MCP server directory

58869 public MCP servers from the official MCP Registry (25190 from verified domains, 33679 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.

Search servers

Search

Showing 121 to 150 of 3012

• Agent Channel Placement

  io.github.sadri-dridi/agent-channel-placement

  Placement across agent channels: MCP, Cursor, Claude, ChatGPT, npm, docs, Smithery, Glama.

  Community remotestreamable-http ai-modelsdeveloper-tools

• Agent Comms

  io.github.ExaDev/agent-comms

  Cross-harness communication mesh for LLM agents — rooms, DMs, presence, and visibility over TCP

  Community npmstdio ai-models

• Agent Cost Hub

  com.agentcosthub/agent-cost-hub

  LLM API prices and AI agent cost estimates, verified daily. Read-only cost lookup tools.

  Verified domain remotestreamable-http ai-modelsapi-integration

• Agent Cost Log

  com.botrecipe/costlog

  Cost per run, tool, model and day for AI agents, from one call or an OpenTelemetry export.

  Verified domain remotestreamable-http ai-models

• Agent Cowork Memory

  io.github.rxthlessbeats/agent-cowork-memory

  Shared memory and delegation for Codex, Cursor, Claude Code, and OpenCode.

  Community npmstdio memoryai-models

• Agent Daily

  io.github.gregpunch/agent-daily

  Live health of 65 agent APIs/MCPs plus a 15-min LLM leaderboard; recommend(task) picks a provider.

  Community remotestreamable-http ai-modelshealth

• Agent Data Co

  com.agentdataco/api

  Daily AI-ecosystem data: GitHub AI/MCP repos, MCP registry, HF trending, LLM pricing, with history.

  Verified domain remotestreamable-http ai-modelsgit

• Agent Data Tools: AI

  io.github.Nutshell2000/agent-data-tools-ai

  33 tools: LLM chat, summaries, translation, embeddings, speech, images. 25 free calls.

  Community remotestreamable-http ai-modelsaudiocommunication

• Agent Docs

  io.github.KonstantinStarovoytov/agent-docs

  Search the official docs of Claude Code, Cursor, OpenAI Codex and MCP, refreshed daily.

  Community remotestreamable-http ai-modelssearch

• Agent Guild

  ai.oddessentials/agent-guild

  See and steer Claude Code, Codex, Antigravity, Grok, Docker Agent and shell sessions in Agent Guild.

  Verified domain npmstdio ai-modelsdevops

• Agent Hub

  com.torbrooknews.mcp/agent-hub

  48 pay-per-call tools: search, scraping, PDF, OCR, LLM, crypto, DeFi, SEC. x402 USDC.

  Verified domain remotestreamable-http cryptodocumentsai-models

• Agent Intern

  io.github.SinanTufekci/agent-intern

  Delegate from Claude Code to Gemini, Codex, Copilot, Cursor and opencode CLIs as sub-agents.

  Community pypistdio ai-models

• Agent JSON Reliability

  io.github.toninovo4249-ai/agent-json-reliability

  Deterministic inspect, safe repair, and JSON Schema validation for agent JSON. No LLM.

  Community pypistdio ai-models

• Agent Lease

  io.github.Buggy1111/agent-lease-mcp

  Keep Claude Code and Codex off each other's files: hook-enforced path leases, presence, messages.

  Community pypistdio ai-modelsfiles

• Agent Permissions Index

  app.vercel.agent-permissions-index/agent-permissions-index

  Grade Claude Code, Gemini CLI and Cursor configs for risky permissions; get public config stats.

  Verified domain remotestreamable-http ai-models

• Agent Prompts A to Z

  com.agentpromptsatoz/packs

  Read-only catalog of prompt packs and rule files: Cursor, CLAUDE.md, AGENTS.md, SKILL.md.

  Verified domain remotestreamable-http ai-modelsfiles

• Agent Provider Depot

  com.getagentdepot/agent-provider-depot

  No-key MCP: pick the LLM, sandbox, search, email or DB provider; sourced prices; API error rescue.

  Verified domain ai-modelsapi-integrationcode-execution

• Agent Readiness Auditor

  io.github.asish-singh/agent-readiness-auditor

  Audits any website for AI agent readiness and safety, scoring prompt injection risk and llms.txt.

  Community npmstdio ai-models

• Agent Relay — Agent Commons

  ch.greenwave.wall-x/agent-relay

  Discuss ideas and uncertainty with LLM agents: join, browse threads, start discussions and reply.

  Verified domain remotestreamable-http ai-models

• Agent Safe

  io.github.wowcool/agentsafe

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

  Community remotestreamable-http ai-modelsemail

• Agent Security Scanner

  io.github.Mikehzp/agentvuln

  Scan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.

  Community pypistdio securityai-models

• Agent Skill & Config Security Audit

  io.github.tylerscomic-lab/agent-skill-audit-mcp

  Scan AI agent skills and configs for hidden Unicode, prompt injection and exfiltration.

  Community remotestreamable-http securityai-models

• Agent-Native Analytics

  io.github.BuilderIO/agent-native-analytics

  Agent-Native Amplitude/Mixpanel - connect data sources, prompt for charts

  Community remotestreamable-http ai-modelsdata-analytics

• Agent-Shield

  io.github.startekenterprises-ai/agent-shield

  Security scanner for AI agents: prompt injection, leaked secrets, PII, and SSRF-risk URL detection.

  Community remotestreamable-http securityai-models

• AgentDiet A2A Indirect Prompt-Injection & Jailbreak Firewall

  dev.agentdiet/prompt-guard

  Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections an.

  Verified domain remotestreamable-http agentsai-models

• AgentDiet Deterministic A2A Broken-JSON Repair & Schema Validator

  dev.agentdiet/json-repair

  Repairs truncated or malformed LLM JSON outputs (trailing commas, markdown fences, single quotes).

  Verified domain remotestreamable-http agentsai-modelsdocuments

• AgentDrive

  sh.agentdrive/agentdrive

  Cross-agent artifact workspace with provenance across Claude Code, Codex, Cursor, LangGraph.

  Verified domain remotestreamable-http ai-models

• AgentGo

  io.github.Nishkalkashyap/agentgo

  Run Codex and Claude Code on your computer from an MCP client, and track or continue their runs.

  Community npmstdio code-executionai-models

• AgentKernel AI model data

  si.agentkernel/models

  Live prices, rankings, licences and privacy of AI models: best model per task, costs, alternatives.

  Verified domain remotestreamable-http ai-models

• AgentSEO

  dev.agentseo.www/agentseo-mcp

  Live SEO workflow tools for Claude Code, Codex, and AI agents.

  Verified domain npmremotestdio ai-modelsautomationmarketing

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.