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.
Shieldly MCPRun by its publisher: served from their own domain, namespace checked by the registry.
@shieldly-io · External

AI-Powered AWS security analysis: scan IAM policies and CloudFormation for risks and escalation.

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.
Security Intel MCP
@selflabbs · External

CVE lookups (NVD) and dependency-manifest audits (OSV) for AI agents. No API keys.

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.
Palveron Governance GatewayRun by its publisher: served from their own domain, namespace checked by the registry.
@palveron · External

Advisory governance checks for MCP hosts; enforcement runs in the Palveron remote MCP proxy.

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.
APIFreaks MCPRun by its publisher: served from their own domain, namespace checked by the registry.
@api-freaks · External

APIFreaks MCP: live APIs for agents. Enable modules with ENABLE_MODULES; discover via list_modules.

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

Verification and trust checks for AI agents: validate, screen, propose, accounts, usage.

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.
Stillos Kya
@stillmarcus24 · External

Counterparty due-diligence infrastructure: OFAC screening, on-chain risk, signed verdicts.

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.
Purify Security Feeds
@eason4kim-rocket · External

Query CISA KEV / EPSS vulnerability feeds with full per-record provenance and auditable versions

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 Docker.Free to use.
MCP server: One MCP server.
Fabler x402 ToolsRun by its publisher: served from their own domain, namespace checked by the registry.
@fablerlabs · External

Free catalog and 2,048-character secret-scan preview for Fabler's x402 agent tools on Base.

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

Discovery, OAuth, project operations, and exact project MCP handoff for Spala backend projects.

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.
Korea Business Verify
@wujinkim · External

한국 사업자 검증 액션 MCP 서버 — 진위확인·휴폐업·과세유형·세금계산서 발행 가능 여부 (국세청 공공데이터 기반)

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

Real-time exploit-exposure risk check for EVM wallets, paid per query via x402 (USDC on Base).

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.
Scamcheck
@smijo-geek · External

Scan suspicious messages, URLs, and text for scams with AI. Free tier - no API key required.

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.
Google Workspace Admin Security-Audit MCP
@shigechika · External

MCP server for Google Workspace security auditing — login audit, external sharing, daily brief

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.
AttestdRun by its publisher: served from their own domain, namespace checked by the registry.
@attestd-io · External

CVE checks, supply chain signals, live catalog, and CVE detail for MCP clients (infra, PyPI, npm).

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.
sql-stewardRun by its publisher: served from their own domain, namespace checked by the registry.
@pawansingh3889 · External

The agent never writes SQL: queries compile from a semantic layer you control, PII refused first.

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 PyPI.The repository is archived.Free to use.
MCP server: One MCP server.
Numbers Online — phone intelligenceRun by its publisher: served from their own domain, namespace checked by the registry.
@numbers · External

Read-only phone intelligence for AI voice agents — line type, risk, DNC, signed receipts.

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.
Agent Transaction ControlRun by its publisher: served from their own domain, namespace checked by the registry.
@flint · External

Issue Agent Passports and verify agent authority before value moves. Signed verification records.

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

Professional DNS diagnostics: 14 tools for DNS, DNSSEC, email security, SSL, and propagation.

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

Read-only banking and personal finance for AI agents: accounts, transactions, spending, budgets.

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

KYC, KYB, AML, wallet screening, transaction monitoring, and fraud workflows for AI agents.

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.
Security IntelRun by its publisher: served from their own domain, namespace checked by the registry.
@elsas · External

Daily Ed25519-signed security intelligence for AI-agent stacks; CVEs & advisories, paid via x402.

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.
MCP Server AttestationRun by its publisher: served from their own domain, namespace checked by the registry.
@studiomeyer · External

Ed25519-signed MCP tool manifests + spawn attestation. Layer-2 supply-chain hardening.

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

Read and grow a person's falsifiable, consent-based model of how they work with AI (CMP).

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

Pre-purchase trust checks for AI agents: recalls, scam signals, proceed/caution/avoid verdict.

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.

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