Odel

Security & privacy

Find vulnerabilities, track threats, check identities and catch fraud.

2,418 servers1,785 publishers8 tags

Most popular in Security & privacy

By GitHub stars, at most two per publisher
  1. Number 1: Nhost@nhost/mcpLet your users work with their own data through an AI assistant, limited to what they can see.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.9,350 GitHub stars.
  2. Number 2: Robin: AI-Powered Dark Web OSINT@apurvsinghgautam/robinDark web OSINT over Tor: search onion engines, scrape pages, report with your own model.12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.7,493 GitHub stars.
  3. Number 3: Jshookmcp@vmoranv/jshookmcpSearch-first MCP server for JavaScript reverse engineering: 735 tools across 36 domains.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2,035 GitHub stars.

Tags in Security & privacy

Fraud & scam detection739Penetration testing445Vulnerability management405Data privacy375Identity & access management325Threat intelligence302Email & DNS security214Identity verification181

All of Security & privacy

By GitHub stars, at most two per publisherRemoteLocal
MCP server: One MCP server.
OpenOSINTRun by its publisher: served from their own domain, namespace checked by the registry.
@openosint · External

AI-powered OSINT agent & MCP server. 21 tools: email, breach, IP, WHOIS, DNS, Shodan, GitHub & more.

11% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
CloudBaseRun by its publisher: served from their own domain, namespace checked by the registry.
@tencentcloudbase · External

CloudBase MCP: DB, functions, storage, hosting via @cloudbase/cloudbase-mcp

4% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
SafeDep Vet MCP
@safedep · External

Protect your AI agents and IDEs from malicious open-source packages.

3% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.Free to use.
MCP server: One MCP server.
UniFi Access MCP
@sirkirby · External

Manage UniFi Access doors, credentials, policies, visitors, and events via MCP.

7% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Package unifi-access-mcp was yanked by its publisher.Free to use.
MCP server: One MCP server.
SkylosRun by its publisher: served from their own domain, namespace checked by the registry.
@duriantaco · External

Dead code, security, secrets detection and code quality for Python, TypeScript, Go.

5% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
SSH — policy-gated remote access
@tufantunc · External

Policy-gated, audited SSH for Linux and Windows hosts: roles, approvals, and an audit log.

5% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
HOL GuardRun by its publisher: served from their own domain, namespace checked by the registry.
@hashgraph-online · External

Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.

5% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
Emilia ProtocolRun by its publisher: served from their own domain, namespace checked by the registry.
@emiliaprotocol · External

Exact-action approval for consequential agent actions: request, track, and verify signed receipts.

5% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
SSH Manager
@bvisible · External

SSH server management for agents, with per-server read-only and allowlist security modes

5% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
walkerOS FlowRun by its publisher: served from their own domain, namespace checked by the registry.
@walkeros · External

Build, validate, simulate, and deploy walkerOS event pipelines

4% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
VeritasGraphRun by its publisher: served from their own domain, namespace checked by the registry.
@bibinprathap · External

Zero-trust, air-gapped Enterprise GraphRAG MCP server with offline, citation-grounded answers.

5% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
DashClaw
@ucsandman · External

Policy checks, approvals, records, and governed HTTP capabilities for unattended agents.

6% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Wireshark
@bx33661 · External

Professional network analysis with tshark. Security audits, deep-dives, and threat detection.

5% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 known advisories (OSV) in its package.Free to use.
MCP server: One MCP server.
Canvas
@vishalsachdev · External

Canvas LMS integration for students and educators with optional privacy controls

5% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
Caf
@codespar · External

DEPRECATED: no live endpoint (api.caf.io does not resolve)

4% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Deprecated by the publisher: No live endpoint: api.caf.io does not resolve. See https://github.com/codespar/mcp-dev-latam/tree/main/packages/identity/cafFree to use.
MCP server: One MCP server.
BigDataCorp
@codespar · External

MCP server for BigDataCorp — Brazilian data enrichment + KYC (CPF/CNPJ/vehicle/property/antifraud)

6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
CrowdStrike Falcon MCP Server
@crowdstrike · External

Connects AI agents with CrowdStrike Falcon for security analysis and automation.

3% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
SuperlocalmemoryRun by its publisher: served from their own domain, namespace checked by the registry.
@varun369 · External

Local-first AI memory with knowledge graphs and hybrid search. 17+ AI tools via MCP. Free.

5% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
node9
@node9-ai · External

Access control for AI agents and MCP servers: allow, hold for approval, or block each tool call

Not assessed yet.What it can do is not assessed yet.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Crowdsentinel
@thomasxm · External

AI threat hunting & incident response for Elasticsearch/OpenSearch with endpoint & network forensics

6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
Parse-DMARC MCP Server
@meysam81 · External

Lightweight DMARC parser: auto-fetch email reports, visualize compliance in a single all-in-one app

4% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.Free to use.

More topics

Sales & customersMarketing & advertisingShopping & e-commerceBusiness financePersonal finance & investingLegal & governmentSoftware developmentAI & agentsCloud & IT operationsData & webWork & productivityCommunicationDocuments & writingDesign & mediaNews & informationScience & researchHealth & fitnessEducation & careersTravel & placesHome & propertyEntertainment & hobbiesIndustry & transport