X Search One
Optional integration for caching or logging query metadata.
Click on "Install 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., "@X Search Onesearch for tweets about climate change"
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.
X Search One
Public product hub for the X Search MCP server: install, tools, security model, and an assistant that explains agent integrations.
Live: https://x-search-one.pages.dev
Public, no-account portfolio product in the same family as trip-one: grounded AI chat, light/dark UI, Cloudflare Pages, secrets server-side.
What it does
Tool catalog — Documented MCP tools with inputs/outputs.
Security model — Token handling, rate limits, least privilege.
Install paths — pip, Docker, Railway — copy-paste ready.
Agent chat — Ask how to wire search into an agent; answers cite the tool list.
HTTP bridge — Call the same capabilities outside MCP clients.
Portfolio-grade docs — Architecture diagram narrative recruiters skim in 60s.
Related MCP server: Twitter MCP
Integrations
Model Context Protocol — Tools for Claude, Cursor, and custom agents
X API v2 — Bearer-authenticated search & user lookup
Railway / Docker — Deploy the Python server anywhere
Supabase optional — Cache or log query metadata
Engineering signals (for recruiters)
AI tooling: MCP server design for external data
API engineering: auth, rate limits, structured tools
Python packaging + deploy (Docker/Railway)
Developer experience: docs site + examples
Quick wins
Interactive try-search playground with demo mode
OpenAPI snippet generation
Per-tool latency metrics panel
Claude Desktop config generator
Stack
Vite + React 18 + TypeScript (strict)
React Router
Cloudflare Pages + Functions (
/api/chat,/api/health)OpenAI
gpt-4o-mini(optional; UI works without it)
Develop
npm install
npm run devCopy .env.example to .dev.vars for Functions:
OPENAI_API_KEY=
AI_MODEL=gpt-4o-miniDeploy
npm run build
npx wrangler pages deploy dist --project-name x-search-one --branch mainSet OPENAI_API_KEY on the Pages project for live chat.
git push updates GitHub only — deploy is a separate step.
Privacy
No accounts. Chat sends the on-page context + your message to /api/chat when AI is configured. No ads, no tracking pixels.
License
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/brianference/x-search-one'
If you have feedback or need assistance with the MCP directory API, please join our Discord server