MCP server directory

> [!CAUTION] > This repository was archived on July 21, 2025. The Atla API is no longer active. An MCP server implementation providing a standardized interface for LLMs to interact with the Atla API for state-of-the-art LLMJ evaluation. > Learn more about Atla here. Learn more about the Model Context Protocol here. - evaluate_llm_response: Evaluate an LLM's response to a prompt using a given evaluation criteria. This function uses an Atla evaluation model under the hood to return a dictionary containing a score for the model's response and a textual critique containing feedback on the model's response. - evaluate_llm_response_on_multiple_criteria: Evaluate an LLM's response to a prompt across _multiple_ evaluation criteria. This function uses an Atla evaluation model under the hood to return a list of dictionaries, each containing an evaluation score and critique for a given criteria.

2 tools · evaluate_llm_response, evaluate_llm_response_on_multiple_criteria

Claude KVM is an MCP tool that controls remote desktop environments over VNC. It consists of a thin JS proxy layer (MCP server) and a platform-native Swift VNC daemon running on your macOS system. > [!TIP] > Phantom-WG could be a great alternative for you. Isolate your VNC server within your own network while enjoying self-hosted VPN performance with the extra privacy features you gain along the way. - Integration Test - Mac Integration Test - Mac Calculator Test - Mac Scientific Calculator Test - Mac Safari Browsing Test - Mac Drag & Drop Test - Mac Chess Test - Mac Chess Direct Test - Mac Phantom-WG Install Test

5 tools · configure, detect_elements

A Model Context Protocol (MCP) proxy server that translates tool calls into TypeScript code generation. Instead of making multiple tool calls back and forth, LLMs can write TypeScript code that calls multiple tools naturally, reducing token overhead and leveraging the LLM's superior code generation capabilities. LLMs make multiple sequential tool calls, burning tokens and struggling with complex workflows: - ❌ Multiple round-trips between LLM and tools - ❌ Complex tool calling sequences are error-prone - ❌ Data cannot easily be passed between tools - ❌ Limited error handling and control flow

5 tools · generate_and_execute_code, get_tool_definitions

A Model Context Protocol server for Scrapezy that enables AI models to extract structured data from websites. - extract_structured_data - Extract structured data from a website - Takes URL and prompt as required parameters - Returns structured data extracted from the website based on the prompt - The prompt should clearly describe what data to extract from the website To install Scrapezy MCP Server for Claude Desktop automatically via Smithery: There are two ways to provide your Scrapezy API key: 1. Environment Variable: bash export SCRAPEZY_API_KEY=your_api_key npx @scrapezy/mcp

3 tools · extract_structured_data, Integrate web extraction into AI workflows

Riza offers an isolated code interpreter for your LLM-generated code. Our MCP server implementation wraps the Riza API and presents endpoints as individual tools. Configure with Claude Desktop as below, or adapt as necessary for your MCP client. Get a free Riza API key in your Riza Dashboard. The Riza MCP server provides several tools to your LLM: - create_tool: Your LLM can write code and save it as a tool using the Riza Tools API. It can then execute these tools securely on Riza using execute_tool. - fetch_tool: Your LLM can fetch saved Riza tools, including source code, which can be useful for editing tools. - execute_tool: Executes a saved tool securely on Riza's code interpreter API. - edit_tool: Edits an existing saved tool. - list_tools: Lists available saved tools. - execute_code: Executes arbitrary code safely on Riza's code interpreter API, without saving it as a tool.

5 tools · create_tool, edit_tool

A Model Context Protocol (MCP) server that provides tools to interact with Powerdrill datasets, authenticated with Powerdrill User ID and Project API Key. Please go to https://chat.powerdrill.ai/ for AI data analysis individually or use with your Team. If you have the Powerdrill User ID and Project API Key of your Team, you can manipulate the data via Powerdrill open sourced web clients: - Node.js edtion: https://flow.powerdrill.ai/, or play with the open source web client https://github.com/powerdrillai/powerdrill-flow. - Python edtion: https://powerdrill-flow.streamlit.app/, or play with the open source web client https://github.com/powerdrillai/powerdrill-flow-streamlit.

