"Discover" matching MCP servers:

It lets MCP clients evaluate a single Emacs Lisp form in an already-running Emacs instance through one tool, enabling agents to discover and invoke built-in, package, and user-defined capabilities from the live runtime.

A lightweight FastMCP server that enables language models to discover, clone, transform, and localize PsyFlow task templates through a streamlined workflow with standardized tools.

Aggregates tools from multiple upstream MCP servers and exposes them through 4 meta-tools, enabling LLMs to discover and use hundreds of tools without loading all schemas upfront.

Parselbox is a local, open-source execution layer that turns MCP servers, APIs, shells and host functions into native Python objects. Agents discover capabilities on demand and compose them with code, files, packages and background tasks in one stateful workspace. Powered by Deno and Pyodide.

Enables AI clients such as Claude Desktop, Cursor, and VS Code to connect via SSE and JSON-RPC, discover C# methods as MCP tools, and execute them with generated schemas. It also provides a Blazor WebAssembly inspector for monitoring and testing tool calls.

Serves skill-defined JSON-in/JSON-out scripts as callable tools over MCP stdio, driven by a portable skill-runtime.json manifest that supplies each tool's title, description, and input schema. Exposes commands to validate, list, and run skills, so hosts can discover and invoke agent skills without custom per-skill glue code.

Lets AI clients discover available API operation schemas and write sandboxed JavaScript that chains those operations together, returning only the results they need. Supports stdio and Streamable HTTP transports.

A server that leverages the XMCP framework to discover and execute tools from the src/tools directory, supporting both SSE and STDIO transport methods for interaction.

Enables MCP clients to connect to running Abaqus/CAE windows over multi-port TCP sockets, discover and switch sessions, and execute Python, model, job, ODB, and viewport operations targeted by session_id.

Enables AI coding agents to discover toolchain availability, audit code for stubs, perform fail-closed verification with real compilers and sandboxed tests, and run Qwen-based repair loops before executing or presenting code.

Enables a Grok Bot to reach a local MCP server over loopback to discover eligible projects, start or continue Codex CLI jobs in sandboxed modes, track results, and handle separate OpenAI Responses text requests.

Enables LLMs to dynamically discover and execute tools through a structured skills system. Serves as a documentation hub where skills are defined in directories, allowing progressive loading and interpretation of capabilities.

A lightweight and fast MCP server that enables AI agents to efficiently discover and execute tools through progressive disclosure, minimizing context consumption while supporting safe code execution in external environments.

Enables AI agents to discover, execute, and validate CyberChef operations for data encoding, decoding, encryption, and transformation tasks. Provides structured access to CyberChef's extensive catalog of data manipulation tools through natural language interactions.

Exposes local Python tools via a persistent Streamable HTTP endpoint, allowing an OpenAI Agents SDK notebook to discover and invoke them while using Groq for reasoning and tool selection.

Enables LLM clients to discover, load, and execute markdown skills with bundled scripts over HTTP, featuring progressive disclosure and sandboxed script execution with timeout and stall detection.

A modular platform that enables LLM agents to discover, register, and execute both local tools and tools from external MCP servers, with REST APIs for server management and Streamable HTTP support.

Provides authenticated access to PostgreSQL databases for Claude AI, enabling users to browse database tables, discover schemas, and execute custom SQL queries through natural language interaction.

Enables ChatGPT and other MCP clients to discover writing skills, safely read and edit files in a shared workspace, run background tasks, and delegate work to ChatGPT sub-agents.

MCP server that lets AI agents discover and call R and Python statistical functions without writing code.