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.

Search servers

Search

Showing 871 to 900 of 1818

• agentlink

  io.github.tombaldwin/agentlink

  AI agents on different machines and Claude accounts message each other. Wakes idle Claude Code.

  Community npmstdio ai-models

• agentram-mcp

  io.github.seanmarkwei/agentram-mcp

  Model Context Protocol server for AgentRAM. Persistent memory for AI agents.

  Community npmstdio ai-modelsmemory

• agentready

  io.github.puluceno/agentready

  Can ChatGPT, Claude and Perplexity reach and read a website? Score, problems found and fixes.

  Community remotestreamable-http ai-modelssearch

• agents-party

  io.github.1gr14/agents-party

  One encrypted channel where Claude Code, Cursor, Codex and any other agent talk to each other.

  Community npmstdio ai-models

• agentshield-mcp

  io.github.dl-eigenart/agentshield-mcp

  Detect prompt injection, jailbreak, and social-engineering attacks in LLM agents.

  Community npmstdio ai-models

• agentsocks

  io.github.Aelethion/agentsocks

  Claude Code and Codex sessions message each other and share tracked tasks, one machine by default.

  Community npmstdio ai-models

• agiscorecard-web3-incentives

  io.github.f-tiger/agiscorecard-web3-incentives

  Model contributor rewards with declared quality weights and caps; separate revenue from subsidies.

  Community remotestreamable-http ai-models

• agiscorecard-web3-permit

  io.github.f-tiger/agiscorecard-web3-permit

  Review declared AI data permissions, expiry and regions; model revenue splits without moving funds.

  Community remotestreamable-http ai-models

• agiscorecard-web3-route

  io.github.f-tiger/agiscorecard-web3-route

  Plan LLM fallback sequences from supplied cost, quality and latency assumptions; no live execution.

  Community remotestreamable-http ai-models

• agora-mcp

  io.github.vorluno/agora-mcp

  Shared per-repo space for Claude Code sessions: see activity, get collision warnings, notes.

  Community npmstdio ai-modelsmemory

• agy-bridge

  io.github.sshahzaiib/agy-bridge

  Delegate heavy tasks from Claude Code to the Antigravity CLI (Gemini) with quota-aware failover.

  Community npmstdio ai-models

• ai-brand-visibility-tracker

  io.github.Cookient16/ai-brand-visibility-tracker

  Check if ChatGPT, Perplexity & Gemini mention or cite a brand. Share of voice + GEO/AEO tracking.

  Community ai-modelsaudiosearch

• ai-cli-mcp

  io.github.mkXultra/ai-cli-mcp

  Run Claude, Codex, Gemini, Forge, and OpenCode CLIs through MCP with background jobs

  Community npmstdio ai-models

• ai-code-scanner

  io.github.4hmetuyar/ai-code-scanner

  Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection

  Community npmstdio ai-modelsapi-integration

• ai-code-scanner

  io.github.GuardBee/ai-code-scanner

  Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection

  Community npmstdio ai-modelsapi-integration

• ai-companion-safety-lint

  io.github.jmshinhwa/ai-companion-safety-lint

  Reads your companion chatbot's system prompt against California SB 243, New York GBL Article 47, Ill

  Community npmstdio ai-models

• ai-consensus

  io.github.TheStevenJohnstone/ai-consensus

  Standing review layer for coding agents: Claude, GPT and Gemini debate, return consensus + dissent.

  Community npmstdio ai-models

• ai-context-kit

  io.github.ofershap/ai-context-kit

  Lint, measure, and sync AI context files across Cursor, Claude Code, Copilot.

  Community npmstdio ai-modelsdeveloper-toolsfiles

• ai-cost-analyzer

  io.github.vpatser1/ai-cost-analyzer

  Analyze LLM API costs: token waste detection, caching savings estimates, model comparison

  Community npmstdio ai-modelsapi-integrationcrypto

• ai-dev-workspace

  io.github.Alenroyfeild/ai-dev-workspace

  Local Markdown task memory shared by Claude Code and Codex over stdio MCP.

  Community pypistdio ai-modelsdocumentsmemory

• ai-model-license-lint

  io.github.jmshinhwa/ai-model-license-lint

  Reads the open-weight model IDs in your code and names the licence clause that binds you - 22 rules

  Community npmstdio ai-models

• ai-model-lifecycle-index

  io.github.oscarlopez-gif/ai-model-lifecycle-index

  Cross-vendor AI model lifecycle: status, sunset dates, and migration targets, source-cited.

  Community remotestreamable-http ai-models

• ai-model-retirement-lint

  io.github.jmshinhwa/ai-model-retirement-lint

  Finds the LLM model IDs pinned in your code that vendors have already switched off, or have dated to

  Community npmstdio ai-models

• ai-r

  io.github.pro-target/ai-r

  Read local AI agent sessions (Claude Code, Codex, OpenCode, Antigravity, Pi): intents, plans, tools

  Community pypistdio ai-models

• ai-visibility

  io.github.sharozdawa/ai-visibility

  Track brand visibility across ChatGPT, Perplexity, Claude, and Gemini.

  Community npmstdio ai-modelssearch

• ai-visibility-tracker

  io.github.gaelasao/ai-visibility-tracker

  Is your brand mentioned and cited in ChatGPT, Perplexity, Gemini and Google AI answers?

  Community ai-modelssearch

• aichat

  io.github.rcgalbo/aichat

  Inter-agent communication for multi-agent Claude Code workflows.

  Community npmstdio agentsai-modelsautomation

• aidatataskrunner-mcp

  io.github.TradeSystemsNique/aidatataskrunner-mcp

  MCP server for AiDataTaskRunner Panel (MT5) - Control data generation and ML model training via MCP

  Community pypistdio ai-models

• aidocs

  io.github.CloudCorpRecords/aidocs

  OpenAI docs, guides, changelog and API reference as MCP tools.

  Community npmstdio ai-modelsapi-integration

• aihot-mcp

  io.github.Jing7ao/aihot-mcp

  AI HOT 资讯 MCP Server - 让 Claude Code 直接获取 AI 行业日报和动态

  Community npmstdio ai-models

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.