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 2941 to 2970 of 3049

• trayd-mcp

  io.github.teamtrayd/trayd-mcp

  Trade Robinhood through natural language in Claude Code.

  Community remotestreamable-http ai-modelstranslation

• trello-mcp-server

  io.github.BillNobill/trello-mcp-server

  Trello Model Context Protocol (MCP) Server for AI Agents

  Community npmstdio ai-modelsproject-management

• tri-train

  com.tri-train/tri-train

  Your triathlon training in Claude: activities, PMC load, plans pushed to Garmin, races, recovery.

  Verified domain remotestreamable-http ai-models

• tribunal

  io.github.thebotclub/tribunal

  Tribunal — Enterprise Claude Code plugin. TDD enforcement, quality gates, vault of rules and agents.

  Community npmstdio ai-models

• triggerfetch

  ai.triggerfetch/triggerfetch

  When a shopper asks ChatGPT, Claude, Gemini or Grok for a product, is yours in the answer?

  Verified domain remotestreamable-http ai-models

• trustai.center pay

  center.trustai.pay/trustai-pay

  Pay-per-use LLM inference for agents: pay in USDC/USDT or per call via x402. 247 chat models.

  Verified domain remotestreamable-http ai-modelscommunication

• truthroute

  io.github.RudrenduPaul/truthroute

  Sends the same prompt to multiple LLM providers in parallel and returns a divergence score via MCP.

  Community npmstdio ai-models

• tuning-engines

  io.github.cerebrixos/tuning-engines

  Domain-specific LLM fine-tuning — sovereign models trained on your data, zero infrastructure.

  Community npmstdio ai-modelsdevops

• tunnel-mcp

  io.github.zachlikefolio/tunnel-mcp

  Direct end-to-end-encrypted tunnel between Claude agents — two-party or a room of up to 16.

  Community npmstdio ai-models

• turbopress Hosting

  de.turbopress/hosting

  Manage turbopress hosting from Claude or ChatGPT: site health, domains, mail, SSL and AI Launch.

  Verified domain remotestreamable-http ai-modelsemailhealth

• tuval-studio

  io.github.ariferol01/tuval-studio

  Tuval Studio MCP: Graphic design, AI design & PDF catalog generator for Claude, Cursor & AI agents.

  Community npmstdio designai-modelsdocuments

• u-he Preset Randomizer

  io.github.Fannon/u-he-preset-randomizer

  Generate, randomize, explain, and manage u-he synthesizer presets via the Model Context Protocol.

  Community npmstdio ai-models

• uimax-mcp

  io.github.prembobby39-gif/uimax-mcp

  Frontend expert for Claude Code. Screenshots, Lighthouse, axe-core, code analysis, auto-fix.

  Community npmstdio ai-models

• uiscanner

  io.github.mishaovcharenko/uiscanner

  Design tokens + a build prompt from any URL, right inside Claude Code, Cursor, and Codex.

  Community npmstdio ai-modelsdesign

• ulup-spaces-mcp

  com.ulupspaces.www/ulup-spaces-mcp

  Create projects, nodes, and tasks in UluP Spaces by conversation with Claude.

  Verified domain remotestreamable-http ai-models

• umbryn-mcp

  io.github.Rinava/umbryn-mcp

  Redacts PII/PHI from text before it reaches an LLM. Fail-closed, self-hosted, no egress.

  Community pypistdio ai-models

• unbounded-consumption-auditor

  io.github.4hmetuyar/unbounded-consumption-auditor

  Scans LLM/agent code for Unbounded Consumption / denial-of-wallet risks (OWASP LLM Top 10 2026 #6)

  Community npmstdio ai-models

• unbounded-consumption-auditor

  io.github.GuardBee/unbounded-consumption-auditor

  Scans LLM/agent code for Unbounded Consumption / denial-of-wallet risks (OWASP LLM Top 10 2026 #6)

  Community npmstdio ai-models

• universalbench

  io.github.nikhilgogulwar/universalbench

  Run code, query databases, call any LLM, and commit to GitHub from your AI, safely. Free tier.

  Community code-executiongitai-models

• urlsnap-mcp

  dev.urlsnap/urlsnap-mcp

  Screenshot, PDF, and markdown extraction from any URL via Claude Desktop and Claude Code.

  Verified domain npmstdio ai-modelsdocumentsimage

• usage-planner

  io.github.ItsOdeLeo/usage-planner

  Plan OpenAI Codex usage from local quota, banked resets and extra-reset forecasts.

  Community npmstdio ai-models

• validatethat-mcp

  io.github.RyanByrne/validatethat-mcp

  Run UX research from Claude — create card sort studies, list studies, pull headline stats.

  Community remotestreamable-http ai-modelsscience

• vallt

  io.github.ptriato/vallt

  API credential manager for Claude Code. Connect services, store keys in keychain, monitor health.

  Community npmstdio ai-modelsapi-integrationecommerce

• vaultit

  io.github.TheRealDataBoss/vaultit

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

  Community pypistdio ai-models

• vaultshell

  io.github.SoWhatI/vaultshell

  Injects secrets into shell commands at exec time; plaintext never reaches the LLM context

  Community ocistdio ai-modelssecurity

• vector-mirror

  io.github.c64dos-png/vector-mirror

  Deterministic SVG perception for LLM agents — measures, never guesses. MCP server.

  Community npmstdio ai-models

• vectora

  io.github.brunosrz/vectora

  AI assistant with RAG, web search, filesystem and memory. MCP sub-agent for Claude Code.

  Community pypistdio ai-modelsfilesmemory

• vectordecisions-mcp-server

  io.github.NikitaDatar/vectordecisions-mcp-server

  AI Governance MCP Server - GATRI trust scoring, kill-switch, EU AI Act compliance for Claude

  Community npmstdio ai-modelslegal

• veida-mcp

  ai.veida/veida-mcp

  Generate AI images from a prompt with no API key, using Veida's anonymous free tier.

  Verified domain npmstdio ai-modelsapi-integrationimage

• veldo

  io.github.thisisnotinsideout-byte/veldo

  Keeps a current picture of your startup so Claude can give your best next move and why.

  Community remotestreamable-http 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.