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

Zero-Trust PII & secrets sanitizer for AI agents with in-memory local redaction.

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 npm.Free to use.
MCP server: One MCP server.
CodemoreRun by its publisher: served from their own domain, namespace checked by the registry.
@abhinavteja123 · External

The static analyzer your AI agent reads — fix-ready, machine-readable scan reports over 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.
MacfaxRun by its publisher: served from their own domain, namespace checked by the registry.
@macfax · External

Identify any Apple serial and read its device record, plus used-Mac prices, listings and checks.

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.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
FlagrixRun by its publisher: served from their own domain, namespace checked by the registry.
@flagrix-io · External

Scan GitHub repos and profiles for malware before cloning — commit-pinned risk verdicts for agents

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

Honeypot probe data: IP reputation, scanners, CVE probing, TLS and SSH fingerprints.

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.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
WhisperRun by its publisher: served from their own domain, namespace checked by the registry.
@whisper-sec · External

One routable IPv6 per AI agent, verifiable from the DNS root. Keyless tools need no signup.

12% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
MCP Gateway Scan
@willianpinho · External

Read-only MCP/agent-gateway readiness scanner — scores a repo across 7 security dimensions.

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 npm.Free to use.
MCP server: One MCP server.
SupraWall
@wiserautomation · External

SupraWall security gateway for AI agents. Provides deterministic guardrails for MCP agents.

9% 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.
Pseudonym
@woladi · External

Locally pseudonymizes sensitive text before cloud LLM work and restores the tokens afterward.

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 npm.Free to use.
MCP server: One MCP server.
VeriSwarmRun by its publisher: served from their own domain, namespace checked by the registry.
@veriswarm · External

VeriSwarm MCP Server — Trust infrastructure for AI agents via Model Context Protocol

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.
Dbridge
@ugurcl · External

Query SQLite, PostgreSQL, and MySQL in plain language - read-only, with column masking and limits.

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.
Zyrax Guard
@tiagosilva07 · External

Audit AI agent configs for prompt injection & rogue MCP servers; vet packages

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.
Raven Nest
@tidynest · External

AI-driven penetration testing - 22 security tools behind safety-hardened MCP endpoints

25% 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 Docker.Free to use.
MCP server: One MCP server.
Create StarterRun by its publisher: served from their own domain, namespace checked by the registry.
@starter-series · External

Scaffold Starter Series projects and check release, deployment, security, and agent instructions.

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.
X402station
@sf1nx · External

x402station.io: independent risk-signal layer for x402 endpoints before agents pay.

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.
Promptrejectormcp
@revsmoke · External

Security gateway for AI agents: detects prompt injections, jailbreaks, and common vulnerabilities.

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.
Presidio Hardened X402
@presidio-v · External

Pre-payment safety gate for x402 agents: PII screening, spend policy, replay checks before signing.

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.
DugganUSA CLI — Local STDIO MCPRun by its publisher: served from their own domain, namespace checked by the registry.
@pduggusa · External

Local STDIO MCP for DugganUSA threat intel. 1.13M IOCs. Read-only. npm: dugganusa-cli.

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.
Keycloak Admin
@mrz1880 · External

Administer Keycloak via its Admin REST API: users, roles, clients, groups, IdP, events.

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.
GTM GA4
@mharnett · External

GTM + GA4 MCP: tag management, consent auditing, workspace versioning, reports.

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.
Qorami
@loicfontaine-max · External

Check an email before an AI agent sends it: send / ask a human / block. Detects prompt injection.

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.
Inbox Check — Email Deliverability TestRun by its publisher: served from their own domain, namespace checked by the registry.
@live-direct-marketing · External

Email inbox placement tests across Gmail, Outlook, Yahoo, Mail.ru, Yandex (SPF/DKIM/DMARC).

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.
MCPAmpel - MCP Security Scanner
@diemoeve · External

Scan installed MCP servers for security vulnerabilities with 16 detection engines.

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.
Waxseal
@degenlegion-com · External

Ed25519 identity for AI agents. Verify seals, sign documents, gate actions with approvals.

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 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