Skip to main content

MCP Threads

PyPI version Python versions License: MIT GitHub stars GitHub issues GitHub last commit MCP

繁體中文

An open-source MCP (Model Context Protocol) server that wraps the Threads API into 6 AI-callable tools for social media content management.

Built for Claude Code, Claude Desktop, and any MCP-compatible AI client. Enables AI agents to read profiles, list posts/replies/mentions, check publishing limits, and publish text posts through natural language.

Disclaimer: This project requires a valid Threads account token. It is intended for personal use and internal tooling only.

What This Does

  • 6 ready-to-use tools covering profile, posts, replies, mentions, publishing limits, and text posting
  • MCP server (stdio JSON-RPC 2.0) — plug into Claude Code and start interacting with Threads immediately
  • Minimal dependencies — built on mcp SDK with no external API client libraries
  • Local stdio server — works with Claude Desktop, Claude Code, and any MCP-compatible host

Quick Start

Install

pip install mcp-threads

Or use uvx (no install needed):

uvx mcp-threads serve

Set your token:

export THREADS_TOKEN="<your-token>"

Use with Claude Code

Add the server via the Claude CLI:

claude mcp add --transport stdio threads -- mcp-threads serve

Or with the environment variable inline:

claude mcp add --transport stdio threads -e THREADS_TOKEN=your_token_here -- mcp-threads serve

If you clone the repo locally, the .mcp.json config will be auto-detected by Claude Code and all 6 tools become available immediately.

Use with Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "threads": {
      "command": "mcp-threads",
      "args": ["serve"],
      "env": {
        "THREADS_TOKEN": "your_token_here"
      }
    }
  }
}

Or with uvx:

{
  "mcpServers": {
    "threads": {
      "command": "uvx",
      "args": ["mcp-threads", "serve"],
      "env": {
        "THREADS_TOKEN": "your_token_here"
      }
    }
  }
}

Tools (6)

Tool Description
threads_profile_me Read the authenticated Threads user profile
threads_posts_list List posts created by the authenticated user
threads_publishing_limit Read publishing quota usage and config
threads_mentions_list List public Threads posts that mention the authenticated user
threads_replies_list List replies created by the authenticated user
threads_post_text Create and publish a text post or reply

License

MIT

Metadata

Release files for mcp-threads 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for mcp-threads 0.1.0
File Size Uploaded Provenance
mcp_threads-0.1.0.tar.gz 32.7 kB With provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for mcp-threads 0.1.0
File Interpreter ABI Platform
mcp_threads-0.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 43.0 kB

Release files / mcp_threads-0.1.0.tar.gz

Download URL mcp_threads-0.1.0.tar.gz
Size 32.7 kB
Tags Source
SHA-256 checksum
How to use checksums
dffdf302c4ab2d9a695c5552b759dda9a5aff8f7e7cde2413fbcde8eb8687080
BLAKE2b-256 checksum
How to use checksums
990e1f146a5f6e04639c60ab3865587c59f521b7896aef6e1a66c7992484b636
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.12

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Jun 4, 2026.

Transparency log

Release files / mcp_threads-0.1.0-py3-none-any.whl

Download URL mcp_threads-0.1.0-py3-none-any.whl
Size 10.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
57259cb34e718cfec646f49d2b0d5e5f228e49295b5101506a4026014367cce7
BLAKE2b-256 checksum
How to use checksums
859e7c7b8ee1c678018bdec816b63dc8e851f6f469f9c9f42e371f81a58a2adf
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.12

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Jun 4, 2026.

Transparency log

Security for mcp-threads 0.1.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

All 2 files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for mcp_threads-0.1.0.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Jun 4, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files Full provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page