Verified directory
MCP Server Directory
Search Registry metadata and see exactly what our independent monitoring has verified.
62,734 matching servers
Local only
AgentFX
io.github.agentfxhq/agentfx
Motion graphics and video effects your AI agent can script, lint, preview and render.
— latency— 24h
Local only
AgentGate
io.github.agentkitai/agentgate
Human-in-the-loop approval gateway for AI agents over MCP: request, decide, approve.
— latency— 24h
Local only
agentgate
io.github.ciceroyang/agentgate
Read-only evidence for the tools agents run: MCP server records, coverage and policy.
— latency— 24h
Local only
agent-gate
com.forgeorbital/agent-gate
Local mandate gate and proof trail for AI agents that take consequential actions.
— latency— 24h
Local only
agent-gate
io.github.Jott2121/agent-gate
Fail-closed quality gate and hash-chained receipt ledger for AI agent workflows.
— latency— 24h
Local only
AgentGo
io.github.Nishkalkashyap/agentgo
Run Codex and Claude Code on your computer from an MCP client, and track or continue their runs.
— latency— 24h
Local only
AgentGo
io.github.Moha2005269/agentgo
Real Chromium browser for AI agents: compact outlines, diff-only replies, real input, you approve.
— latency— 24h
Local only
agent-godmode
io.github.mdvohra/agent-godmode
Sandboxed workspace MCP: file ops, argv-only run_command, list_files; BYO LLM prompts.
— latency— 24h
Local only
AgentGraph Trust
io.github.agentgraph-co/agentgraph-trust
Security scanning and trust verification for AI agent tools.
— latency— 24h
Local only
agent-graph-auditor
io.github.4hmetuyar/agent-graph-auditor
Finds transitive excessive agency across LangGraph/CrewAI/AutoGen orchestration graphs
— latency— 24h
Local only
agent-graph-auditor
io.github.GuardBee/agent-graph-auditor
Finds transitive excessive agency across LangGraph/CrewAI/AutoGen orchestration graphs
— latency— 24h
Local only
agentgrasp
io.github.damejeras/agentgrasp
Yes/no questions about local files, and relevant-file search, with TypeSafe Jev
— latency— 24h
Local only
AgentGuard
io.github.MerchantGuard/agentguard
Local spend caps, kill-switch blocking and Ed25519-signed receipts for AI agent tool calls.
— latency— 24h
Local only
agentguard
io.github.MukundaKatta/agentguard
Network-egress firewall for agent tools: check URLs against a declarative policy.
— latency— 24h
Local only
agentguard
io.github.agentwares/agentguard
MCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log.
— latency— 24h
Local only
AgentGuard
io.github.zaxcoraider/agentguard-mcp
Let an AI agent pay on NEAR through a vault whose spending rules a contract enforces, not the agent.
— latency— 24h
Local only
agent-guard
io.github.ipezygj/agent-guard
Safety checks an agent runs before it acts: package malware, destructive command, secret leak.
— latency— 24h
Local only
agent-guard
io.github.mdfifty50-boop/agent-guard
Constitutional guardrails and loop detection for AI agents
— latency— 24h
Local only
AgentGuard — security checks for AI agents
io.github.shuaicongxiaomai/agentguard
Secret, CVE and dependency-vulnerability scanning for AI agents (free, OSV.dev).
— latency— 24h
Local only
agentguard47
io.github.bmdhodl/agentguard47
Read-only MCP server for coding-agent traces, alerts, costs, usage, and budget health.
— latency— 24h
Local only
agent-guard-mcp
io.github.Kavachh/agent-guard-mcp
Git-aware safe file ops for AI agents: delete anything except git-tracked source code.
— latency— 24h
Local only
agent-guard-mcp
io.github.liminalpepe/agent-guard-mcp
Verify-before-act safety checks for AI agents: packages, lockfiles, manifests, CI workflows.
— latency— 24h
Local only
agent-guardrail
io.github.rudimentall1/agent-guardrail
Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.
— latency— 24h
Local only
agent-guards
io.github.mlawsonking/agent-guards
All six agent guard suites in one local MCP server, with optional cloud intelligence.
— latency— 24h