"Y Combinator" matching MCP servers:

Enables MCP clients to execute Python code directly via stdin, preserving quotes, f-strings, and backslashes exactly as written, and returns stdout, stderr, and exit codes.

Provides direct, unsandboxed local machine access via filesystem, Python, Node.js, and shell commands for MCP agents.

Enables Claude to generate executable test cases from decision tables in CSV, JSON, or Markdown formats. Provides intelligent test planning guidance and generates Playwright/API test code with TypeScript support.

A Model Context Protocol server built with FastMCP that enables dynamic tool loading and configuration from individual Python files. It provides a flexible framework for automatically discovering, testing, and running tools via Stdio or HTTP transport modes.

Join your computers and your friends' to run large open AI models, reuse shared code, and run sandboxed jobs on a community network — from Claude Code, Cursor or any MCP client (npx -y bitpull mcp).

This read-only MCP Server allows you to connect to Apache Cassandra data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).

This read-only MCP Server allows you to connect to Oracle data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).

Enables AI assistants to execute R code, create visualizations, analyze data, and manage packages through a local Rscript CLI.

A basic MCP server that implements a calculate tool for arithmetic operations (add, subtract, multiply, divide). It handles requests via stdio.

Enables schema-validated, sandboxed access to 34 Python-powered tools across Pillow, requests, pypdf, pandas, openpyxl, and python-docx, plus an autonomous ReAct converter agent that can grow the catalog by requirement and self-repair at runtime. It also provides a control console and hardened Docker deployment for secure MCP client integration.

A local MCP server that connects Claude Desktop to execute custom local code, such as generating custom greetings.

An extensible TypeScript-based MCP server designed for Claude Code with a modular architecture for easily adding custom tools. It includes built-in examples like a calculator and echo tool, utilizing Zod for robust input validation and error handling.

Turns any YAML manifest into a fully-functional MCP server without hosting infrastructure, enabling custom tools, resources, and prompts via declarative configuration.

This read-only MCP Server allows you to connect to Stripe data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).

Enables compatible MCP AI tools to read, write, design windows, and run programs in the E-Language IDE.

A Python template for building Model Context Protocol (MCP) servers that expose tools via JSON-RPC, enabling secure and scalable context and tool invocation for language models.

A self-hosted MCP server that enables AI coding agents to read, edit, search, and run code in local projects with human review loops and policy controls.

This read-only MCP Server allows you to connect to Google BigQuery data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).

Enables asynchronous and parallel execution of Claude Code tasks across multiple sessions, allowing users to start background tasks and continue working immediately without blocking.

Enables AI assistants to build, test, and balance PICO-8 games through headless simulation, screenshots, and authoring of sprites, sound effects, and music.

A Model Context Protocol server built with FastMCP that features dynamic tool loading and modular management via a dedicated tool directory. It supports both stdio and HTTP transport modes, enabling efficient development and deployment of custom MCP tools.

A Model Context Protocol implementation that plays sound effects (completion, error, notification) for Cursor AI and other MCP-compatible environments, providing audio feedback for a more interactive coding experience.

Enables agents to accomplish multi-step work by writing a single sandboxed JavaScript program that drives shell, filesystem, HTTP, and every tool of any configured MCP server, returning only a small summary instead of raw JSON. This collapses dozens of advertised tool schemas into one tool, cutting per-request context by roughly 26× while keeping disabled upstream servers reachable.

Enables AI agents to write, validate, and render high-quality PostScript by providing operator lookup, vetted PSlib fragments, cited reference search, and Ghostscript-based checking.

Provides agents with real Linux VMs to run commands, manage files, expose ports, and track costs, all through an ephemeral sandbox service.

Enables AI assistants to create and modify Google Apps Script projects, manage versions and deployments, run functions, and inspect execution history through natural language.

Enables AI assistants to read, edit, and execute Jupyter notebook files (.ipynb) with live kernel output, without requiring JupyterLab.

Gives AI assistants a genuine Borland Turbo C 3.0 toolchain via MCP, enabling compile and run of real 16-bit DOS C programs with diagnostics and classic examples.

Enables Gemini-powered multimodal analysis (video, audio, image, documents), Google search, and code execution via the API易 service. Supports Docker deployment and flexible configuration.

Enables MCP-compatible apps to expose a folder of RAPP agent.py files as callable tools, deriving each tool's schema from its metadata and running calls in isolated, timed processes.

Enables basic arithmetic operations (addition, subtraction, multiplication, division) with 64-bit precision and matrix multiplication capabilities. Provides mathematical computation tools for AI assistants through the Model Context Protocol.

A starter project for rapidly developing Model Context Protocol (MCP) servers using the TypeScript SDK and Zod schema validation. It includes example implementations for tools and resources to streamline the creation of custom MCP integrations.

Wraps MiniMax AI as an autonomous code executor for Claude Code, offloading coding tasks to save Claude subscription tokens.

A foundational project for quickly developing Model Context Protocol servers using the TypeScript SDK and Zod for schema validation. It features pre-implemented examples for tools like a calculator and greeting service, along with templates for managing dynamic resources.

Provides a secure, sandboxed interface for LLM agents to interact with HPC clusters via bubblewrap isolation, managing workspaces and executing commands locally or through Slurm.

Enables controlling OriginLab Origin through MCP to read and write worksheets, build and style multi-panel graphs, and export figures, reporting what Origin actually did rather than what it was asked to do. Works from macOS or Linux against Origin running in a Windows VM.

A Model Context Protocol server for time manipulation tasks, enabling AI models to get the current date/time and calculate duration between timestamps.

Enables an MCP client to guide users through 12 stages of game creation, from concept to launch, by managing decisions, recommending skills, and generating playable HTML5 prototypes, GDDs, and backlogs.

Enables AI assistants to inspect, refactor, lint, run, and version Power Query (M) queries in Excel workbooks and Power BI projects, with snapshot safety and live evaluation.

econ-r-mcp is a local MCP server plus companion skill for reproducible applied econometrics and statistics workflows powered by headless R execution.