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.

Show All Verified domain Community Sort Stars Recent Name

Showing 1651 to 1680 of 1741

synapse-audit

io.github.digidenone/synapse-audit

AI-Powered Security Scanner for LLMs. Detects vulnerabilities and syncs with SynapseAudit.

Community npmstdio security
tablecloth-mcp

io.github.yourtablecloth/tablecloth-mcp

Open Korean e-Gov and finance sites in a clean, disposable Windows Sandbox with security programs.

Community npmstdio code-execution finance security
taskbounty-check

io.github.eliottreich/taskbounty-check

Local GitHub Actions/CI maintenance check (action pinning, token perms). Not a full security audit.

Community npmstdio security crypto git
tech-risk

ai.greyridgesignals/tech-risk

MCP security scanner: tool-poisoning & prompt-injection audit (OWASP LLM01/LLM08), x402-payable

Verified domain pypiremotestdio security
tech-risk

io.github.rezearcher/tech-risk

MCP security scanner: tool-poisoning & prompt-injection audit (OWASP LLM01/LLM08), x402-payable

Community pypiremotestdio security
techtenstein-seo

io.github.sathvic-kollu/techtenstein-seo

On-page SEO audit for any URL. Titles, meta, headings, links, score, and fix recommendations.

Community pypistdio marketing security
tellcheck

io.github.CloudCorpRecords/tellcheck

Voice-style checks and a deterministic AI-tell audit for your writing.

Community npmstdio security
test-shape-mcp

io.github.mrfentmen/test-shape-mcp

Audit local test structure using aggregate as MCP: real tools for real work.

Community npmstdio security testing
the drain

ai.thedrain/board

Plain-text security bulletin board for AI agents: read, search, post, reply. No auth to read.

Verified domain remotestreamable-http search security
think-mcp

net.agentutil/think-mcp

Intent security pre-flight checks for autonomous AI agents.

Verified domain npmstdio security
thrd

io.github.SergioRico1/thrd

Thrd MCP: agent email tools for events/threads, safe send/reply, usage, trust and security.

Community npmstdio email security
threat-rules

io.github.GuardBee/threat-rules

GuardBee MCP bridge to Agent Threat Rules (ATR) for runtime agent/MCP threat detection

Community npmstdio security
threatcluster

io.github.Jam0k/threatcluster

Live threat intel for agents: incidents, actors, CVEs with KEV/EPSS, ransomware leak-site victims.

Community npmremotestdio security
three.ws Provenance

io.github.nirholas/provenance-mcp

Append-only, signed, on-chain-verifiable agent action log — record and audit what agents did.

Community npmstdio security
tlpt

io.tooloracle/tlpt

TLPTOracle — 17-tool TIBER-EU TLPT framework: scope, threat intel, scenarios, reports.

Verified domain remotestreamable-http security
token-risk

io.nip.5-9-107-124/token-risk

DeFi pool yield+security intelligence & token/contract risk scanner. USDC on Base via x402.

Verified domain remotestreamable-http crypto security
tollbooth

io.github.huwhitememes/tollbooth

37 paid x402 MCP tools for OSINT, prediction markets, web intel, and agent security on Base USDC.

Community remotestreamable-http security
toolmesh

io.github.DunkelCloud/toolmesh

Self-hosted MCP gateway. Turn any REST API into MCP tools via YAML (DADL). Authz, audit, policies.

Community api-integration security
toolprint by JEStats

io.github.jestatsio/toolprint

package-lock.json for MCP trust: catch MCP rug-pulls, tool poisoning, and leaked secrets.

Community npmstdio security
tools

dev.workers.sebastiaan-ba3.mcpgateway/tools

Doormat Capital's paid x402 safety tools (token scan, HTTP security headers) for AI agents.

Verified domain remotestreamable-http api-integration crypto security
totp-mcp

io.github.mrfentmen/totp-mcp

Generate and verify TOTP codes offline: RFC 6238 with SHA-1/256/512 and fresh base32 secrets

Community npmstdio security
tracewatch

io.github.CloudCorpRecords/tracewatch

Observability, tracking, and root-cause for Security Wave scans and findings.

Community npmstdio monitoring security
tradememory-protocol

io.github.mnemox-ai/tradememory-protocol

Tamper-evident decision audit trail and outcome-weighted memory for AI trading agents.

Community pypistdio finance memory security
trust-tools

com.obeliskgate/trust-tools

Website security ratings, token verification, and tamper-evident ledger heads from Obelisk Gate.

Verified domain remotestreamable-http crypto security
trustsource

io.github.SurfEther/trustsource

x402-paid domain verification for AI agents — trustscore, SSL, security headers, robots.

Community npmstdio security
turva-mcp

dev.turva/turva-mcp

Read-only MCP server for turva.dev, an agent-readiness audit and advisory service.

Verified domain remotestreamable-http security
unflagdomain: website blacklist removal

com.unflagdomain/website-blacklist-removal

Website flagged by security vendors? Free scan, then we send the removal requests for you (paid).

Verified domain remotestreamable-http security
universalcartmerchantgate-mcp

com.clauxel.universalcartmerchantgate/universalcartmerchantgate-mcp

Remote MCP for Universal Cart merchant readiness MCP, structured receipts, audit logs, and reviewer-

Verified domain remotestreamable-http monitoring security
update-hijack-poc

io.github.NOTTIBOY137/update-hijack-poc

PoC benign MCP server for update-hijack security research

Community npmstdio science security
uta-shield

io.github.eddyflores100-lang/uta-shield

Provider-side MCP firewall: identity, threat-intel, barter, rate limits, DLP, audit.

Community npmstdio security

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.