# MCP Thesaurus

> A reference directory of 12,317 Model Context Protocol servers, remote servers, agent skills and loops. Each entry records the tools a server exposes, install commands for around a dozen clients, its licence and transport, its version history, and an audited quality score.

MCP (Model Context Protocol) is an open standard that lets AI assistants call external tools and read external data. An MCP server provides those tools; a client (Claude Code, Cursor, VS Code and others) connects to it.

## Machine-readable access

- Every entry has a Markdown twin: append `.md` to any entry URL, e.g. https://mcpthesaurus.com/servers/<slug>.md
- Every entry has a JSON twin: append `.json` to any entry URL
- Full corpus as JSON: https://mcpthesaurus.com/api/v1/listings
- Longer index of entries: https://mcpthesaurus.com/llms-full.txt

## Main pages

- [MCP servers](https://mcpthesaurus.com/servers): servers that run locally
- [Remote MCP servers](https://mcpthesaurus.com/remote-servers): hosted servers you connect to by URL
- [Agent skills](https://mcpthesaurus.com/skills): portable skill packages for agents
- [Categories](https://mcpthesaurus.com/categories): browse by subject
- [How we score](https://mcpthesaurus.com/score): the published scoring rubric
- [What is an MCP server?](https://mcpthesaurus.com/learn/what-is-an-mcp-server)
- [Local vs remote MCP servers](https://mcpthesaurus.com/learn/local-vs-remote-mcp-servers)
- [MCP server security](https://mcpthesaurus.com/learn/mcp-server-security)
- [JSON API](https://mcpthesaurus.com/docs/api): read the directory programmatically
- [Changelog](https://mcpthesaurus.com/changelog)
- [Submit a server](https://mcpthesaurus.com/submit)
- [Claim a listing](https://mcpthesaurus.com/claim)

## Categories

- [Browser Automation](https://mcpthesaurus.com/categories/browser-automation): 139 entries
- [Web Scraping](https://mcpthesaurus.com/categories/web-scraping): 113 entries
- [Search](https://mcpthesaurus.com/categories/web-search): 721 entries
- [Databases](https://mcpthesaurus.com/categories/databases): 257 entries
- [Version Control](https://mcpthesaurus.com/categories/version-control): 7760 entries
- [DevOps & Deployment](https://mcpthesaurus.com/categories/devops): 196 entries
- [Cloud & Infrastructure](https://mcpthesaurus.com/categories/cloud-infrastructure): 156 entries
- [Monitoring & Observability](https://mcpthesaurus.com/categories/monitoring): 228 entries
- [Communication](https://mcpthesaurus.com/categories/communication): 357 entries
- [Project Management](https://mcpthesaurus.com/categories/project-management): 57 entries
- [Productivity](https://mcpthesaurus.com/categories/productivity): 145 entries
- [Files & Storage](https://mcpthesaurus.com/categories/file-systems): 284 entries
- [AI & Machine Learning](https://mcpthesaurus.com/categories/ai-ml): 2659 entries
- [Data & Analytics](https://mcpthesaurus.com/categories/data-analytics): 248 entries
- [Sales & CRM](https://mcpthesaurus.com/categories/sales-crm): 133 entries
- [Marketing](https://mcpthesaurus.com/categories/marketing): 349 entries
- [E-commerce](https://mcpthesaurus.com/categories/ecommerce): 140 entries
- [Finance & Payments](https://mcpthesaurus.com/categories/finance): 1056 entries
- [Design](https://mcpthesaurus.com/categories/design): 127 entries
- [Media & Content](https://mcpthesaurus.com/categories/media): 471 entries
- [Memory & Knowledge](https://mcpthesaurus.com/categories/memory-knowledge): 439 entries
- [Security](https://mcpthesaurus.com/categories/security): 584 entries
- [Location & Maps](https://mcpthesaurus.com/categories/location-maps): 167 entries
- [Healthcare](https://mcpthesaurus.com/categories/healthcare): 168 entries
- [Legal](https://mcpthesaurus.com/categories/legal): 525 entries
- [Education](https://mcpthesaurus.com/categories/education): 92 entries
- [Gaming](https://mcpthesaurus.com/categories/gaming): 80 entries
- [IoT & Hardware](https://mcpthesaurus.com/categories/iot): 45 entries
- [Developer Tools](https://mcpthesaurus.com/categories/development): 3480 entries
- [Other](https://mcpthesaurus.com/categories/other): 2 entries

