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.
Vulnicheck
@andrasfe · External

HTTP MCP Server for comprehensive Python vulnerability scanning and security analysis.

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 Docker.Free to use.
MCP server: One MCP server.
SchemaBrainRun by its publisher: served from their own domain, namespace checked by the registry.
@arun-kc · External

The trust and intelligence layer between AI agents and your database.

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 PyPI.Free to use.
MCP server: One MCP server.
EU AI Act
@ark-forge · External

EU AI Act + GDPR compliance scanner. One call, no arguments, 10 seconds. 22 AI frameworks detected.

14% 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.
x402checkRun by its publisher: served from their own domain, namespace checked by the registry.
@caiovicentino · External

Risk-check counterparties before an AI agent pays; pay x402 resources only after a verified allow

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.
Klarion
@0x1adi · External

Secret scanning for AI agents: rules and entropy find candidates, a model decides which are real.

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 MCPB.Free to use.
MCP server: One MCP server.
GigaMail
@adecubed · External

Your real mailbox and calendar for your agent (M365/IMAP); a human approves every send.

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 PyPI.Free to use.
MCP server: One MCP server.
VulnCheck
@vulncheck-oss · External

VulnCheck exploit intelligence — CVE research, exploit data, advisories, and threat analysis.

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

Vet a package (CVEs, license, maintenance) before your AI agent uses it, plus capability discovery.

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.
HackTricks MCP Server
@xplo8e · External

Search and query HackTricks pentesting documentation with quick lookup and section extraction

14% 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.
DadosBRRepublished by Smithery for its author.
@smithery · External · via Smithery

# MCP DadosBR Servidor MCP focado em dados públicos do Brasil. Oferece duas ferramentas simples e…

12% 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; it needs your API key.Free to use.
MCP server: One MCP server.
SanctuaryRun by its publisher: served from their own domain, namespace checked by the registry.
@sanctuaryprotocol · External

Open-source MCP server: encrypted local keys and state, operator approval gates, a hash-chained 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.
skgate
@helv-io · External

OAuth MCP gateway. SI proxy with model aliases. Grok subscription as OpenAI-compatible API, no key.

Not assessed yet.What it can do is not assessed yet.Runs on your machine, installed from Docker.Free to use.
MCP server: One MCP server.
GreenLake usersRun by its publisher: served from their own domain, namespace checked by the registry.
@hewlettpackard · External

HPE GreenLake users MCP Server

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 PyPI.Free to use.
MCP server: One MCP server.
PerspectiveGraph
@luiacuaniello · External

Read-only attack-path tools: reachable routes to sensitive assets, and what a fix would cut.

12% 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.
TrentRun by its publisher: served from their own domain, namespace checked by the registry.
@trent · External

Security reviews, threat models over a repo or website, and remediation tracking, in your editor.

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.A remote server; you sign in with your account.Free to use.
MCP server: One MCP server.
AMH Cloudflare Ops MCP by WT
@pain2hustle · External

The bridge from K2 agents through Wrangler to your master AI - safe, approval-gated Cloudflare ops.

21% 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; it needs your API key.Free to use.
MCP server: One MCP server.
ClearfrontRun by its publisher: served from their own domain, namespace checked by the registry.
@clearfront · External

OSINT sweep of a digital footprint: breaches, accounts, data brokers, domains and IPs

17% 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.
Bug Bounty Intelligence
@holistis · External

AI security scanner for Solidity + free CC0 dataset of Sherlock audit-competition acceptance rates.

12% 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.The endpoint has not answered since 9 Oct.Free to use.
MCP server: One MCP server.
Lightning Memory
@singularityjason · External

Decentralized agent memory for the Lightning economy. Nostr identity, L402 payments.

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 PyPI.Free to use.
MCP server: One MCP server.
Redacta
@nickjlamb · External

Keep patient identifiers out of AI agent context — a local privacy boundary for healthcare agents.

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.
IrisRun by its publisher: served from their own domain, namespace checked by the registry.
@iris-eval · External

Stop shipping agents on vibes. Score every agent output for quality, safety, and cost.

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

Deterministic tech stack recommendations, audits, and project estimates. No hallucinations.

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.
Canvas LMS
@bruchris · External

TypeScript MCP server for Canvas LMS — 172 tools across 42 domains.

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

Cross-agent memory over MCP: hybrid recall, knowledge graph, private/shared visibility, redaction.

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.

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