro/tanstack-mcp --install # Interactive — pick which clients
npx @g7aro/tanstack-mcp --install --all # Install into all detected clients
npx @g7aro/tanstack-mcp --install cursor codex # Install into specific clients only
npx @g7aro/tanstack-mcp --uninstall # Remove from all clientsSupported clients
Client | Detection | Config method |
Claude Code |
|
|
Codex (OpenAI) |
|
|
Cursor |
|
|
Windsurf |
|
|
Trae |
|
|
Antigravity |
|
|
OpenCode |
|
|
Zed |
|
|
VS Code (Copilot) |
|
|
Manual Setup
If you prefer to configure manually, add to your client's MCP config:
{
"mcpServers": {
"tanstack": {
"command": "npx",
"args": ["-y", "@g7aro/tanstack-mcp"]
}
}
}Tools
Tool | Description |
| List all available TanStack Start add-ons for a given framework |
| Get detailed info about a specific add-on (files, deps, options, routes) |
| Scaffold a new TanStack Start app with add-ons and options |
| List all TanStack libraries with descriptions and links |
| Fetch the full content of a TanStack documentation page |
| Search across TanStack documentation |
| List TanStack ecosystem partners with optional filters |
Prerequisites
Node.js >= 18
npxavailable in PATH (ships with npm)
How it works
Each MCP tool maps to a @tanstack/cli command with --json output:
listTanStackAddOns -> tanstack create --list-add-ons --framework <f> --json
getAddOnDetails -> tanstack create --addon-details <id> --framework <f> --json
createTanStackApplication -> tanstack create <name> --framework <f> --add-ons <a,b> ...
tanstack_list_libraries -> tanstack libraries --json
tanstack_doc -> tanstack doc <library> <path> --json
tanstack_search_docs -> tanstack search-docs "<query>" --json
tanstack_ecosystem -> tanstack ecosystem --jsonThe server spawns npx @tanstack/cli for each invocation, parses the JSON output, and returns it through the MCP protocol over stdio.
Development
npm install
npm run build # compile TypeScript -> dist/
npm start # run the server (stdio)
npm run dev # watch modeLicense
MIT
Available Tools
7 toolscreateTanStackApplicationB
Scaffold a new TanStack Start application with the specified add-ons and options
Inputs: projectName (required), framework, addOns, packageManager, +6 more.
getAddOnDetailsA
Get detailed information about a specific TanStack Start add-on (files, dependencies, options, routes)
Inputs: addonId (required), framework.
listTanStackAddOnsA
List all available TanStack Start add-ons for a given framework
Inputs: framework.
tanstack_docA
Fetch the full content of a specific TanStack documentation page
Inputs: library (required), path (required), docsVersion.
tanstack_ecosystemB
List TanStack ecosystem partners (auth, database, deployment, monitoring, etc.) with optional category/library filters
Inputs: category, library.
tanstack_list_librariesA
List all TanStack libraries with their descriptions, supported frameworks, and links
Inputs: group.
tanstack_search_docsA
Search across TanStack documentation for a query string. Returns matching pages with titles, URLs, and breadcrumbs.
Inputs: query (required), library, framework, limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Each tool has a distinct purpose: scaffolding (create, list add-ons, get add-on details), documentation (fetch page, search, list libraries, list ecosystem partners). No overlap.
First three tools use camelCase (createTanStackApplication, getAddOnDetails, listTanStackAddOns) while last four use lowercase underscores (tanstack_doc, etc.). Also, the first three include verb-noun pattern but the last four lack clear action verbs in names (e.g., tanstack_doc is just a noun).
Seven tools is well-scoped for a server covering TanStack Start scaffolding and documentation reference. Not too many, not too few.
The set covers key scaffolding operations (create, list, get details) and comprehensive documentation access (search, fetch, list libraries, list ecosystem). No obvious gaps for the intended domain.
Maintenance
Related MCP Connectors
Search, read and install agent-ready React components, screens and blocks for AI products.
Gives AI agents direct access to your Sanity projects and guidance for working with them
Versioned documentation registry and semantic search for AI tools and coding assistants.
Search @imqueue docs and scaffold typed services & clients from your AI coding agent.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceWraps the GitHub Copilot CLI to provide natural language command suggestions, explanations, and shell configuration for shell, git, and GitHub CLI commands through the Model Context Protocol.1MIT
- AlicenseAqualityDmaintenanceEnables AI agents to build React applications using JP Morgan Chase's Salt Design System by providing real-time access to component APIs, documentation, and accessibility guidelines. It supports tasks such as scaffolding new projects, building UI patterns, and converting Figma designs into Salt code via the Model Context Protocol.61ISC
- AlicenseDqualityDmaintenanceEnables AI assistants to manage cloud infrastructure using Pulumi by running commands like preview, deploy, and stack output retrieval through the Model Context Protocol.5Apache 2.0
- AlicenseAqualityDmaintenanceEnables AI assistants to access and work with Radix UI libraries (Themes, Primitives, Colors) by retrieving components, documentation, and installation guides through the Model Context Protocol.11102 npm8MIT