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.
JFrog Remote MCP Server
@jfrog · External

MCP Server for JFrog, providing tools for development and artifact management.

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.
Domain IntelligenceRun by its publisher: served from their own domain, namespace checked by the registry.
@oti-labs · External

WHOIS/RDAP, DNS, SSL, live subdomains with IPs, and SPF/DMARC/DKIM for any domain.

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.
Ntobjmanager
@lupingqaq · External

Stateful Windows RPC attack-surface research for AI agents: 22 tools on NtObjectManager.

Not assessed yet.What it can do is not assessed yet.Runs on your machine, installed from a package registry.Free to use.
MCP server: One MCP server.
BomlyRun by its publisher: served from their own domain, namespace checked by the registry.
@bomly-dev · External

Give your coding agent the dependency graph it is about to change: scan, diff, explain, audit

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

Local-first, contract-governed data explorer with read-only, PII-masked query tools for AI agents.

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.Free to use.
MCP server: One MCP server.
quantakrypto pqc-toolsRun by its publisher: served from their own domain, namespace checked by the registry.
@quantakrypto · External

Scan code for quantum-vulnerable cryptography and get NIST post-quantum migration guidance.

5% 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.
AegisRun by its publisher: served from their own domain, namespace checked by the registry.
@getaegis · External

Credential isolation for AI agents. Inject secrets at the network boundary.

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.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
mcp-fns-check
@atomno-mcp · External

Russian tax authority (FNS) counterparty checks: status, debts, blocks. Due diligence MCP.

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

Schema, database, document, user and dev-server tools for a Rebase backend project.

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.
Infrabroker
@luisgf · External

SSH & Kubernetes access broker for AI agents; the model never touches a credential.

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.
Authentik MCP Server
@samik081 · External

Manage Authentik through AI assistants

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

Vanta compliance MCP server: vulnerabilities, tests, controls, evidence, people, vendors, docs

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.
Webhook.site MCP Server
@zebbern · External

Capture HTTP, email, and DNS callbacks with webhook.site from MCP clients.

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

Credential isolation for AI agents: placeholder secrets, policy checks, optional human approval.

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.
Cortex Gateway
@wellknownmcp · External

Self-hosted federated MCP gateway: one OAuth 2.1 MCP server in front of N apps, user-level scopes.

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

Security scanner for MCP servers and skill files. Detects AVE vulnerabilities before production.

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 PyPI.Free to use.
MCP server: One MCP server.
ChromaDB Remote MCP Server
@meloncafe · External

Remote ChromaDB vector database MCP server with streamable HTTP transport

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.
SatGate – Economic Firewall for AI AgentsRun by its publisher: served from their own domain, namespace checked by the registry.
@satgate-io · External

Budget, payment and audit controls for AI agent API calls and MCP tool calls.

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; it needs your API key.Free to use.
MCP server: One MCP server.
CIPP
@wyre-ai · External

MCP server for CIPP — M365 multi-tenant management for MSPs (users, tenants, policies).

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 Docker.Free to use.
MCP server: One MCP server.
pkgxray
@adamsjack711-ux · External

Pre-install security scans for npm packages, MCP servers, and AI agents with cited verdict evidence.

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.
CIPP
@wyre-technology · External

MCP server for CIPP — M365 multi-tenant management for MSPs (users, tenants, policies).

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 Docker.Free to use.
MCP server: One MCP server.
Scopeblind
@tomjwxf · External

Scan, protect, and monitor APIs from AI coding tools. Device-level rate limiting.

9% 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.
Scholar SidekickRun by its publisher: served from their own domain, namespace checked by the registry.
@mlava · External

Catch AI-fabricated citations (real DOI + fake title). Retraction, open-access, 10,000+ CSL styles.

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.
Trentina
@crunchtools · External

Secure MCP gateway and quarantine for AI agent traffic — three-layer prompt injection defense

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 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