Odel

Security & privacy

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

2,424 servers1,791 publishers8 tags

All of Security & privacy

By GitHub stars, at most two per publisherRemoteLocal
MCP server: One MCP server.
HEIDES
@abduljabbarbxr · External

Deterministic code analysis harness giving AI agents senses, memory and judgment for code.

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 MCPB.Free to use.
MCP server: One MCP server.
Redact PdfRun by its publisher: served from their own domain, namespace checked by the registry.
@dambuchs · External

Permanently redact PII from PDFs and scans. EU/Swiss-hosted, never used to train AI models.

4% 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.
Enterprise Gateway
@benjaminj · External

Production-grade MCP Gateway in Go with RBAC, in-flight PII redaction, and audit logging.

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 a package registry.Free to use.
MCP server: One MCP server.
site-specRun by its publisher: served from their own domain, namespace checked by the registry.
@ariaxhan · External

MCP server: audit any website for SEO, accessibility, and AI-searchability, then auto-fix it.

4% 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.
Sentinel ScanRun by its publisher: served from their own domain, namespace checked by the registry.
@ventrova · External

MCP security scanner: detect tool poisoning, prompt injection & rug-pulls - 10 OWASP heuristics.

7% 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.
Weavatrix OnlineRun by its publisher: served from their own domain, namespace checked by the registry.
@weavatrix · External

Weavatrix Online extension: guarded sync, advisories, malware review, architecture contracts.

8% 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.
Deadchannel
@plus8bit · External

Check an x402 endpoint before you pay it: verdict, risk score and what is wrong. $0.005 in USDC.

8% 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.
Keycloak
@dockndevai · External

Keycloak admin for AI agents — realms, users, clients, roles; safe-by-default governance.

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.
Timps SwarmRun by its publisher: served from their own domain, namespace checked by the registry.
@sandeeprdy1729 · External

161 AI agents for code gen, health, AI/ML, infra, India-stack. One command.

15% 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.
ItsocRun by its publisher: served from their own domain, namespace checked by the registry.
@ankit512 · External

Read-only MCP server over a local log-analysis backend; a client that computes no verdicts.

6% 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.
Opa Authz
@kanywst · External

Authorization answers from real policy code: evaluate Rego locally, or ask an AuthZEN 1.0 PDP.

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.
MCP server: One MCP server.
RealAgent MCP
@reddatetech · External

AI agent real-name identity: SM2 keypair, QR real-name link, SD-JWT VP generate/verify.

14% 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.
BeVigil OSINT
@santhosh-005 · External

Discover mobile app attack surfaces via BeVigil OSINT — hosts, subdomains, URLs, and more.

9% 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.
BagOS
@edycutjong · External

MCP server for Bags on Solana: token analytics, trade quotes, and gated write operations.

7% 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.
MCPSentinel
@gentaarnezzi · External

Precision-first security scanning for Model Context Protocol servers.

7% 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.
Safe Fetch
@sanoy24 · External

MCP server for fetching URLs, safe against SSRF, DNS rebinding, and redirect-to-internal attacks.

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 npm.Free to use.
MCP server: One MCP server.
Agentic Wallet Guardian V3
@rudimentall1 · External

Explainable ALLOW/WARN/BLOCK risk decisions for AI agent actions before execution, signed as OAA.

8% 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.
SkillguardRun by its publisher: served from their own domain, namespace checked by the registry.
@rudrendupaul · External

Security scanner for third-party AI agent-skill files (SKILL.md, hooks, scripts) via MCP.

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 PyPI.Free to use.
MCP server: One MCP server.
Taranis AI
@taranis-ai · External

Search stories and discover OSINT sources in Taranis AI.

7% 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.
Graph Atlas
@darrenjrobinson · External

Tracks documented and undocumented Microsoft Graph API schema changes, with an MCP Apps visualiser

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 npm.Free to use.
MCP server: One MCP server.
lockvet
@matteo-sung · External

Explain any lockfile or workflow-pin change: bumps, vulns, ages, deprecations — 61 formats

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.
Har Forensics
@aryanspv · External

Tells you what leaked in a .har capture, who's on the page, and what to strip. No network calls.

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.
AgentEnvelopeRun by its publisher: served from their own domain, namespace checked by the registry.
@blackboxengineering · External

Neutral MCP server for AgentEnvelope authority: sovereign verify + vault verify/lookup/mint.

6% 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.
FriskRun by its publisher: served from their own domain, namespace checked by the registry.
@tryfrisk · External

Screen the counterparty of an x402 payment before an agent pays it. Runs offline by default.

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 npm.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