MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
—
oci MIT ★ 16 -
—
★ 4 -
Code Interpreter MCP Server - Secure code execution via E2B on Function Compute
pypi MIT -
MCP server for AWS Bedrock AgentCore CodeInterpreter
npm MIT -
Code Interpreter MCP server on basis of WASM/pyodide with support for searching a shared library of code snippets
MIT ★ 1 -
code-interpreter-agent MCP server by Nova (CIVAI), remote Streamable HTTP
MIT -
@watermelonpm/greennode-code-interpreter-mcpgithub.com/greennodehub/greennode-code-interpreter-mcpactive
MCP server exposing a remote code-interpreter sandbox (execute code, run commands, read/write files) over stdio. One sandbox session per agent session.
npm Apache-2.0 -
code-interpretergithub.com/thehapyone/code-interpreterupdated this year
An open-source MCP server providing notebook-like code execution with session affinity, multi-language support, and session-scoped file storage.
MIT ★ 6 -
MCP Python Interpreter: run python code. Python-mcp-server, mcp-python-server, Code Executor
pypi NOASSERTION ★ 104 -
jupyter-interpreter-mcpgithub.com/lmseidler/jupyter-interpreter-mcpupdated this year
Serving access to a JupyterHub as code interpreter sandbox for LLMs using MCP.
MIT -
CodeBoxMCPgithub.com/MadhanMohanReddy2301/CodeBoxMCPupdated this year
Code Box is a self-hosted, open-source Model Context Protocol (MCP) server that provides AI agents with a secure, stateful environment to execute Python and JavaScript code. It acts as a direct, zero-cost replacement for Azure Assistants Code Interpreter by persisting variables across calls, and safely executing read-only SQL querys
MIT -
ostructgithub.com/yaniv-golan/ostructupdated this year
Schema-first AI analysis CLI that transforms messy data into structured insights. Define your output format, get guaranteed JSON results from any source. Combines OpenAI models with multi-tool orchestration (Code Interpreter, File Search, Web Search, MCP) for AI-powered data synthesis.
NOASSERTION ★ 8 -
js code interpreter MCP server
MIT -
A secure and sandboxed python code interpreter for LLMs. Accessable via MCP, or directly in code
pypi MIT -
A Model Context Protocol (MCP) server that gives an LLM a way to interact with a Python code interpreter
-
Run Python from an MCP client without a shell mangling your code. Code goes to the interpreter over stdin, so nested quotes, f-strings and backslashes survive verbatim.
Apache-2.0 -
prompaticgithub.com/cppis/prompt-lensupdated this year
Prompatic — AI prompt analysis MCP server for Claude Desktop & Claude Code. Shows how AI reads your prompts with 5-axis scoring and 3-color interpretation reports.
npm MIT -
Ba Zi, Jyotish, Human Design and more: Python calculators on Swiss Ephemeris, skills for LLM agents, an MCP server and a local web UI. The code computes, the model only interprets. Docs and output in Russian.
AGPL-3.0 -
aws-bedrock-agentcore-support-agentgithub.com/HosniBelfeki/aws-bedrock-agentcore-support-agentactive
AI customer support agent on Amazon Bedrock AgentCore and the Strands SDK: MCP Gateway tools, Knowledge Base RAG, cross-session memory, Code Interpreter and Browser.
-
Multi-capability AI customer support agent built with Amazon Bedrock AgentCore, Strands Agents, MCP, RAG, Memory, Code Interpreter, Browser, Lambda, and API Gateway.
-
AI customer support agent on Amazon Bedrock AgentCore — MCP Gateway tools (Lambda), RAG Knowledge Base, cross-session Memory, Code Interpreter & Browser. Strands SDK + Nova 2 Lite
NOASSERTION -
ParcelPilot: customer support agent on Amazon Bedrock AgentCore built with Strands Agents. Tracks orders and processes refunds through an MCP Gateway to Lambda, answers from a Bedrock Knowledge Base, remembers customers with AgentCore Memory, computes loyalty discounts in Code Interpreter, browses live pages, and alarms on errors in CloudWatch.
NOASSERTION -
magiclane-mcp-serverno update data
The Magic Lane Model Context Protocol (MCP) Server enables any AI agent or application to become a geospatially intelligent assistant, capable of acting as a reliable companion for pedestrians, cyclists, and drivers alike. Built on top of Magic Lane's advanced mapping and routing technology, this TypeScript-based MCP server empowers AI agents to: - Understand and process geospatial data - Interpret user intent in a spatial context - Deliver accurate, contextually relevant navigation guidance By leveraging Magic Lane's global map data and real-time geospatial intelligence, the MCP Server enables deeply personalized navigation and trip-planning experiences through core tools: - Intelligent Search: find addresses, points of interest (POIs), or coordinates with intelligent search capabilities and POI category filtering. - Smart Routing: generate optimized routes between multiple waypoints with support for various transport modes, route preferences, and dynamic POI integration. - Round Trip Planning: create circular routes that start and end at the same location, perfect for jogging routes, cycling loops, or delivery runs. - Reverse Geocoding: convert geographic coordinates into detailed address information including street name, city, state, country, and postal code. - Isochrone Analysis: calculate reachability polygons showing areas accessible within specific time or distance constraints. - Route Visualization: create visual map images of calculated routes, isochrones, and round trips for immediate geographical context and presentation. - Geofence Management: create, manage, and query geographic boundaries for asset monitoring, location-based alerts, and spatial analysis with support for polygons, circles, and rectangles. - Interactive Map: Display an interactive vector tile map directly inside the conversation using MapLibre GL JS and MagicLane vector tiles. Supports location views, route visualization, isochrone overlays, round trip routes, search result markers, geofence areas, and custom coordinate paths — with one or many overlays per map and pan/zoom interactions. The map functionalities can be visualized as high-quality map images through our new beta feature to generate custom map views with markers, bounding boxes, or location-centered areas without route calculation, complementing route visualization for routes, isochrones, and round trips. Together, these capabilities enable AI agents to act as true geospatial copilots - understanding spatial context, anticipating user needs, and optimizing every journey with precision and ease.