6 tools · mcp_powerdrill_create_data_source_from_local_file, mcp_powerdrill_create_dataset

这是一个基于 ALAPI 的 MCP (Model Context Protocol) 服务器实现，可以通过MCP协议直接调用ALAPI的接口，轻松将ALAPI丰富的API资源集成到各类支持MCP的AI应用中。 - 🔍 丰富API资源 - 提供IP查询、天气查询、热搜榜单、企业信息等100+种常用API服务 - 🧩 MCP 协议支持 - 完全兼容 Model Context Protocol，轻松集成到各类AI应用 - 🔄 自动加载 - 自动加载 ALAPI OpenAPI 规范，无需手动配置 - 🎯 灵活调用 - 支持加载全部或指定API，按需使用（短视频解析、天气查询、每天60秒读懂世界、企业查询等） - 🛡️ 统一响应 - 提供统一的错误处理和响应格式，简化开发流程 - ⚙️ 可配置性 - 支持环境变量配置，轻松适应不同使用场景 ALAPI MCP Server 设计为与支持 MCP 协议的客户端配合使用，不支持独立的命令行配置。请按照以下步骤在您的 MCP 客户端中配置使用： 通过 Smithery 安装 ALAPI MCP Server，适用于 Claude Desktop 客户端：

6 tools · Company verification, Content moderation

A tool to manage Ephemeral Environments on the Shipyard platform. - Linux and macOS curl https://www.shipyard.sh/install.sh | bash - Windows Navigate to the releases page and download the executable for Windows. - Homebrew brew tap shipyard/tap brew install shipyard Run shipyard login to initialize the CLI. This will prompt you to log in to Shipyard in the browser. The CLI will then save your API token in a local config. You're ready to start running commands. Set your Shipyard API token as the value of the SHIPYARD_API_TOKEN environment variable.

6 tools · get_environment, get_environments

> [!WARNING] > This repository is deprecated and no longer maintained. > > Scorable now runs a hosted remote MCP server at https://api.scorable.ai/mcp. It needs no > installation, no local process, and no container, and it tracks the platform automatically. > > bash > claude mcp add --transport http scorable https://api.scorable.ai/mcp \ > --header "Authorization: Bearer $SCORABLE_API_KEY" > > > The hosted server covers everything this one did and more: alongside running evaluators and > judges it can list, create, and update them, generate a judge from a plain-language > description, and query past execution logs — 14 tools in total. It also scores whole > conversations, not just single request/response pairs. > > See the MCP Server documentation for > install instructions for Claude Code, Codex, Cursor, and other clients. > > This repository stays available for anyone who specifically needs a stdio transport or wants > to run the MCP layer inside their own network, but it will not re

6 tools · list_evaluators, list_judges

The Globus MCP Server enables LLM applications to interact with Globus services. - globus_transfer_list_endpoints_and_collections - List endpoints and collections the user has access to - globus_transfer_search_endpoints_and_collections - Use a filter string to search all endpoints and collections that are visible to the user - globus_transfer_submit_task - Submit a transfer task between two collections - globus_transfer_get_task_events - Get a list of task events - globus_transfer_list_directory - List contents of a directory on a collection

6 tools · globus_compute_get_task_status, globus_compute_register_python_function

> [!IMPORTANT] > This project has been archived. It was built to address the lack of browser control in AI agents such as Claude and Codex, but the agents now have these functions built in without the need for a dedicated MCP based solution. YetiBrowser MCP is a fully open-source implementation of the Browser MCP workflow. It links a Node-based MCP server with Chrome/Firefox extensions so Model Context Protocol clients—Codex/Claude Code, Cursor, Windsurf, MCP Inspector, or your own tools—can automate a real browser tab while keeping every byte on your machine and auditable.

5 tools · browser_evaluate, browser_fill_form

A Model Context Protocol (MCP) server implementation for enabling agents to access observability insights using Digma for code observability and dynamic code analysis 🗣️ Observability-assisted code reviews: Check the PR branch for any issues discovered by pre-prod observability. 🔎 Find code inefficiencies with dynamic code analysis: Identify issues in the code/queries that are slowing the app down 🔭 Utilize code runtime usage data from distributed tracing: Check for breaking changes or generated relevant tests

5 tools · Assess impact of changing a function, Check for new issues in a specific environment

- MacOS/Linux: curl -LsSf https://astral.sh/uv/install.sh | sh - Windows: powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex" 1. Download Claude Desktop. 2. Launch Claude and go to Settings > Developer > Edit Config. 3. Modify claude_desktop_config.json with: json { "mcpServers": { "Adfin": { "command": "<home_path>/.local/bin/uv", "args": [ "--directory", "<absolute_path_to_adfin_mcp_folder>", "run", "main_adfin_mcp.py" ], "env": { "ADFIN_EMAIL": "<email>", "ADFIN_PASSWORD": "<password>" } }, "filesystem": { "command": "<home_path>/.local/bin/uv", "args": [ "--directory", "<absolute_path_to_adfin_mcp_folder>", "run", "filesystem.py" ] } } } 4. Relaunch Claude Desktop.

