X API FastMCP Server

X API FastMCP Server

A local MCP server that exposes the X API (formerly Twitter API) as tools, enabling operations like posting, searching, user management, and more via natural language commands.

Category
Visit Server

README

X API FastMCP Server

Run a local MCP server that exposes the X API OpenAPI spec as tools using FastMCP. Streaming and webhook endpoints are excluded.

Prerequisites

  • Python 3.9+
  • An X Developer Platform app (to get tokens)
  • Optional: an xAI API key if you want to run the Grok test client

Setup (local)

  1. Create a virtual environment and install dependencies:
    • python -m venv .venv
    • source .venv/bin/activate
    • pip install -r requirements.txt
  2. Create your local .env:
    • cp env.example .env
    • Required values (do not skip):
      • X_OAUTH_CONSUMER_KEY
      • X_OAUTH_CONSUMER_SECRET
      • X_BEARER_TOKEN (required for this setup; keep it set even if using OAuth1)
    • OAuth1 callback (defaults are fine):
      • X_OAUTH_CALLBACK_HOST (default 127.0.0.1)
      • X_OAUTH_CALLBACK_PORT (default 8976)
      • X_OAUTH_CALLBACK_PATH (default /oauth/callback)
      • X_OAUTH_CALLBACK_TIMEOUT (default 300)
    • Server settings (optional):
      • X_API_BASE_URL (default https://api.x.com)
      • X_API_TIMEOUT (default 30)
      • MCP_HOST (default 127.0.0.1)
      • MCP_PORT (default 8000)
      • X_API_DEBUG (default 1)
  • Tool filtering (optional, comma-separated):
    • X_API_TOOL_ALLOWLIST
  • Optional Grok test client:
    • XAI_API_KEY
    • XAI_MODEL (default grok-4-1-fast)
    • MCP_SERVER_URL (default http://127.0.0.1:8000/mcp)
  • Optional OAuth2 token generation:
    • CLIENT_ID
    • CLIENT_SECRET
    • X_OAUTH_ACCESS_TOKEN
- `X_OAUTH_ACCESS_TOKEN_SECRET` (optional)
  • Optional OAuth1 debug output:
    • X_OAUTH_PRINT_TOKENS
    • X_OAUTH_PRINT_AUTH_HEADER
  1. Register the callback URL in your X Developer App:
http://<X_OAUTH_CALLBACK_HOST>:<X_OAUTH_CALLBACK_PORT><X_OAUTH_CALLBACK_PATH>

Example (defaults):

http://127.0.0.1:8976/oauth/callback
  1. Start the server:
python server.py

The MCP endpoint is http://127.0.0.1:8000/mcp by default.

  1. Connect an MCP client:
  • Local client: point it to http://127.0.0.1:8000/mcp.
  • Remote client: tunnel your local server (e.g., ngrok) and use the public URL.

Whitelisting tools

Use X_API_TOOL_ALLOWLIST to load a small, explicit set of tools:

X_API_TOOL_ALLOWLIST=getUsersByUsername,createPosts,searchPostsRecent

Whitelisting is applied at startup when the OpenAPI spec is loaded, so restart the server after changes. See the full tool list below before building your allowlist.

OAuth1 flow (startup behavior)

On startup, the server opens a browser for OAuth1 consent and waits for the callback. Tokens are kept in memory only for the lifetime of the server process. Set X_OAUTH_PRINT_TOKENS=1 to print tokens, or X_OAUTH_PRINT_AUTH_HEADER=1 to print request headers.

Available tool calls (allowlist-ready)

Below is the full list of tool calls you can whitelist via X_API_TOOL_ALLOWLIST. Copy any of these into your .env allowlist.

