OSINTSAFE
OSINT intelligence MCP server for AI agents — 37 tools, 12 sources. Shodan, VirusTotal, Censys, SecurityTrails, DNS reconnaissance, WHOIS, certificate transparency, BGP routing, Wayback Machine, GeoIP. Automated open source intelligence and attack surface mapping via Model Context Protocol.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
English | 简体中文 | 繁體中文 | 한국어 | Deutsch | Español | Français | Italiano | Dansk | 日本語 | Polski | Русский | Bosanski | العربية | Norsk | Português (Brasil) | ไทย | Türkçe | Українська | বাংলা | Ελληνικά | Tiếng Việt | हिन्दी
OSINT & reconnaissance intelligence for AI agents.
Shodan, VirusTotal, Censys, SecurityTrails, DNS, WHOIS, BGP, Wayback Machine — unified into a single MCP server. Your AI agent gets full-spectrum OSINT on demand, not 12 browser tabs and manual correlation.
The Problem • How It's Different • Quick Start • What The AI Can Do •
e4d1c343704dOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add osint-mcp-server --env CENSYS_API_SECRET=${CENSYS_API_SECRET} --env SHODAN_API_KEY=${SHODAN_API_KEY} --env ST_API_KEY=${ST_API_KEY} --env VT_API_KEY=${VT_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"osint-mcp-server": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"CENSYS_API_SECRET": "${CENSYS_API_SECRET}",
"SHODAN_API_KEY": "${SHODAN_API_KEY}",
"ST_API_KEY": "${ST_API_KEY}",
"VT_API_KEY": "${VT_API_KEY}"
}
}
}
}Exposed tools (37)
36 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
bgp_asn | read | Look up ASN details and announced IPv4/IPv6 prefixes via BGPView. Returns ASN name, description, contacts, and all announced prefixes. |
bgp_ip | read | Look up BGP routing information for an IP address. Returns matching prefixes, ASNs, and RIR allocation. |
bgp_prefix | read | Look up details for a specific IP prefix/CIDR. Returns announcing ASNs, name, country, and RIR. |
censys_certificates | read | Search Censys certificate database. Returns certificate fingerprints, subjects, issuers, validity, and SANs. Requires CENSYS_API_ID + CENSYS_API_SECRET. |
censys_host_details | read | Get detailed Censys host information for a single IP: all services, certificates, OS, location, ASN. Requires CENSYS_API_ID + CENSYS_API_SECRET. |
censys_hosts | read | Search Censys for hosts matching a query. Returns IPs, services, ports, location, ASN. Requires CENSYS_API_ID + CENSYS_API_SECRET. |
crtsh_search | read | Search Certificate Transparency logs via crt.sh. Returns unique subdomains and certificate details (issuer, validity, SANs). |
dns_email_security | read | Analyze email security posture: SPF, DMARC, DKIM records with risk assessment and recommendations. Checks common DKIM selectors (google, selector1, selector2, k1, etc.). |
dns_lookup | read | Resolve DNS records for a domain. Supports A, AAAA, MX, TXT, NS, SOA, CNAME, SRV record types. |
dns_reverse | read | Perform reverse DNS (PTR) lookup for an IP address. Returns associated hostnames. |
dns_spf_chain | read | Recursively resolve SPF include chain. Shows all included domains, IP ranges, detected services (Google Workspace, Microsoft 365, SendGrid, etc.), and RFC 7208 lookup limit compliance. |
dns_srv_discover | read | Discover SRV records and common service CNAMEs for a domain. Probes for SIP, XMPP, Autodiscover, LDAP, Kerberos, CalDAV, CardDAV, and checks CNAMEs for autodiscover, lyncdiscover, OWA, ADFS, etc. |
dns_wildcard_check | read | Check if a domain has wildcard DNS configured by resolving a random subdomain. |
geoip_batch | read | Batch geolocate up to 100 IP addresses at once. Uses ip-api.com (free, no API key). |
geoip_lookup | read | Geolocate an IP address: country, city, ISP, ASN, proxy/hosting/mobile detection. Uses ip-api.com (free, no API key). |
hackertarget_aslookup | read | Look up ASN information for an IP or ASN via HackerTarget. Free tier: 50 queries/day. |