3 tools · Check credit control status, Create a new invoice

tidal-cli wraps the Tidal API v2 into a single command-line tool. Search the catalog, manage playlists, explore artists, play tracks, and handle your library — all without opening a browser. Every command supports --json output, making it the backbone for LLM agent automation through OpenClaw. - Search artists, albums, tracks, videos, playlists, and autocomplete suggestions - Artists — info, top tracks, discography, similar artists, radio - Albums — details, barcode lookup - Tracks — info, similar tracks, ISRC lookup, radio - Playlists — full CRUD, add/remove tracks, reorder, add entire albums - Library — favorites for artists, albums, tracks, videos, playlists - Playback — stream info, direct URLs, local playback via DASH - Recommendations — personalized mixes (Daily, Discovery, New Release, Offline) with drill-down into mix items - History — recently added tracks, albums, artists; search history (list, delete, clear) - Save for Later — bookmark items in a separate queue from your mai

6 tools · artist, Control your library

Run containerized workloads across AWS, GCP, Azure, OCI, and your own hardware under one API. It loads Control Plane's domain knowledge, production guardrails, and live MCP tools into Claude Code, Codex, and Antigravity CLI so your assistant can deploy, troubleshoot, secure, and migrate workloads with verified cpln commands. Update with /plugin marketplace update controlplane then /reload-plugins (third-party marketplaces don't auto-update unless you enable it in /plugin → Marketplaces). Alternatively, install from Anthropic's community plugin marketplace, where every listing has passed Anthropic's review:

5 tools · Configure networking and TLS, Deploy a workload from Kubernetes manifests

Model Context Protocol (MCP) is a new, standardized protocol for managing context between large language models (LLMs) and external systems. This repository provides comprehensive MCP servers for Cloudinary's media management platform, enabling you to use natural language to upload, transform, analyze, and organize your media assets directly from AI applications like Cursor and Claude. With these MCP servers, you can seamlessly manage your entire media workflow through conversational AI - from uploading and transforming images and videos, to configuring automated processing pipelines, analyzing content with AI-powered tools, and organizing assets with structured metadata. Whether you're building media-rich applications, managing large asset libraries, or automating content workflows, these servers provide direct access to Cloudinary's full suite of media optimization and management capabilities.

6 tools · Build workflow automations, Configure environment settings

> For Your Intelligence. The FYI your agent needs before it acts. Fathom is an MCP server that gives AI agents financial reality awareness before they make consequential decisions. The problem: Every AI agent operating in crypto today is blind. Trading bots see prices but don't understand context. DeFi agents deploy capital without knowing where we are in the cycle. Treasury managers make decisions without macro awareness. They have data but no understanding. The solution: Fathom synthesizes 8 real-time data sources into interpreted intelligence — regime classification, cycle positioning, sentiment state, DeFi health, macro context, and on-chain signals — delivered as plain English guidance an agent can act on immediately.

6 tools · get_asset_context, get_macro_context

[![NPM Version][npm-shield]][npm-url] [![Contributors][contributors-shield]][contributors-url] [![Forks][forks-shield]][forks-url] [![Stargazers][stars-shield]][stars-url] [![Issues][issues-shield]][issues-url] [![MIT License][license-shield]][license-url] [![Discord][discord-shield]][discord-url] > Transform your content operations with AI-powered tools for Kontent.ai. Create, manage, and explore your structured content through natural language conversations in your favorite AI-enabled editor. Kontent.ai MCP Server implements the Model Context Protocol to connect your Kontent.ai projects with AI tools like Claude, Cursor, and VS Code. It enables AI models to understand your content structure and perform operations through natural language instructions.

5 tools · Administer environment settings, Control publishing and workflows

Give your AI agent a Bitcoin wallet. MCP server + CLI. Works with Claude Code, OpenClaw, Cursor, and any agent framework. - update_operator tool / lw set-email - set your operator email from the MCP client or CLI; a verification link is emailed to you. - claim_promo tool / lw claim-promo - claim the free-sats install promo directly from your agent. Requirements: verified email + operator account at least 3 hours old. - get_info works before registration - service info no longer requires an API key.

