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

Scan GitHub-hosted AI skills for vulnerabilities: prompt injection, malware, OWASP LLM Top 10.

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.
identifAI MCP ServerRun by its publisher: served from their own domain, namespace checked by the registry.
@identifai · External

Detect AI-generated images, videos, and audio with identifAI's deepfake detection tools.

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

Governed app access for AI agents: 1,000+ apps & 12,000+ tools via Code Mode MCP.

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; you sign in with your account.Free to use.
MCP server: One MCP server.
Toolforest
@toolforest · External

Hosted MCP server with managed OAuth for 15+ toolkits: Google Workspace, Fitbit, Oura, Kalshi, etc.

10% 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.
InboxGuardRun by its publisher: served from their own domain, namespace checked by the registry.
@inboxguard · External

Scan and fix a domain's email deliverability (SPF, DKIM, DMARC, MTA-STS, BIMI, DNS blocklists).

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

Linux kernel CVE analyzer: upload a .config, get a CycloneDX VEX report of affecting CVEs.

4% 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.
Agent Zero — ERC-8004 Trust FilterRun by its publisher: served from their own domain, namespace checked by the registry.
@onchainagentintel · External

Trust filter for ERC-8004: only ~3.8% of x402 endpoints hit 5+ payers/30d. Free MCP; x402 upgrade.

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.
MCP server: One MCP server.
Agent Safe
@wowcool · External

Email safety MCP server. Detects phishing, prompt injection, CEO fraud for AI agents.

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; it needs your API key.Free to use.
MCP server: One MCP server.
Satoshidata Wallet Intel
@wrbtc · External

Bitcoin wallet intelligence for AI agents: trust, labels, tx verify, fees, and timestamps.

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.
MCP server: One MCP server.
DealHub Admin
@vishvick · External

DealHub MCP server for admins. Manage versions and users with 7 tools via Claude AI agents.

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.
Policycheck
@vibegpt · External

AI seller verification and policy risk analysis for any online store.

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.
Apiiro
@vardior9 · External

Ship software securely with an AI AppSec Agent

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 a package registry.Free to use.
MCP server: One MCP server.
AgentSec MCP
@traveljamboree · External

Security intelligence via x402 on Base. CVE lookup, IP reputation, secret scanning.

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.
Defender
@trickyfalcon · External

Execute KQL queries against Microsoft Defender Advanced Hunting via natural language.

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 PyPI.Free to use.
MCP server: One MCP server.
Msdefenderkql
@trickyfalcon · External

Execute KQL queries against Microsoft Defender Advanced Hunting via natural language.

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 PyPI.Free to use.
MCP server: One MCP server.
WhoisLookup
@therealmrfunguy · External

Domain WHOIS, DNS records, SSL certificates, and availability checks.

12% 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; it needs your API key.Free to use.
MCP server: One MCP server.
Voice Truthgate
@hei33enberg · External

Honest voice authenticity for AI agents: enrol a voice, verify a call clip. Signal, not verdict.

12% 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.
N0s1
@spark1security · External

Secret scanner for Slack, Jira, Confluence, Asana, Wrike, Linear, Zendesk, GitHub and GitLab

21% 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.
Mception
@soufianetahiri · External

Audits other MCP servers for security risks. Returns safe / caution / unsafe / inconclusive.

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 PyPI.Free to use.
MCP server: One MCP server.
RunSec Io MCP
@runsec-io · External

RunSec MCP server for workspace security scanning and remediation workflows.

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.
Wolfpack Intelligence
@rok-labs · External

On-chain security and market intelligence for trading agents on Base.

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.
ComOS Portal — AI-Native SaaS Management
@ronrey · External

93 MCP tools for platform administration via AI agents. Billing, support, teams, and more.

Not assessed yet.What it can do is not assessed yet.A remote server; no sign-in.Deprecated by the publisher: Decommissioned — mcp.comos-portal.com no longer resolves to a service. The live MCP surface is https://mcp.comos-gateway.com/mcp (io.github.ronrey/comos-federation), Streamable HTTP. The endpoint has not answered since 1 Oct.Free to use.
MCP server: One MCP server.
Polarity
@radar989 · External

Real-time threat intelligence lookups and IOC parsing from your self-hosted Polarity instance.

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.
Anchord (AnchorID)
@nolenation04 · External

Read-only MCP for identity resolution and write guardrails.

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; it needs your API key.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