Odel

Security & privacy

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

2,418 servers1,785 publishers8 tags

All of Security & privacy

By GitHub stars, at most two per publisherRemoteLocal
MCP server: One MCP server.
Storefront Guard
@maxigirl123 · External

Verifies a merchant storefront is legitimate before an AI agent commits payment.

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.
Israel Business Intelligence MCP
@itzikhr18 · External

Israeli invoice PAY/HOLD/BLOCK gate; cheapest paid path company-changes $0.01 USDC.

13% 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.
PHI Guard
@abidit · External

Local-first PHI detection for source code, LLM prompts, logs, and analytics

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.
AgentPay — Pay-per-call AI MicroservicesRun by its publisher: served from their own domain, namespace checked by the registry.
@agentpay · External

34 pay-per-call AI microservices via x402, USDC on Base, no API keys.

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.A remote server; no sign-in.The repository cannot be reached since 8 Oct.Free to use.
MCP server: One MCP server.
SAT69 — Listas del SAT (69 y 69-B del CFF)
@edbror · External

Verifica RFCs contra las listas del SAT (69/69-B CFF, EFOS): veredicto de riesgo fiscal.

18% 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 7 Oct.Free to use.
MCP server: One MCP server.
Agentrisk
@neurobyteio · External

Pre-trade token risk scoring API for Base tokens, paid via x402.

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.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
secureFlows
@michal-lefler · External

MCP server for secureFlows (secure-flows.com). Alias of io.github.michal-lefler/secureflows-mcp.

9% 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.
secureFlows
@michal-lefler · External

MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.

11% 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.
Passiv Web Tools
@mahope · External

Free web tools for AI agents: HTML to Markdown, compliance scan, page profile, security headers.

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 a package registry.Free to use.
MCP server: One MCP server.
skanfirmy.pl
@bartosz-kuc · External

Verify Polish companies by NIP/KRS/REGON + EU VAT (VIES). 14 MCP tools (9 no-key).

6% 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.
Deliverability Doctor
@integrity-os · External

Check if a domain can be email-spoofed: SPF, DMARC, DKIM, MX graded from public DNS. Authless.

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.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Ox402 Utils
@hasned-spec · External

47 micro-priced utilities: search, screenshots, OCR, whois, prices, video downloads. x402 USDC.

39% 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.
Blackwall X402 GuardrailRun by its publisher: served from their own domain, namespace checked by the registry.
@blackwalltier · External

Keyless hosted MCP: pre-signature x402 payment verdict (GO/HOLD/STOP) with a signed receipt.

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.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
ERC-8126 Scan
@cybercentry · External

378k+ ERC-8004 agents and their security verifications. Two tools free, the rest USDC over x402.

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

XFA's remote MCP server — query device posture, compliance, policies & CVEs. Read-only.

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.A remote server; you sign in with your account.Free to use.
MCP server: One MCP server.
traqlRun by its publisher: served from their own domain, namespace checked by the registry.
@traql · External

AML risk scoring for crypto addresses and transactions on Ethereum, BSC, TRON, TON, Bitcoin

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.
Nel VeilRun by its publisher: served from their own domain, namespace checked by the registry.
@nelproinc · External

Free passive security scanning - check any domain's DMARC, TLS, headers, and exposures.

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.
Cleared IndexRun by its publisher: served from their own domain, namespace checked by the registry.
@clearedindex · External

Cleared Check before pay: lookup_merchant, cleared_check, route_gateway for x402 agents.

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

Document fraud detection for manipulated, fake and AI-generated PDF and image documents.

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.A remote server; you sign in with your account.Free to use.
MCP server: One MCP server.
entraadm MCP
@shigechika · External

MCP server for Microsoft Entra ID sign-in and audit-log triage (read-only)

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.
MCP x402 - Evidence-Backed Web Verification
@diogoup26 · External

Evidence-backed x402 web verification for AI agents, with auditable decisions for every condition.

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.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Compliance & Sanções
@mcp-dir · External

Due diligence & KYC: PEP, national and international sanctions (OFAC, UN, EU, UK, FBI, INTERPOL, FIN

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

HTTP MCP gateway: principal on tools/call + SSE, allowlists, vault rotate, CHP gates.

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.
Auditra
@mwstech · External

Read-only MCP server for WordPress plugin audits: vulnerabilities, bloat, cron, orphaned tables.

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 a package registry.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