Osint MCP Server

OSINT MCP server — 23 tools: DNS, WHOIS, Shodan, breaches, GEOINT, crypto. Works with Claude Code. That is what the osint mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

It is a structured knowledge base — a curated set of methodologies, tool registries, pivot playbooks, ethics rules, and report templates — that any autonomous AI agent can consume to instantly adopt the operating discipline of a senior open-source intelligence analyst.

The tools it exposes

The server publishes 14 tools. What each one is for:

• Anti — hallucination rules.** Explicit prohibitions on fabricating identifiers, tool output, dates, or confidence levels
• Agent — Guide
• Cursor — integrations/cursor.md
• OpenCode — integrations/opencode.md
• AutoClaw — integrations/autoclaw.md
• Playbook — Trigger
• email-to-username.md — You found an email address
• username-to-identity.md — You found a username
• domain-to-infrastructure.md — You found a domain
• ip-to-attribution.md — You found an IP address
• breach-to-credentials.md — You confirmed an email is in a breach
• phone-to-person.md — You found a phone number

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

How it compares

Among the team communication options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Osint's toolset — Anti, Agent, Cursor and 11 more — is a fair guide to whether it matches your workflow. It is maintained by frangelbarrera; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Osint's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Things to watch

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Osint.
• Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.