soxoj/awesome-osint-mcp-servers

🔌 A curated list of OSINT MCP servers. Pull requests are welcomed!

What it solves

Open-source intelligence (OSINT) work involves many scattered tools and data sources. This list makes it easier to find ready-made MCP servers that connect those tools to AI assistants like Claude, Cursor, or Windsurf, so investigators can query social media, network infrastructure, company records, and other public data using plain language.

How it works

The project is a curated, categorized index. Each entry links to an MCP server, notes whether it's open source, free, or paid, and gives a one-line description of what it does. Servers are grouped by use case: social media intelligence (SOCMINT), network scanning, web scraping, company intelligence, public records, threat intelligence, geospatial, research, discovery, blockchain, and market data. MCP (Model Context Protocol) is the standard that lets these servers expose their tools to LLM-based applications.

Who it's for

Investigators, researchers, security analysts, and developers who use AI assistants for OSINT and want a quick reference to pluggable MCP servers. It's also useful for anyone evaluating which MCP servers cover the intelligence sources they need.

Highlights

  • Dozens of categorized entries, each with licensing and pricing info.
  • Covers a wide range: social media, network recon, web scraping, company registries, sanctions, threat intel, and more.
  • Includes both open-source and hosted MCP servers, with free tiers or trials where available.
  • Each entry links directly to the server's page or repository, with an MCP endpoint where relevant.

Related

  • Project
    damonwan1/AutoScholarLoop

    AutoScholarLoop is an open‑source, multi‑agent research automation framework. It orchestrates a five‑stage loop (field mapping, idea generation, execution, writing, quality control) to turn a seed idea and references into a draft paper with full audit trails. It supports local deterministic demos or real LLMs via an OpenAI‑compatible provider, integrates Semantic Scholar/OpenAlex literature retrieval, and can generate ACM/IEEE/Springer/Chinese‑thesis manuscripts (optionally compiling PDFs). Both a CLI (`autoscholarloop run …`) and a Vue web console are provided. The project is licensed under a Responsible AI license that requires disclosure of AI assistance in any resulting publications.

  • Project
    Gennadiyev/STS2MCP

    A mod for Slay the Spire 2 that exposes game state and actions via a REST API and MCP server, enabling AI agents to fully automate gameplay.

  • Project
    0sec-labs/0

    0 is an open‑source, AI‑driven security‑workflow platform. Install a tiny binary, configure an LLM provider, then run pre‑built or custom security templates (code review, dependency scan, smart‑contract audit, etc.) via a browser UI, CLI, or remote MCP server. Results are stored locally with evidence and suggested fixes, and the system integrates with common dev‑ops tools (GitHub, CI, Slack, etc.). It’s a research‑preview tool licensed MIT/Apache‑2.0.

  • Project
    ARCANGEL0/Mitsu

    Mitsu is an agentic penetration-testing framework that automates authorized engagements from reconnaissance to post-exploitation, using an MCP server to connect a chosen LLM to 165+ red-team tools. It keeps persistent per-session intelligence and offers three modes (Recon, Guided, AutoPwn) to balance automation with operator control.