## Most referenced entries

- [Doc Coauthoring](https://mcpthesaurus.com/skills/anthropics-doc-coauthoring): Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or 
- [Template Skill](https://mcpthesaurus.com/skills/anthropics-template-skill): Replace with description of the skill and when Claude should use it.
- [Smart Explore](https://mcpthesaurus.com/skills/thedotmack-smart-explore): Token-optimized structural code search using tree-sitter AST parsing. Use instead of reading full files when you need to understand code structure, find functions, or explore a codebase efficiently.
- [browser use](https://mcpthesaurus.com/servers/browser-use-browser-use): Control a real Chrome browser to complete any task: fill forms, extract data, book flights.
- [Mem Search](https://mcpthesaurus.com/skills/thedotmack-mem-search): This skill should be used when the user asks to "search memory", "what do you remember about X", "check claude-mem", "mem search", "find past observations", "what did we do last session", or wants prior-session context about a project, decision, file, or task. Searches the user's Claude-Mem (cmem.ai) memory.
- [How It Works](https://mcpthesaurus.com/skills/thedotmack-how-it-works): Explain how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user asks "how does claude-mem work?" or "what is this thing doing?".
- [Ulw Research](https://mcpthesaurus.com/skills/code-yeongyu-ulw-research): Team-first maximum-saturation research orchestration. ALWAYS asks which final format to render (PDF+DOCX default), then stands up a max-size cooperating team (team_create): one member per axis plus skeptic/red-team members for ultradebate/hyperdebate cross-critique, explore/librarian lanes, live journaling, an EXPAND loop until leads run dry, claims proven by code or the claim-graph gate, and a ci
- [Git Master](https://mcpthesaurus.com/skills/code-yeongyu-git-master): MUST USE whenever a task needs a commit or git-history investigation. Covers atomic commits, staging, commit-message style, rebase, squash, fixup/autosquash, blame, bisect, reflog, git log -S/-G, and questions like who wrote this or when was this added. Do not use for ordinary code edits unless the user asks for git work.
- [Scrapling MCP Server](https://mcpthesaurus.com/servers/d4vinci-scrapling): Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported.
- [Hyperplan](https://mcpthesaurus.com/skills/code-yeongyu-hyperplan): Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of 
- [claude flow](https://mcpthesaurus.com/servers/ruvnet-claude-flow): AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
- [Onboarding](https://mcpthesaurus.com/skills/code-yeongyu-onboarding): Onboarding tour for first-time omo users
- [World Monitor](https://mcpthesaurus.com/remote-servers/app-worldmonitor-mcp): Live markets, conflicts, country risk, chokepoints, energy, and China decision signals. 74 tools.
- [Context7](https://mcpthesaurus.com/servers/upstash-context7): Up-to-date code docs for any prompt
- [labelhead artist momentum](https://mcpthesaurus.com/remote-servers/incorporatedpartners-labelhead-artist-momentum): Trending hip-hop artist momentum scores across four cultural dimensions.
- [Saga Orchestration](https://mcpthesaurus.com/skills/wshobson-saga-orchestration): Implement saga patterns for distributed transactions and cross-aggregate workflows. Use this skill when implementing distributed transactions across microservices where 2PC is unavailable, designing compensating actions for failed order workflows that span inventory, payment, and shipping services, building event-driven saga coordinators for travel booking systems that must roll back hotel, flight
- [Chrome DevTools MCP](https://mcpthesaurus.com/servers/chromedevtools-chrome-devtools-mcp): MCP server for Chrome DevTools
- [Web Component Design](https://mcpthesaurus.com/skills/wshobson-web-component-design): Master React, Vue, and Svelte component patterns including CSS-in-JS, composition strategies, and reusable component architecture. Use when building UI component libraries, designing component APIs, or implementing frontend design systems.
- [Histolab](https://mcpthesaurus.com/skills/k-dense-ai-histolab): Lightweight WSI tile extraction and preprocessing. Use for basic slide processing, tissue detection, tile extraction, and stain normalization for H&E images. Best for simple pipelines, dataset preparation, and quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.
- [Nextflow](https://mcpthesaurus.com/skills/k-dense-ai-nextflow): Build, run, and debug Nextflow data pipelines and nf-core workflows end to end. Use whenever the user mentions Nextflow, nf-core, .nf files, nextflow.config, DSL2, processes/channels/operators, samplesheets, or wants to run a community pipeline (e.g. nf-core/rnaseq, nf-core/sarek), write or test a module/subworkflow with nf-test, configure executors/containers (Docker, Singularity/Apptainer, Conda
- [Architecture Patterns](https://mcpthesaurus.com/skills/wshobson-architecture-patterns): Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design. Use this skill when designing clean architecture for a new microservice, when refactoring a monolith to use bounded contexts, when implementing hexagonal or onion architecture patterns, or when debugging dependency cycles between application layers.
