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.
Declaw AI MCPRun by its publisher: served from their own domain, namespace checked by the registry.
@declaw-ai · External

Secure Firecracker microVM sandboxes for AI agents: network policy, PII & injection guardrails.

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.
Pwntools
@daedalus · External

MCP server exposing pwntools 4.15.0 functionality for binary exploitation

19% 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.
Pymetasploit3
@daedalus · External

MCP server for Metasploit Framework via pymetasploit3

40% 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.
Solrisk
@comil27 · External

RETIRED - this server is discontinued and its backend is offline. Do not use.

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 a package registry.Free to use.
MCP server: One MCP server.
Attest
@chudah1 · External

Credential enforcement middleware for MCP servers — verifies scoped tokens on every tool call

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

Security gateway for MCP agents: blocks prompt-injection-driven tool calls before they execute.

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.
BitatlasRun by its publisher: served from their own domain, namespace checked by the registry.
@bitatlas-group · External

Zero-knowledge encrypted storage for humans and AI agents. Client-side AES-256-GCM, EU-hosted.

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.
MCP server: One MCP server.
Trust
@agntor · External

Trust layer for AI agents: identity, guard, redact, escrow, and x402 payments.

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.
Agentscore
@thezenmonster · External

MCP security trust layer: scan packages, inspect repos, check exposure, monitor changes.

8% 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.
x402 Triage MCPRun by its publisher: served from their own domain, namespace checked by the registry.
@tatelyman · External

MCP server for no-payment x402 surface triage, 402 Index health checks, and paid review handoff.

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.
Agentpay Sentinel
@rumblingb · External

Security guardrails for AI agent payments

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 a package registry.Free to use.
MCP server: One MCP server.
FormaCVRun by its publisher: served from their own domain, namespace checked by the registry.
@rocketech-software-development · External

FormaCV MCP server for AI-powered CV formatting, anonymization, tailoring, and ATS push-back.

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.
LGPD
@lordmendes · External

MCP Server para conformidade LGPD. Ferramentas de bases legais, consentimento, PIA e políticas.

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.
Chain SignerRun by its publisher: served from their own domain, namespace checked by the registry.
@kevthetech143 · External

Security suite for AI agents: flag drains, permit-phishing & risky actions before signing.

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 PyPI.Free to use.
MCP server: One MCP server.
KYT Screen by InfinihashRun by its publisher: served from their own domain, namespace checked by the registry.
@infinihash · External

Screen crypto wallets vs OFAC SDN + threat intel; pre-payment checks, signed receipts; SAR drafts

8% 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; you sign in with your account.Free to use.
MCP server: One MCP server.
Hookwarden — Webhook IntegrityRun by its publisher: served from their own domain, namespace checked by the registry.
@hookwarden · External

Webhook signature-verification audit. Stripe, GitHub, Shopify, Twilio +23. Local. Deterministic.

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.
Guardrails
@expertvagabond · External

AI Agent Guardrails MCP server - security layer

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.
Dep Diff
@digicatalyst-systems · External

Translates a lockfile diff into a human-readable upgrade plan for npm, PyPI, and GitHub Actions.

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

Email deliverability for AI agents. 12 tools: verify, DNSBL, DMARC, spam-trap, finder.

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.
Ariel MemoryRun by its publisher: served from their own domain, namespace checked by the registry.
@cipher208 · External

Two-layer memory MCP server for AI agents with 37 tools, RAG, graphs, wiki, auth

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.
COPPA FERPARun by its publisher: served from their own domain, namespace checked by the registry.
@csoai-org · External

Children's privacy compliance: COPPA (US), FERPA (US edu), EU AI Act children's provisions, UK A...

10% 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.
Agentradar
@bichev · External

Trust scoring, scam detection, and EAS attestations for ERC-8004 + x402 agents on Base.

12% 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.
VibeScan
@aguantar · External

MCP server for VibeScan — scan projects for leaked secrets and security issues

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.
Pentagonal
@achilles1089 · External

AI smart contract forge — 8-agent security audits, generation, and compilation across 8 chains

11% 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.

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