6 tools · create_agent, keysend

> A Model Context Protocol (MCP) server for Kubernetes cluster management with ArgoCD and GitLab integration. This repository contains the Claude Kubernetes MCP (Model Context Protocol) server, built in Go. The server integrates with ArgoCD, GitLab, Claude AI, and Kubernetes to enable advanced control and automation of Kubernetes environments. - Overview - Prerequisites - Setup Instructions - Configuration - Running Locally - Building and Running with Docker - Production Deployment - API Documentation - Postman Collection - License

6 tools · Get resource details, List ArgoCD applications

A Model Context Protocol (MCP) integration for managing content in the DevHub CMS system. You will need the uv package manager installed on your local system. To use this server with the Claude Desktop app, add the following configuration to the "mcpServers" section of your claude_desktop_config.json: After updating the config, restart Claude Desktop. This MCP can also be used in cursor with a similar configuration from above added to your Cursor global environment or to individual projects. Claude Code's command line supports MCP installs.

5 tools · create_blog_post, get_businesses

URnetwork is a decentralized privacy network. It's designed to keep users anonymous by default and give them access to all the content in the world. Humans use the apps (Android, iOS, Chrome). Agents use the API and MCP skills: - The API spec is at: https://github.com/urnetwork/connect/blob/main/api/bringyour.yml - The API is hosted at: https://api.bringyour.com - The MCP server is hosted at: https://mcp.bringyour.com Agents should consider the guidance below when using the API and MCP server. The API and the MCP server authenticate differently. Use the right one for the surface you are calling.

Reexpress MCP Server is a drop-in solution to add state-of-the-art statistical verification to your complex LLM pipelines, as well as your everyday use of LLMs for search and QA for software development and data science settings. It's the first reliable, statistically robust AI second opinion for your AI workflows. Simply install the MCP server and then add the Reexpress prompt to the end of your chat text. The tool-calling LLM (e.g., Anthropic's LLM model Claude Opus 4.7) will then check its response with the provided pre-trained Reexpress Similarity-Distance-Magnitude (SDM) estimator, which ensembles gpt-5.5-2026-04-23, gemini-3.1-pro-preview, and gemini-embedding-2, along with the output from the tool-calling LLM, and calculates a robust estimate of the predictive uncertainty against a database of training and calibration examples from the OpenVerification1 dataset. Unique to the Reexpress method, you can easily adapt the model to your tasks: Simply call the ReexpressAddTrue or Reex

4 tools · Add a false example to the model, Add a true example to the model

Mezmo MCP is a remote Model Context Protocol (MCP) server that lets AI assistants and IDE chat agents interact with the Mezmo observability platform via the Model Context Protocol. Use it for streamlined observability, log analysis, and root-cause analysis in your favorite tools. - 🕵️ Run advanced Root-cause analysis over recent logs - 📦 List and describe Pipelines - 📤 Export and filter Logs with powerful query syntax Mezmo MCP is a remote MCP server that connects AI assistants and IDE chat to Mezmo so you can run advanced root-cause analysis, discover pipelines, and export logs without hosting anything yourself. It's built for observability use cases and works across many popular MCP clients.

3 tools · export_logs, list_pipelines

An MCP (Model Context Protocol) server that gives AI assistants on-demand access to the complete amCharts 5 knowledge base: 140+ documentation pages, 280+ code examples, and 1,000+ class API references. Works with Claude Code, Claude Desktop, Cursor, Windsurf, VS Code + GitHub Copilot, and any other MCP-compatible AI tool. Instead of loading the entire amCharts reference into the AI's context window, the MCP server lets the AI query exactly what it needs — a specific chart type reference, a code example, or an API lookup. This means better answers with less context waste.

5 tools · get_chart_reference, get_example

Allyson MCP Server - AI-powered animation generator that transforms static files into animated SVG components using the Model Context Protocol (MCP). Options: --api-key <key> Your Allyson API key (required) --help Show help message Examples: allyson-mcp --api-key your-api-key-here API_KEY=your-key allyson-mcp You can also set your API key as an environment variable: - AI-Powered Animation Generation: Transform static images into animated SVG components - MCP Protocol Compatible: Works with any MCP-compatible AI assistant or tool - File Upload Support: Supports various image formats (PNG, JPG, SVG, etc.) - Custom Animation Prompts: Describe exactly what animation you want - Local File Processing: Reads files from your local filesystem - Automatic Output Generation: Saves animated components to specified paths

3 tools · Create custom motion effects from images, generate_svg_animation

A Model Context Protocol (MCP) server for connecting AI tools to the Dovetail API. - Node.js 22 or higher (download Node from nodejs.org) - A Dovetail API token (see Dovetail API Documentation for details on obtaining one) 1. Download the latest index.js here 2. Head over to configuration to continue 1. Clone the repository: bash git clone https://github.com/dovetail/dovetail-mcp.git cd dovetail-mcp 2. Install dependencies: bash yarn install 4. Locate and copy the dist/index.js filepath (this will copy the path to your clipboard for the configuration step): bash realpath dist/index.js | pbcopy