- [Tiledbvcf](https://mcpthesaurus.com/skills/k-dense-ai-tiledbvcf): Efficient storage and retrieval of genomic variant data using TileDB. Scalable VCF/BCF ingestion, incremental sample addition, compressed storage, parallel queries, and export capabilities for population genomics.
- [Threat Mitigation Mapping](https://mcpthesaurus.com/skills/wshobson-threat-mitigation-mapping): Map identified threats to appropriate security controls and mitigations. Use when prioritizing security investments, creating remediation plans, or validating control effectiveness.
- [Codebase Memory](https://mcpthesaurus.com/servers/deusdata-codebase-memory-mcp): Codebase knowledge graph for AI agents — 159 languages, sub-ms queries, 99% fewer tokens.
- [playwright mcp](https://mcpthesaurus.com/servers/microsoft-playwright-mcp): Playwright Tools for MCP
- [tldraw](https://mcpthesaurus.com/remote-servers/tldraw-tldraw): Draw and visually collaborate with your agents on tldraw's canvas.
- [Metabase](https://mcpthesaurus.com/remote-servers/metabase-mcp): Lets AI clients search, explore, query, and visualize data in a Metabase instance.
- [Skyvern](https://mcpthesaurus.com/remote-servers/skyvern-ai-skyvern): AI-powered browser automation — navigate, click, fill forms, and extract data from any website.
- [GitHub](https://mcpthesaurus.com/servers/github-github-mcp-server): Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
- [puter](https://mcpthesaurus.com/remote-servers/puter-mcp-server): Puter MCP enables AI tools to interact with Puter: manage files, websites, workers, and more
- [Planning With Files](https://mcpthesaurus.com/skills/othmanadi-planning-with-files): Persistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.md on disk; lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and emits aggregate counts only; --replay may emit bounded nonce-framed excerpts. O
- [Planning With Files](https://mcpthesaurus.com/skills/othmanadi-planning-with-files-2): Persistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.md on disk; agent instructions read selected project planning context when invoked. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and emits aggregate counts only; --replay may emit bounded nonce-fram
- [Planning With Files](https://mcpthesaurus.com/skills/othmanadi-planning-with-files-3): Persistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.md on disk; Gemini lifecycle hooks inject selected project planning context. Automatic recovery reads project planning files only. Explicit session-catchup.py --metadata reads same-project local agent session records and emits aggregate counts only; --replay may emit bounded nonce-framed exce
- [Reactive Resume](https://mcpthesaurus.com/remote-servers/amruthpillai-reactive-resume): Free open-source resume builder with remote MCP tools for resumes and job applications.
- [Beads](https://mcpthesaurus.com/skills/gastownhall-beads): Use when working in a repository that uses bd or Beads for durable project task tracking, issue dependencies, blocker management, multi-session handoff, or shared work memory. Trigger when the user asks to find ready work, claim or close tasks, create follow-up work, inspect blockers, recover project context, or choose between local planning and persistent project tracking.
- [PostHog MCP Server](https://mcpthesaurus.com/remote-servers/posthog-mcp): Official PostHog MCP Server for product analytics, feature flags, experiments, and more.
- [Snowflake Development](https://mcpthesaurus.com/skills/alirezarezvani-snowflake-development): Use when writing Snowflake SQL, building data pipelines with Dynamic Tables or Streams/Tasks, using Cortex AI functions, creating Cortex Agents, writing Snowpark Python, configuring dbt for Snowflake, or troubleshooting Snowflake errors.
- [Loop Library](https://mcpthesaurus.com/skills/alirezarezvani-loop-library): Discover, find, compare, audit, repair, adapt, and design repeatable AI-agent loops with explicit triggers, actions, verification, stopping conditions, guardrails, and handoffs. Use when a user asks to analyze a codebase for potential loops, mine coding-thread history for work done more than once, turn repeated engineering work into a loop, find or recommend a published loop, create a recurring ag
- [Product Manager Toolkit](https://mcpthesaurus.com/skills/alirezarezvani-product-manager-toolkit): Comprehensive toolkit for product managers including RICE prioritization, customer interview analysis, PRD templates, discovery frameworks, and go-to-market strategies. Use when prioritizing features, synthesizing user research, writing requirement documentation, or developing product strategy.
- [Planning With Files](https://mcpthesaurus.com/skills/othmanadi-planning-with-files-4): Persistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.md on disk; Kiro skill instructions and steering state read selected project planning context. Recovery reads project planning files and their timestamps only, not agent transcript stores. This adapter registers no Stop hook, never requests continuation, and never runs commands declared in Ma

## Notes on the data

- Provenance and paid placement are separate. `Official` and `Verified` are earned and cannot be purchased; `Sponsored` is always a disclosed paid placement and never affects ranking or scoring.
- Entries whose repositories are archived or have had no commits for over a year are labelled as such rather than quietly removed.
- Scores follow a published rubric at https://mcpthesaurus.com/score and every criterion is shown with its pass/fail on the entry page.