hackertarget_hostsearch | read | Find subdomains and their IPs for a domain via HackerTarget. Free tier: 50 queries/day. |
hackertarget_reverseip | read | Reverse IP lookup via HackerTarget — find all domains hosted on an IP. Free tier: 50 queries/day. |
m365_tenant | read | Discover Microsoft 365 tenant information for a domain. Returns tenant ID, region, and OpenID configuration endpoints. |
m365_userrealm | read | Detect authentication type for a domain |
osint_domain_recon | read | Quick domain reconnaissance combining free sources: DNS (A/MX/NS/TXT), WHOIS, crt.sh subdomains, HackerTarget hosts, and email security analysis. No API keys required. |
osint_list_sources | read | List all OSINT data sources, their availability, API key requirements, and tool counts. Use this to check which sources are configured. |
shodan_dns_resolve | read | Resolve hostnames to IPs using Shodan |
shodan_exploits | read | Search Shodan |
shodan_host | read | Get Shodan host details for an IP: open ports, services, banners, vulns, OS, ASN, geolocation. Requires SHODAN_API_KEY. |
shodan_search | read | Search Shodan for hosts matching a query (e.g. |
st_dns_history | read | Get historical DNS records for a domain via SecurityTrails. Shows first/last seen dates, values, and organizations. Requires ST_API_KEY. |
st_subdomains | read | Enumerate subdomains for a domain via SecurityTrails. Returns FQDNs. Requires ST_API_KEY. |
st_whois | read | Enhanced WHOIS lookup via SecurityTrails with registrant/admin/technical contacts. Requires ST_API_KEY. |
vt_domain | read | VirusTotal domain analysis: reputation score, detection stats, categories, registrar, DNS records. Requires VT_API_KEY. |
vt_ip | read | VirusTotal IP analysis: reputation, detection stats, country, ASN, network. Requires VT_API_KEY. |
vt_subdomains | read | Enumerate subdomains for a domain via VirusTotal. Requires VT_API_KEY. |
vt_url | write | Submit a URL to VirusTotal for scanning and get analysis results (malicious/suspicious/harmless). Requires VT_API_KEY. |
wayback_snapshots | read | Get Wayback Machine snapshot history for a specific URL. Returns timestamps, status codes, and direct archive links. Shows first/last seen dates. |
wayback_urls | read | Search Wayback Machine for archived URLs of a domain. Returns unique URLs with timestamps, status codes, and MIME types. Useful for finding old endpoints, hidden paths, and removed content. |
whois_domain | read | RDAP/WHOIS lookup for a domain. Returns registrar, registration/expiration dates, nameservers, and contact entities. |
whois_ip | read | RDAP/WHOIS lookup for an IP address. Returns network name, CIDR range, country, and responsible entities. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
@modelcontextprotocol/sdk, zod, @types/bun, @types/node, typescript
- Read it from `process.env` in `src/index.ts` → `buildToolContext()`
Gates applied: no_behavioural_pass.
e4d1c343704dfull audit observations/trust-audit/mcp-server/badchars__osint-2.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | e4d1c343704d | SAFE | B | 89 | first audit |
Questions
What is the OSINT MCP server?
OSINT intelligence MCP server for AI agents — 37 tools, 12 sources. Shodan, VirusTotal, Censys, SecurityTrails, DNS reconnaissance, WHOIS, certificate transparency, BGP routing, Wayback Machine, GeoIP. Automated open source intelligence and attack surface mapping via Model Context Protocol.
What tools does OSINT expose?
37 in total: 36 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is OSINT safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does OSINT need?
It reads CENSYS_API_SECRET, SHODAN_API_KEY, ST_API_KEY and VT_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does OSINT run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as osint-mcp-server at 0.2.0.
How current is this page?
The grade is for one exact copy of the source (e4d1c343704d), read on 2026-10-08. The repository is watched and re-audited when it changes.