3 tools · Access project data, Integrate with AI assistants

Every AI conversation starts from zero. You repeat yourself to every agent — your name, your preferences, your allergies, your tech stack. Chat history is siloed per app. There's no portable memory layer. Epitome fixes this. One database that every AI agent shares, so they all remember you. 1. Sign up at epitome.fyi 2. Go to Settings → API Keys and copy your MCP URL 3. Connect an AI agent — done Open localhost:5173 and sign in with Google or GitHub OAuth. Get your API key from Settings → API Keys in the dashboard (hosted or self-hosted).

3 tools · memorize, recall

The Tunetank music & sound‑effects catalog as an MCP server — so any AI assistant (Claude, ChatGPT, Cursor, …) can find the right royalty‑free track or SFX for a video, ad, podcast or stream. Ask things like “find an energetic rock track around 60 seconds for a YouTube intro” or “a whoosh SFX under 2 seconds” and the assistant searches Tunetank's real catalog and hands back a preview link plus the track page on tunetank.com. - 🎵 Search music by mood, genre, theme, artist, name and target length (± tolerance) - 🔊 Search sound effects (SFX) by category and length - 📚 Browse genres, moods, themes and curated playlists - ▶️ Every result includes an audio preview URL and the canonical track page (https://tunetank.com/track/<id>-<slug>/) - 🆓 Completely free — no API key, no auth, no rate‑limit sign‑up. Read‑only.

5 tools · duration, list_genres

Control plane for autonomous software labor. Planwright is the objective-native planning board for agent-led software development. Humans define outcomes at the Objective layer; coding agents (Claude Code, Cursor, Codex, and others) claim work, decompose tasks, execute, and report back via native MCP—with every state change captured in a hash-chained, Ed25519-signed audit trail. Your browser opens for GitHub login. That's it. See the full agent setup guides for Cursor, Codex, Claude Desktop, and generic MCP clients.

6 tools · planwright_check_alignment, planwright_claim_objective

This repository provides a Model Context Protocol (MCP) Server for validating OpenAPI specifications using APIMatic. The server processes OpenAPI files and returns validation summaries by leveraging APIMatic’s API. - Validates OpenAPI 2.0 and 3.0 files - Uses APIMatic’s API for comprehensive validation - Supports both JSON and YAML formats - Implements Model Context Protocol (MCP) for seamless integration To use the server, an APIMatic API key is required. Sign up at APIMatic and obtain the API key.

3 tools · Check an API definition before implementation, Get a structured validation report

Work on dataset metadata with MLCommons Croissant validation and creation.

A Model Context Protocol (MCP) server for integrating VISO TRUST API capabilities with AI assistants. VISO TRUST hosts a managed instance of this MCP server, so you don't need to build, run, or self-host anything to get started: Connect any MCP client to this endpoint using the Streamable HTTP transport and authenticate with your VISO TRUST API token. For information on how to generate an API token, see the VISO TRUST support documentation. Example client configuration: json { "mcpServers": { "viso-mcp": { "type": "streamable-http", "url": "https://mcp.visotrust.com/mcp", "headers": { "Authorization": "Bearer <your-api-token>" } } } }

6 tools · create_assessment, create_bitsight_intelligence_report

MCP (Model Context Protocol) server for the Chia Health telehealth prescription platform. Enables AI assistants (ChatGPT, Claude, Gemini, OpenClaw, Copilot, and custom agents) to help patients browse medications, complete medical intake, sign consent documents, place orders, pay, and manage their treatment — all through natural conversation. Available treatments include GLP-1 medications (semaglutide, tirzepatide including tablets), peptide therapies (sermorelin, NAD+, glutathione), and longevity programs. All prescriptions are evaluated by licensed US healthcare providers and delivered from FDA-regulated 503A compounding pharmacies across all 50 US states + DC.

6 tools · Browse medications and check eligibility, Complete medical intake

Model Context Protocol (MCP) server for Capital.com Open API - enabling LLM-driven access to your Capital.com trading account. Your use of the Capital.com Public API and any third-party tools, including AI/LLM-based tools, is at your own risk. Capital.com is execution-only and does not endorse or take responsibility for third-party software or its outcomes. Nothing here is investment advice. You are solely responsible for your trading decisions, including any price differences arising from latency introduced by third-party tools, and must comply with applicable terms and laws.

6 tools · cap_market_search, cap_session_status

Dynamically search and call tools using UnifAI Network