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 1591 to 1620 of 1741
-
security-controls
io.github.Ansvar-Systems/security-controls
1,451 security controls across 261 frameworks with bidirectional mapping
-
security-engineer
io.github.GuardBee/security-engineer
Fix GuardBee AI Security Engineer findings in your repo with your coding agent, then verify
-
security-headers-csp-lint
io.github.jmshinhwa/security-headers-csp-lint
Reads security headers and CSP line by line in your config file and names the lines that silently do
-
security-intel
it.elsas/security-intel
Daily Ed25519-signed security intelligence for AI-agent stacks; CVEs & advisories, paid via x402.
-
security-proxy
io.github.4hmetuyar/security-proxy
MCP gateway: many servers, one policy, lethal-trifecta blocking, PII masking, audit log
-
security-proxy
io.github.GuardBee/security-proxy
MCP gateway: many servers, one policy, lethal-trifecta blocking, PII masking, audit log
-
security-scanner-ai-mcp
io.github.CSOAI-ORG/security-scanner-ai-mcp
Security Scanner Ai MCP Server by MEOK AI Labs
-
security-suite
io.github.GuardBee/security-suite
Every GuardBee MCP security tool in one server: OWASP MCP Top 10, secrets, supply chain, TLS/DNS
-
security-tools
com.rangercheck/security-tools
Free front-end security check for any website: a grade plus the secrets and keys it exposes.
-
security-txt-cra-lint
io.github.jmshinhwa/security-txt-cra-lint
13 rules that decide whether a vulnerability report ever reaches you
-
securityscan
io.github.securityscan-api/securityscan
Security for AI agents: MCP audits, secret redaction, skill vetting, network scans, agent checkout.
-
seedance-prompts-mcp
io.github.hanshs474/seedance-prompts-mcp
Search, audit and compose AI video prompts — 150 of them, each rendered into a real video
-
seegeo
com.see-geo/seegeo
Audit any website for AI visibility: graded report, findings with fixes, AI crawler access check.
-
seekrit (local crypto plane)
dev.seekrit/mcp
Zero-knowledge secrets manager — local crypto-plane MCP server: decrypts and injects secrets.
-
selvo
io.github.Cope-Labs/selvo
Linux CVE prioritisation: 16 MCP tools for scan, fleet, runtime, and PR-able fix discovery.
-
sentrysurface
io.github.sentrysurface/sentrysurface
Cybersecurity MCP server for URL scanning, threat intelligence, and domain reputation.
-
seo-webmaster-mcp
io.github.JvnnDev/seo-webmaster-mcp
Audit any public URL for SEO. Add Google Search Console and Bing data through MCP.
-
seracade
io.github.Rckl88/seracade
LLM cost optimization. Audit your calls, prove savings, route to the cheapest quality model. BYOK.
-
shadowgate-mcp
io.github.josephibra/shadowgate-mcp
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
-
shellward
io.github.jnMetaCode/shellward
AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.
-
shield-kya
io.github.The-Pixel-Boys/shield-kya
Audit trail and traceability for AI agents. MCP gate: evaluate, ingest, request approval.
-
shipshape-mcp
io.github.Bytestay/shipshape-mcp
Dockerfile and Kubernetes lint for AI agents: Pod Security Standards, A–F grade, a fix per finding.
-
shopify-geo-audit
io.github.builtbyabs/shopify-geo-audit
Audit any Shopify store for AI search (GEO/AEO) readiness and generate the fixes. No signup.
-
shopify-operations-mcp
io.github.jpka/shopify-operations-mcp
Safe-write Shopify operations: plan-before-execute writes with out-of-band approval and audit.
-
sidclaw-governance-mcp
io.github.VladUZH/sidclaw-governance-mcp
Governance proxy for MCP servers — policy evaluation, human approval, audit trails.
-
sign-cli
io.github.DrBaher/sign-cli
Agent-first e-signature MCP server with offline PAdES signing and hash-chained audit.
-
signoff
io.github.ayuanxx-max/signoff
Five gates that make an agent's 'done' provable: run them, read the verdict, audit the record.
-
signoff-cli
io.github.ayuanxx-max/signoff-cli
Five gates that make an agent's 'done' provable: run them, read the verdict, audit the record.
-
site
uk.co.energyauditcost/site
Energy Audit Cost: the site's own MCP server — enquiry (enquiry = a human handoff, not a...
-
site
uk.co.vacantpropertysecuritycost/site
Vacant Property Security Cost: the site's own MCP server — enquiry (enquiry = a human handoff,...
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.