  • addListsMember
  • addUserPublicKey
  • appendMediaUpload
  • blockUsersDms
  • createCommunityNotes
  • createComplianceJobs
  • createDirectMessagesByConversationId
  • createDirectMessagesByParticipantId
  • createDirectMessagesConversation
  • createLists
  • createMediaMetadata
  • createMediaSubtitles
  • createPosts
  • createUsersBookmark
  • deleteActivitySubscription
  • deleteAllConnections
  • deleteCommunityNotes
  • deleteConnectionsByEndpoint
  • deleteConnectionsByUuids
  • deleteDirectMessagesEvents
  • deleteLists
  • deleteMediaSubtitles
  • deletePosts
  • deleteUsersBookmark
  • evaluateCommunityNotes
  • finalizeMediaUpload
  • followList
  • followUser
  • getAccountActivitySubscriptionCount
  • getActivitySubscriptions
  • getChatConversation
  • getChatConversations
  • getCommunitiesById
  • getComplianceJobs
  • getComplianceJobsById
  • getConnectionHistory
  • getDirectMessagesEvents
  • getDirectMessagesEventsByConversationId
  • getDirectMessagesEventsById
  • getDirectMessagesEventsByParticipantId
  • getInsights28Hr
  • getInsightsHistorical
  • getListsById
  • getListsFollowers
  • getListsMembers
  • getListsPosts
  • getMarketplaceHandleAvailability
  • getMediaAnalytics
  • getMediaByMediaKey
  • getMediaByMediaKeys
  • getMediaUploadStatus
  • getNews
  • getOpenApiSpec
  • getPostsAnalytics
  • getPostsById
  • getPostsByIds
  • getPostsCountsAll
  • getPostsCountsRecent
  • getPostsLikingUsers
  • getPostsQuotedPosts
  • getPostsRepostedBy
  • getPostsReposts
  • getSpacesBuyers
  • getSpacesByCreatorIds
  • getSpacesById
  • getSpacesByIds
  • getSpacesPosts
  • getTrendsByWoeid
  • getTrendsPersonalizedTrends
  • getUsage
  • getUserPublicKeys
  • getUsersAffiliates
  • getUsersBlocking
  • getUsersBookmarkFolders
  • getUsersBookmarks
  • getUsersBookmarksByFolderId
  • getUsersById
  • getUsersByIds
  • getUsersByUsername
  • getUsersByUsernames
  • getUsersFollowedLists
  • getUsersFollowers
  • getUsersFollowing
  • getUsersLikedPosts
  • getUsersListMemberships
  • getUsersMe
  • getUsersMentions
  • getUsersMuting
  • getUsersOwnedLists
  • getUsersPinnedLists
  • getUsersPosts
  • getUsersRepostsOfMe
  • getUsersTimeline
  • hidePostsReply
  • initializeMediaUpload
  • likePost
  • mediaUpload
  • muteUser
  • pinList
  • removeListsMemberByUserId
  • repostPost
  • searchCommunities
  • searchCommunityNotesWritten
  • searchEligiblePosts
  • searchNews
  • searchPostsAll
  • searchPostsRecent
  • searchSpaces
  • searchUsers
  • sendChatMessage
  • unblockUsersDms
  • unfollowList
  • unfollowUser
  • unlikePost
  • unmuteUser
  • unpinList
  • unrepostPost
  • updateActivitySubscription
  • updateLists

Generate an OAuth2 user token (optional)

  1. Add CLIENT_ID and CLIENT_SECRET to your .env.
  2. Update redirect_uri in generate_authtoken.py to match your app settings.
  3. Run python generate_authtoken.py and follow the prompts.
  4. Copy the printed access token into .env as X_OAUTH_ACCESS_TOKEN. If your flow returns a secret, store it as X_OAUTH_ACCESS_TOKEN_SECRET.

Run the Grok MCP test client (optional)

  1. Set XAI_API_KEY in .env.
  2. Make sure your MCP server is running locally (or set MCP_SERVER_URL).
  3. If Grok is not running on your machine, use ngrok to expose your local MCP server and set MCP_SERVER_URL to the public HTTPS URL that ends with /mcp. Example flow: ngrok http 8000 then MCP_SERVER_URL=https://<id>.ngrok-free.dev/mcp.
  4. Run python test_grok_mcp.py.

Notes

  • Endpoints with /stream or /webhooks in the path are excluded.
  • Operations tagged Stream or Webhooks, or marked with x-twitter-streaming: true, are excluded.
  • The OpenAPI spec is fetched from https://api.twitter.com/2/openapi.json at startup.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured