An MCP server that gives Claude, Cursor, VS Code Copilot, and other AI assistants instant, offline access to TwitterAPI.io documentation. - 59 API endpoints with full HTTP method, body/query parameters, cURL examples, and response schemas - 32 guide pages covering pricing, authentication, rate limits, webhooks, streaming - 24 blog posts with tutorials and use cases - All v2 write endpoints documen
Add this skill
npx mdskills install dorukardahan/twitterapi-docs-mcpComprehensive offline documentation bundle for TwitterAPI.io with 59 endpoints, fuzzy search, and excellent setup guides
Offline TwitterAPI.io documentation for Claude and AI assistants via MCP. 59 endpoints (with full method/params/body), 32 guides, 24 blog posts. No API key needed.
# Quick install (Claude Code)
claude mcp add twitterapi-io -- npx -y twitterapi-io-mcp
An MCP server that gives Claude, Cursor, VS Code Copilot, and other AI assistants instant, offline access to TwitterAPI.io documentation.
login_cookies, proxy, and body paramsUnlike other Twitter MCP servers that proxy live API calls (and need your API key), this one ships a complete documentation snapshot. Your AI assistant reads it locally, instantly.
npm run scrape keeps data freshDisclaimer: Independent community project. Not affiliated with TwitterAPI.io.
Previously published as
twitterapi-docs-mcp? Just change the package name — everything else stays the same.
Requires: Node.js 18.18.0+
# Add globally (all projects)
claude mcp add --scope user twitterapi-io -- npx -y twitterapi-io-mcp
# Or project-only
claude mcp add twitterapi-io -- npx -y twitterapi-io-mcp
# Verify
claude mcp list
Add to your config file:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json~/.config/Claude/claude_desktop_config.json{
"mcpServers": {
"twitterapi-io": {
"command": "npx",
"args": ["-y", "twitterapi-io-mcp"]
}
}
}
Add to .cursor/mcp.json in your project root:
{
"mcpServers": {
"twitterapi-io": {
"command": "npx",
"args": ["-y", "twitterapi-io-mcp"]
}
}
}
Add to .vscode/mcp.json in your project root:
{
"servers": {
"twitterapi-io": {
"command": "npx",
"args": ["-y", "twitterapi-io-mcp"]
}
}
}
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"twitterapi-io": {
"command": "npx",
"args": ["-y", "twitterapi-io-mcp"]
}
}
}
docker run -i --rm $(docker build -q .) 2>/dev/null
Or build from source:
git clone https://github.com/dorukardahan/twitterapi-io-mcp.git
cd twitterapi-io-mcp && npm install
node index.js
| Tool | Description | Best for |
|---|---|---|
search_twitterapi_docs | Full-text search across all docs (fuzzy matching, typo-tolerant) | Finding endpoints, guides, or blog posts by keyword |
get_twitterapi_endpoint | Get full endpoint documentation with params, examples, response schema | Deep dive into a specific API endpoint |
list_twitterapi_endpoints | List endpoints, optionally filtered by category | Browsing what's available in a category |
get_twitterapi_guide | Get guide pages (pricing, auth, rate limits, webhooks, etc.) | Understanding platform rules and setup |
get_twitterapi_url | Fetch content by URL path or page key | When you have a direct link to docs |
get_twitterapi_pricing | Quick pricing overview | Cost questions |
get_twitterapi_auth | Quick authentication guide | Auth setup and API key usage |
If you're an AI assistant using this MCP server, here's a quick reference:
| User wants... | Use this tool | Example |
|---|---|---|
| Find an endpoint | search_twitterapi_docs | query: "advanced search" |
| Endpoint details | get_twitterapi_endpoint | endpoint_name: "tweet_advanced_search" |
| List all endpoints | list_twitterapi_endpoints | category: "user" (optional) |
| Pricing info | get_twitterapi_pricing | No params needed |
| Auth guide | get_twitterapi_auth | No params needed |
| Any guide/page | get_twitterapi_guide | guide_name: "qps_limits" |
| Fetch by URL | get_twitterapi_url | url: "pricing" |
Tips:
"twet object" still finds resultsmax_results: 5 for focused resultsdeprecation_notice field — some legacy endpoints have v2 replacementsHere are real prompts that work well with this MCP server:
