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.
Proctor
@louissarvin · External

Human oversight for AI agents: block a tool call on a verified human, with on-chain proof.

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 npm.Free to use.
MCP server: One MCP server.
Verify China Supplier | Supplier Check
@lu7897859-tech · External

Verify a Chinese supplier before you pay: company identity, status, risk signals. x402 per call.

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.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Abnormal MCP Server
@gregdog · External

Abnormal Security MCP: threats, search, remediation, ATO cases, vendor/BEC, and evidence download.

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 Docker.Free to use.
MCP server: One MCP server.
ScanScam Integrity
@gabothefounder · External

Independent agent preflight: verify change, mandates, evidence, and exact execution.

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

One API, all things verified — control, delegation, human approval, anti-impersonation.

7% 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; it needs your API key.Free to use.
MCP server: One MCP server.
AmlRun by its publisher: served from their own domain, namespace checked by the registry.
@oceanalt · External

Screen a payee address before an AI agent pays: sanctions, mixers, scam lists, on-chain risk.

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.Free to use.
MCP server: One MCP server.
SendCheck — EVM address verification (x402)Run by its publisher: served from their own domain, namespace checked by the registry.
@pennyforge · External

Pre-send EVM address checks: free pre-check, $0.01 check, $0.05 deep scan. x402: payment is auth.

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

Verify an npm package before install: advisories, install scripts, typosquats, declared repository.

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.
Alphapipeline
@parkyucheol-del · External

Pay-per-call x402 API for AI trading agents: pre-trade security checks, Polymarket & HIP-4 odds.

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; no sign-in.Free to use.
MCP server: One MCP server.
NumberBroom
@cameron-creations · External

Verify US phone numbers: line type, carrier, and TCPA litigator status via the NumberBroom API.

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.A remote server; you sign in with your account.Free to use.
MCP server: One MCP server.
Company filing and CVE evidence snapshots
@stavros65 · External

Company filing/CVE snapshots, status and optional feedback. Remote MCP or local stdio. Free Phase A.

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.The endpoint has not answered since 8 Oct.Free to use.
MCP server: One MCP server.
nittimRun by its publisher: served from their own domain, namespace checked by the registry.
@nittim · External

Production-safety audits for AI-generated code, with a fix for every finding.

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.
Token risk x402Run by its publisher: served from their own domain, namespace checked by the registry.
@ogenalabs · External

Pre-trade token safety checks for AI agents on Solana and Base. x402 USDC per call, no key.

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.
Intesta — trust registry lookupRun by its publisher: served from their own domain, namespace checked by the registry.
@intesta · External

One-call trust check for any domain (A0-A4, verdict, signed) + fact passports; same tools as remote

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 PyPI.Free to use.
MCP server: One MCP server.
WhoisxmlapiRun by its publisher: served from their own domain, namespace checked by the registry.
@whois-api-llc · External

32 WHOIS, DNS, IP, threat intelligence, email, and bulk tools for AI agents via WhoisXML API.

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

Email infrastructure for AI agents: send, authenticate domains, track delivery, diagnose issues.

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.
Utuh watcherRun by its publisher: served from their own domain, namespace checked by the registry.
@pugarhuda · External

Sweep bonded completeness claims on Creditcoin against Ethereum, and refute one that omits an event.

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.
whatismynetip
@labaccessnow · External

Subnet math, port and MAC lookups, DNS, DNSBL, TLS cert inspection, public IP. No account.

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.
SecOps Field Notes
@labaccessnow · External

CVSS scoring, IOC extraction, email header triage, hash/JWT/timestamp decoding, CISA KEV lookup.

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 Docker.Free to use.
MCP server: One MCP server.
Loophole Tape
@gosadu · External

pump.fun & Robinhood Chain launch data: radar, risk checks, delta feed, datasets, keys. x402 USDC

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

x402 seller trust for AI agents: verify on-chain revenue, check delivery, diagnose listings.

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.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
MANDATE Credential Broker
@projetnanocorp · External

MCP server for mandates, delegation, policy-gated execution, credential grants, and audit.

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

Is this number safe to call or text right now? Live carrier, CNAM, spam and SMS checks for agents.

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.
upkeep-mcp
@tiagocalado86 · External

Website maintenance checks: domains, SSL, uptime, technical SEO and accessibility

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