MCP server directory
59888 public MCP servers from the official MCP Registry (26001 from verified domains, 33887 community). Search, filter, copy a setup snippet. Nothing here is installed by cosmic-mcp.
Community listing. Not installed or verified by cosmic-mcp. Check the source before you run anything.
Showing 781 to 810 of 1125
-
etch
io.github.SaravananJaichandar/etch
Etch is a signed audit chain for AI agent decisions, offline-verifiable against pinned public keys.
-
fde-agent
io.github.minjikim89/fde-agent
Diagnose AI workflows for failure, security, and handoff risks — RED/AMBER/GREEN per node.
-
feedmyagent
io.github.makash/feedmyagent
Agent-readable feed: AI/agent tech news, security advisories, compliance deadlines, and live events.
-
figuard-mcp
io.github.figuard/figuard-mcp
Pre-flight spend authorization for AI agents. Set a budget, enforce limits, audit every decision.
-
flagrix
io.github.flagrix-io/flagrix
Scan GitHub repos and profiles for malware before cloning — commit-pinned risk verdicts for agents
-
flatbread
io.github.flatbread-cli/flatbread
Share a coding agent's session as one link, secrets redacted first; pull another run's brief.
-
flowcheck
io.github.CloudCorpRecords/flowcheck
Least-privilege auditor for GitHub Actions workflows: permissions, triggers, secrets.
-
flutter_structure_mcp
io.github.Nilesh9783/flutter_structure_mcp
Audit architecture, security, memory, and code quality in Flutter, Laravel, Node, Python, & Vue.
-
forkflux-mcp
io.github.forkflux/forkflux-mcp
Self-hosted multi-agent collaboration and audit layer for AI-assisted engineering teams
-
frame-mcp
io.github.lambdasec/frame-mcp
MCP server for the Frame security scanner: scan, verify, fix, exploit, packs and separation logic.
-
freshdeps-mcp
io.github.SolvoHQ/freshdeps-mcp
Live npm/PyPI dependency-health verdicts so AI agents stop recommending stale or CVE'd packages
-
gatekeeper
io.github.Runestone-Labs/gatekeeper
Run MCP tool calls through Runestone Gatekeeper — policy enforcement, human approval, audit.
-
ghg-ledger
io.github.jdhart81/ghg-ledger
Deterministic Scope 1/2/3 GHG inventories with bundled factors and audit hashes.
-
ghost-mcp-server
io.github.ghostsecurity/ghost-mcp-server
Minimal MCP server for Ghost Security API - compatible with all MCP clients
-
ghost-post-preview
io.github.farssaadeldin7-ux/ghost-post-preview
Read a draft post the way its audience and its ranking system will: fold test, hook audit,...
-
github-audit-mcp
io.github.robertoyanguas-ops/github-audit-mcp
Evaluates any GitHub repository for license risk, maintenance velocity, stars/forks, and security.
-
global-intel-exchange
io.github.Joseph-CEO/global-intel-exchange
Real-time sanctions screening, CVE, and company registry checks for agents.
-
goflag
io.github.tancredesimonin/goflag
SEO and i18n audit of the site an agent is editing: localhost or protected preview, with sources.
-
golive
io.github.myanptl/golive-mcp
Check a site before you share it: link previews, SPA refresh 404s, noindex, security headers.
-
gorgon-scout
io.github.Gorgon-Cyber/gorgon-scout
Run AI-driven web-app and API security scans (DAST) from Claude or any MCP agent. Windows.
-
grantex
io.github.mishrasanjeev/grantex
OAuth 2.0 for AI agents — scoped delegation tokens, audit trails, and revocation.
-
grim-mcp
io.github.AbduljabbarBXR/grim-mcp
Security audit for AI agents: code, deps, exposure, secrets, drift, SBOM, and IoC.
-
groundtruth
io.github.rm-rf-prod/groundtruth
Live docs MCP server. 793+ libraries, evidence-verified answers, code audit, snippets, dispatch.
-
gsep-mcp
io.github.gsepcore/gsep-mcp
AI agent security via MCP: C3 firewall, C4 immune system, C5 action guard, self-evolving prompts.
-
guardrails
io.github.ExpertVagabond/guardrails
AI Agent Guardrails MCP server - security layer
-
guardvibe
io.github.goklab/guardvibe
Deterministic security layer your AI can't be. 657 rules, 39 tools, CLI + doctor + host audit.
-
gws-admin-mcp
io.github.antct11/gws-admin-mcp
Safe Google Workspace admin for AI agents: read-only by default, confirm-gated deletes, audit log.
-
hacktricks-mcp
io.github.zebbern/hacktricks-mcp
Offline full-text search over the HackTricks security wiki, synced every 3 days.
-
handinloop-mcp-server
io.github.handinloop/handinloop-mcp-server
Human-in-the-loop document extraction: submit a doc, get validated fields and an audit trail.
-
handinloop-mcp-server
io.github.lesofi/handinloop-mcp-server
Human-in-the-loop document extraction: submit a doc, get validated fields and an audit trail.
Source: the official MCP Registry (registry.modelcontextprotocol.io), refreshed daily, plus public GitHub data. "Verified domain" means the publisher proved the namespace's domain to the registry; it is not a review. Machine-readable: /v1/directory/servers.