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 1051 to 1080 of 1818

• context-keeper

  io.github.jarmstrong158/context-keeper

  Durable project-memory MCP: decisions, constraints, and pipelines across Claude sessions.

  Community pypistdio ai-models

• context-oversharing-auditor

  io.github.GuardBee/context-oversharing-auditor

  OWASP MCP10 context oversharing: session dumps, unscoped memory, shared context, prompt leaks

  Community npmstdio ai-modelsmemory

• context-sync

  io.github.Intina47/context-sync

  Universal AI Memory - Sync context across Claude, VsCode, Cursor, Continue, Windsurf, Zed & more

  Community npmstdio ai-modelsdeveloper-toolsmemory

• contextatlas

  io.github.traviswye/contextatlas

  Pre-computed atlas of your codebase for Claude Code: LSP + ADRs + git. 45-72% token reduction.

  Community npmstdio ai-modelscryptodeveloper-tools

• contextforge-mcp

  io.github.alfredoizdev/contextforge-mcp

  Persistent memory MCP server for Claude Code, Cursor, and GitHub Copilot.

  Community npmstdio ai-modelsgitmemory

• contextkeeper

  io.github.TheRealDataBoss/contextkeeper

  Zero model drift between AI agents. Session continuity for Claude, GPT, Gemini, and any LLM.

  Community pypistdio ai-models

• contextweaver

  io.github.dgenio/contextweaver

  MCP gateway: bounded tool shortlists + artifact-backed result firewall. Deterministic, no model.

  Community pypistdio ai-models

• convalytics

  io.github.Dan-Cleary/convalytics

  Read-only analytics for Convex apps, queryable via MCP from Claude, Cursor, and other clients.

  Community remotestreamable-http ai-modelsdata-analytics

• conviction-mcp

  io.github.abcxz/conviction-mcp

  The arena where AI agents compete for real returns. Prompt a strategy.

  Community npmstdio ai-models

• cool-workflow

  io.github.coo1white/cool-workflow

  Signed, cited, replayable workflows for Claude, Codex, Gemini, DeepSeek, and other agents.

  Community npmstdio ai-modelsautomation

• corpusAI Cloud Pricing

  io.github.JTraversa/corpus-cloud-pricing-mcp

  Cloud, GPU and LLM token prices with index fixings. Pay per call over x402 or with a prepaid key.

  Community npmremotestdio ai-modelscrypto

• correctover-mcp-server

  io.github.Correctover/correctover-mcp-server

  Real-time LLM output verification with 6-dim contract validation and auto-failover across providers.

  Community npmstdio ai-models

• cortex

  io.github.VBlackJack/cortex

  Local multi-client RAG server over the Model Context Protocol.

  Community pypistdio ai-modelsvector-search

• crayon-c4-mcp

  io.github.SQUORA-NL/crayon-c4-mcp

  Author, validate and maintain a CRAYON-C4 architecture model — never write an invalid file.

  Community npmstdio ai-models

• creatorloop

  io.github.pandich93/creatorloop

  Instagram content studio for Claude: analytics, competitors, Reels, publishing queue.

  Community pypistdio ai-modelscontentdata-analytics

• creatorscore-mcp

  io.github.creatorscore/creatorscore-mcp

  Vet creators from Claude or ChatGPT: cross-platform trust scores, risk evidence, background checks.

  Community npmstdio ai-models

• creditkarma-mcp

  io.github.chrischall/creditkarma-mcp

  Credit Karma transactions for Claude — spending by category, merchant, and account summary

  Community npmstdio ai-models

• creedspace-mcp-server

  io.github.Creed-Space/creedspace-mcp-server

  Constitutional-AI safety guardrails for any LLM — personas, constitutions, adjudication.

  Community npmstdio ai-models

• crewchat

  io.github.deepankar17/crewchat

  A group chat for AI coding agents: Claude Code, Cursor, Codex, Gemini CLI, Qwen Code and OpenCode.

  Community pypistdio ai-modelscommunication

• crimson-crab-mcp-template

  io.github.singhpratech/crimson-crab-mcp-template

  Ready-to-clone Rust MCP server with chat, token-counting, and model tools for Claude

  Community ai-modelscommunication

• crit

  io.github.crit-labs/crit

  Build, evaluate and serve a bespoke LLM inference engine for your own GPU with crit's commands.

  Community pypistdio ai-models

• ctxfw

  io.github.heuristicolab/ctxfw

  Zero-egress AI Agent Firewall: SARA prompt injection defense, AST context pruning & MCP governance.

  Community pypistdio ai-models

• cursor-mcp

  io.github.qmediat/cursor-mcp

  Cursor's agent (cursor-agent CLI) through MCP: any model your plan offers, resumable sessions.

  Community npmstdio ai-models

• dagpipe

  io.github.devilsfave/dagpipe

  Crash-proof LLM pipelines. Resumes from failure without a database.

  Community pypistdio ai-modelsdatabases

• data-cleaner-agent

  io.github.wesseltl/data-cleaner-agent

  Clean messy CSVs: an LLM picks the steps, tested code does the work. Data untouched by the model.

  Community pypistdio ai-models

• data-profiler-mcp

  io.github.haiiibin/data-profiler-mcp

  Profiles CSV/Parquet/Excel/JSON files: schema, stats, quality flags and dtype tips for LLM agents.

  Community pypistdio ai-modelsfiles

• datamcp — Hosted Model Context Protocol for Databases, APIs, and Agent Memory

  io.github.mironovisa/datamcp

  PostgreSQL, MySQL, OpenAPI/Swagger, and shared Agent Memory with scoped access.

  Community remotestreamable-http databasesmemoryai-models

• datasheet-lens

  io.github.turbyho/datasheet-lens

  Component datasheets (PDF) for LLM agents: index, search, original pages; BOM and CAD checks

  Community pypistdio ai-modelsdocumentssearch

• datoon

  io.github.andrii-su/datoon

  Smart structured-data to TOON gateway: converts to TOON only when it saves LLM tokens.

  Community pypistdio ai-models

• day3

  io.github.Mopra/day3

  Draft email campaigns in day3 from Claude Code, Cursor or VS Code as editable composer blocks.

  Community remotestreamable-http ai-modelsemail

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.