get_twitterapi_guideget_twitterapi_endpointget_twitterapi_authget_twitterapi_pricinglist_twitterapi_endpoints with category: "user"search_twitterapi_docssearch_twitterapi_docs with query: "deprecated"get_twitterapi_endpoint callsAll 59 endpoints by category
| Category | Count | Endpoints |
|---|---|---|
| User | 12 | get_user_by_username, get_user_followers, get_user_followings, batch_get_user_by_userids, and 8 more |
| Tweet | 8 | tweet_advanced_search, get_tweet_by_ids, get_tweet_replies_v2, get_user_tweets, and 4 more |
| Community | 9 | create_community_v2, get_community_by_id, join_community_v2, and 6 more |
| Profile | 3 | update_avatar_v2, update_banner_v2, update_profile_v2 |
| Webhook | 4 | add_webhook_rule, get_webhook_rules, update_webhook_rule, delete_webhook_rule |
| Stream | 3 | add_user_to_monitor_tweet, get_user_to_monitor_tweet, remove_user_from_monitor_tweet |
| Action | 14 | create_tweet_v2, like_tweet_v2, retweet_tweet_v2, upload_media_v2, and 10 more |
| DM | 2 | send_dm_v2, get_dm_history_by_user_id |
| List | 2 | get_list_followers, get_list_members |
| Other | 2 | get_trends, get_space_detail |
| Environment Variable | Default | Description |
|---|---|---|
TWITTERAPI_MCP_DISK_CACHE | 1 (on) | Set to 0 to disable disk caching |
npx hangs or fails on first run
The first run downloads the package from npm. If it hangs, try:
npx -y twitterapi-io-mcp@latest
Or install globally: npm install -g twitterapi-io-mcp
"Node.js version not supported"
This server requires Node.js 18.18.0 or later. Check your version:
node --version
claude mcp add not recognized
Make sure Claude Code CLI is installed and up to date:
claude --version
Server starts but no tools appear
Restart your MCP client after adding the server config. Most clients (Claude Desktop, Cursor) need a restart to detect new MCP servers.
┌─────────────┐ MCP (stdio) ┌──────────────────┐
│ Claude / │ ◄──────────────────► │ twitterapi-io-mcp│
│ Cursor / │ │ │
│ VS Code │ │ Bundled docs │
└─────────────┘ │ (59 endpoints) │
└──────────────────┘
No network needed
| Property | Value |
|---|---|
| Runtime | Node.js 18.18.0+ (ES Modules, no build step) |
| Protocol | MCP via stdio |
| Caching | Hybrid (memory + disk), 24h TTL |
| Search | N-gram tokenization with fuzzy matching |
I use TwitterAPI.io daily for my projects. Switching between my editor and their docs site got old fast. So I packaged the entire documentation into an MCP server. Now I ask Claude and get answers without leaving my terminal.
If you work with the Twitter/X API through TwitterAPI.io, this saves you the same context-switching. Install it, forget about it, and just ask.
git clone https://github.com/dorukardahan/twitterapi-io-mcp.git
cd twitterapi-io-mcp
npm install
npm test # Run tests (52 tests)
npm start # Start server locally
npm run scrape # Update docs snapshot from twitterapi.io
If your AI tool doesn't support MCP (like OpenClaw), use the skill version instead — a single markdown file with all 55 endpoints:
👉 twitterapi-io-skill — works with OpenClaw, Claude, GPT, Gemini, and any LLM.
PRs welcome! Fork the repo, create a branch, make your changes, and open a pull request. Bug reports and feature requests go to GitHub Issues.
Install via CLI
npx mdskills install dorukardahan/twitterapi-docs-mcpTwitterapi IO MCP is a free, open-source AI agent skill. An MCP server that gives Claude, Cursor, VS Code Copilot, and other AI assistants instant, offline access to TwitterAPI.io documentation. - 59 API endpoints with full HTTP method, body/query parameters, cURL examples, and response schemas - 32 guide pages covering pricing, authentication, rate limits, webhooks, streaming - 24 blog posts with tutorials and use cases - All v2 write endpoints documen
Install Twitterapi IO MCP with a single command:
npx mdskills install dorukardahan/twitterapi-docs-mcpThis downloads the skill files into your project and your AI agent picks them up automatically.
Twitterapi IO MCP works with Claude Code, Claude Desktop, Cursor, Vscode Copilot, Windsurf, Continue Dev, Gemini Cli, Amp, Roo Code, Goose. Skills use the open SKILL.md format which is compatible with any AI coding agent that reads markdown instructions.