smithery -
MCP server for Python code execution and environment management
pypi MIT License -
Python-Runtime-Interpreter-MCP-Servergithub.com/hileamlakB/Python-Runtime-Interpreter-MCP-Serverstale
PRIMS is a lightweight, open-source Model Context Protocol (MCP) server that lets LLM agents safely execute arbitrary Python code in a secure, throw-away sandbox.
MIT ★ 30 -
@crownest/mcpgithub.com/crownest-dev/crownestupdated this year
MCP stdio server for CrowNest cloud sandboxes.
npm Apache-2.0 -
A Roslyn-based mcp server for dynamically executing C# code snippets
★ 3 -
smart-e2bstale
A smart MCP server that integrates E2B for code execution in the cloud
npm MIT -
mcp-run-python-code: MCP server for running Python code, installing packages, and executing Python files.
pypi Apache License 2.0 -
py4agent-mcpupdated this year
MCP (Model Context Protocol) Server for py4agent - Provides code execution capabilities through Jupyter kernels
pypi -
PostScript for precision and imagination. A modern PostScript interpreter in Rust for precise document rendering and expressive generative art. PNG, SVG, PDF, WASM, and MCP.
npm Apache-2.0 ★ 2 -
ipyboxgithub.com/gradion-ai/ipyboxupdated this year
Unified execution environment for Python code, shell commands, and programmatic MCP tool calls.
pypi Apache-2.0 ★ 76 -
Terse — an AI-native code language: a machine-designed, token-dense format for AI coding agents. Open source, Apache-2.0.
Apache-2.0 ★ 1 -
Extend what your machine can really compute, within limits you control.
Apache-2.0 ★ 1 -
MCP server for Alibaba Cloud Agent Sandbox (阿里云智能体沙箱): run commands, execute code and manage files in cloud sandboxes
MIT -
boxlite-mcpgithub.com/boxlite-ai/boxlite-mcpupdated this year
Powered by BoxLite - embeddable sandbox with hardware-level isolation and no daemon. The SQLite of sandbox, coming soon as open source.
Apache-2.0 ★ 43 -
go-playground-mcpgithub.com/samber/go-playground-mcpupdated this year
🤹 A MCP server to execute Go code in Go Playground and generate shareable URLs
npm MIT ★ 6 -
MCP server for Sandbox as a Service: give an agent a real Linux VM — run commands, move files, expose a preview URL, destroy it.
mcpb MIT -
Open-source Agent Environment & Host Runtime (macOS Apple Container / Docker / WSL 2). Stream native GUI windows (Wayland to Metal), MCP server, and instant snapshots for AI Agents.
Apache-2.0 ★ 5 -
Cross-architecture LLM internal observation database (23 models, 13 architecture families). Exposed as MCP tools for any AI coding agent.
★ 43 -
An open-source pipeline that turns your writing into a specification for AI agents. It describes how you reason, communicate and decide. Agents read it before acting for you. Each claim cites facts that quote your own words, so you can check and correct any claim.
Apache-2.0 ★ 5 -
Every language before it was built for humans to read and learn. LOVA is the first built for AI: programs are integer sequences — 64 one-byte operators, structured faults with repair hints, declared effects, budgets, lineage, a Rust VM at 11M steps/s, an MCP server. Open source: extend, modify or rebuild it to make AI faster.
MIT ★ 7 -
Context provider for data agents (MCP + REST + CLI): metrics, golden queries, and interpretation knowledge. Google Cloud native (Cloud Run + Cloud SQL), secret-zero.
MIT ★ 21 -
One MCP, many parsers. Routes between markitdown (default), Docling, LlamaParse. Plus an interpret tool that pipes parsed markdown into Claude with caching. FastMCP, Python.
mcpb MIT -
MCP server and recordkeeping protocol for fact-specific written interpretations between two parties: JIAs, RMAs, no-action letters, advisory opinions, private letter rulings. Plain markdown, manifest-checked, gist-bound. The verifiable-records layer of th
npm Apache-2.0 -
A personal, local-first AI coach for one triathlete/runner. Reads your AI Endurance (or intervals.icu) and Garmin data and *interprets* it — readiness, race-time models built on you, weather-aware sessions, deep session feedback — plus an MCP server to query it all from Claude. Your data never leaves your machine. MIT.
MIT