About Mcp X Intelligence
mcp-x-intelligence is an MCP server for X/Twitter research that runs inside Claude, Cursor and other MCP-compatible clients to search viral posts, analyze accounts and track trends. It is aimed at content creators, marketers and researchers, is read-only, and gets its data from twitterapi.io.
Key features
- 01Keyword search for high-engagement posts with filters
- 02Account profile analysis with top posts and engagement rate
- 03Real-time trending topics by country
- 04Discovery of top accounts in a niche
- 05Read-only access with no posting or direct messages
Use cases
- 01Researching viral content in a niche before writing posts
- 02Analyzing a competitor's account and content strategy
- 03Monitoring real-time trending topics across regions
MCP support
The project runs as an MCP server and provides 4 tools to MCP clients such as Claude and Cursor for searching X data, analyzing accounts and querying trends.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEmcp-x-intelligence — X/Twitter Research MCP for Claude, Cursor & AI Agents
Search viral content, analyze X accounts, track trending topics and discover niche leaders — directly from Claude, Cursor, Windsurf or any MCP-compatible AI agent. Powered by twitterapi.io. No posting. No DMs. Pure read-only research.
What it does — 4 X Research Tools for AI Agents
| Tool | What it does | Example prompt |
|---|---|---|
search_viral_content | Find top posts by keyword with engagement filters (likes, retweets, time window) | "Find the most viral posts about AI agents in the last 48h" |
analyze_account | Full profile analysis: followers, top posts, engagement rate, active hours | "Analyze @fluyeporlaweb and tell me their best content strategy" |
get_trending_topics | Trending topics by country in real time | "What's trending in Spain and Mexico right now?" |
get_niche_leaders | Top accounts in any niche sorted by follower count | "Who are the top 10 AI tool creators on X?" |
Compatible with Every Major MCP Client
Claude Desktop · Claude Code · Cursor · Windsurf · Cline · Codex CLI · Gemini CLI · any MCP-compatible AI agent
Quick Start
Option 1 — Hosted Version via MCPize (No Setup Required)
Recommended for non-technical users. No API key, no Node.js, nothing to install. Just connect and start researching.
→ Use mcp-x-intelligence on MCPize
| Plan | Calls/month | Price |
|---|---|---|
| Free | 50 | Free |
| Pro | 1,000 | $9/mo |
Option 2 — BYOK: Bring Your Own twitterapi.io Key (Free)
Connect directly to our hosted endpoint using your own API key. No server setup needed — we host the MCP server for you.
Step 1 — Get a free twitterapi.io API key
Sign up at twitterapi.io and copy your key from the dashboard.
Step 2 — Add the MCP server to your AI client config
Pick your client below and replace YOUR_TWITTERAPI_KEY with your actual key.
Claude Desktop on Windows
Config file: %LOCALAPPDATA%\Packages\Claude_...\LocalCache\Roaming\Claude\claude_desktop_config.json
{
"mcpServers": {
"x-intelligence": {
"command": "cmd",
"args": [
"/c", "npx", "-y", "mcp-remote",
"https://mcp-x-intelligence.fluyeporlaweb.workers.dev/mcp",
"--header", "x-twitterapi-key: YOUR_TWITTERAPI_KEY"
]
}
}
}
Claude Desktop on Mac
Config file: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"x-intelligence": {
"command": "npx",
"args": [
"-y", "mcp-remote",
"https://mcp-x-intelligence.fluyeporlaweb.workers.dev/mcp",
"--header", "x-twitterapi-key: YOUR_TWITTERAPI_KEY"
]
}
}
}
Cursor / Windsurf / Cline
Same config as Mac above. Add it to your MCP settings JSON file.
Step 3 — Restart your AI client and verify
Ask your AI assistant:
"What tools do you have available?"
You should see the x-intelligence tools listed.
Tool Parameters Reference
search_viral_content
query string required Search keyword or phrase
min_likes number optional Minimum likes (default: 50)
min_retweets number optional Minimum retweets (default: 0)
hours_back number optional Hours back to search (default: 48)
limit number optional Max results (default: 20)
analyze_account
username string required X username without @
tweets_limit number optional Tweets to analyze (default: 20)
get_trending_topics
woeid number optional Where On Earth ID (default: 1 = Worldwide)
23424977=USA · 23424950=Spain · 23424900=Mexico
23424747=Argentina · 23424791=Colombia
get_niche_leaders
keyword string required Niche or topic keyword
limit number optional Max accounts (default: 10)
Use Cases for X Research with AI
- Content creators — Find what's going viral in your niche before writing your next thread or post
- Marketers — Competitive account analysis and real-time trend monitoring at zero cost
- Developers — Build research pipelines and content strategy tools backed by live X data
- Researchers — Social media data collection without the official X API price tag
Example Prompts to Try
- "Search for viral posts about Claude MCP from the last 48 hours with over 100 likes"
- "Analyze the account @OpenAI — what are their top 5 posts and when do they usually post?"
- "What's trending in Mexico and Argentina right now?"
- "Find the top 10 accounts in the AI tools niche on X"
Why Not the Official X API?
The official X API uses pay-per-use credit pricing — no monthly minimums. However it still requires: a developer account approval process, OAuth 2.0 authentication setup, and custom integration work to connect with AI agents like Claude.
mcp-x-intelligence removes all that friction. One API key from twitterapi.io, one config block, done.
| Official X API | mcp-x-intelligence | |
|---|---|---|
| Pricing model | Pay-per-use credits (no minimum) | Free (BYOK) or $9/mo hosted |
| Setup time | Developer account approval required | Minutes |
| MCP native | No — requires custom integration | Yes — plug and play |
| Works with Claude | Manual integration | Native |
| Auth complexity | OAuth 2.0 setup required | Single API key |
Troubleshooting
"Tool execution failed" or RuntimeError
Make sure you are using v1.2.0 or later. Earlier versions had a schema compatibility issue affecting Hermes, Cursor and Windsurf users.
The hosted endpoint at MCPize is always up to date.
Tools not appearing in my AI client
- Check your config file has the correct JSON syntax
- Restart your AI client completely (not just the window)
- Verify your twitterapi.io key is valid at twitterapi.io/dashboard
Empty results
Some queries may return no results if:
- The keyword is too specific
- The time window (hours_back) is too short
- The engagement filter (min_likes) is too high
Try broadening your search parameters.
Rate limits
twitterapi.io enforces rate limits on free accounts. If you get errors after many requests, wait a few minutes and try again.
Built by
@fluyeporlaweb — AI tools, automation and developer resources in Spanish.
Join the community: t.me/fluyeporlaweb
Listed on Smithery
License
MIT — do whatever you want with it.
Comments
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.