A locally run connector that lets coding agents use the X (formerly Twitter) API through 41 typed tools, with access controlled by policies. It requires authentication and configuration through environment variables.

Use it to let an agent work with X data and actions through the API, subject to your authentication, policy, media, profile, timeout, logging, and budget settings.

It puts X API access in one agent-ready interface and lets you restrict which actions are allowed. Running locally keeps the connector on your machine.

x-mcp-ai — MCP server for Claude Code and Codex by IvanBBaev

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/IvanBBaev/x-mcp

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/mcp/ivanbbaev/x-mcp/x-mcp-ai.svg)](https://agentmods.dev/mcp/ivanbbaev/x-mcp/x-mcp-ai)

Your own site

<a href="https://agentmods.dev/mcp/ivanbbaev/x-mcp/x-mcp-ai"><img src="https://agentmods.dev/badge/mcp/ivanbbaev/x-mcp/x-mcp-ai.svg" alt="Measured on agentmods" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

x-mcp-ai scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

server.json · 29 lines

What it actually says

{
  "x-mcp-ai": {
    "command": "npx",
    "args": [
      "-y",
      "x-mcp-ai"
    ],
    "env": {
      "X_MCP_AUTH_MODE": "",
      "X_MCP_CLIENT_ID": "",
      "X_MCP_CLIENT_SECRET": "",
      "X_MCP_BEARER_TOKEN": "",
      "X_MCP_TOKEN_FILE": "",
      "X_MCP_TOKEN_KEYCHAIN": "",
      "X_MCP_POLICY": "",
      "X_MCP_POLICY_ALLOW": "",
      "X_MCP_POLICY_DENY": "",
      "X_MCP_HIDE_DENIED": "",
      "X_MCP_MEDIA_DIR": "",
      "X_MCP_AVAILABILITY": "",
      "X_MCP_PROFILES_FILE": "",
      "X_MCP_PROFILE": "",
      "X_MCP_TIMEOUT_MS": "",
      "X_MCP_LOG_LEVEL": "",
      "X_MCP_CREDIT_BUDGET": "",
      "X_MCP_BUDGET_MODE": ""
    }
  }
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

6d ago First seen · 29 lines scan A 54f9a99b65c3

Subscribe to this mod's changes

x-mcp-ai is an MCP server published in the GitHub repository IvanBBaev/x-mcp (0 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Backend and APIs mcp mcp-server nodejs oauth2 twitter

cds-mcp

Model Context Protocol (MCP) server for AI-assisted development of CAP applications. Runs locally from the @cap-js/mcp-server npm package.

cap-js/mcp-server · not measured

mcp-server

Model Context Protocol (MCP) server for AI-assisted development of CAP applications. Runs locally from the @cap-js/mcp-server npm package.

cap-js/mcp-server · not measured

getmcpauth

Drop-in OAuth 2.1 + Dynamic Client Registration token verification for Python MCP servers, backed by mcpauth. Runs locally from the getmcpauth Python package.

yilmazali325/getmcpauth-python · not measured

http-mcp

MCP server "http-mcp" as configured in cUDGk/http-mcp. Runs locally from the http-mcp npm package.

cUDGk/http-mcp · not measured

salesforce-mcp-server

Comprehensive Salesforce MCP Server with 61+ specialized tools for complete Salesforce ecosystem management - from data operations to advanced DevOps workflows. Supports stdio + HTTP modes for AI assistants and orchestration platforms. Runs locally from the @kirtijha/salesforce-mcp-server npm package.

KirtiJha/salesforce-mcp-server · not measured

gsheets

Model Context Protocol (MCP) server for Google Sheets API integration. Runs locally from the mcp-gsheets npm package.

freema/mcp-gsheets · not measured