"Open Collective" matching MCP servers:

The most powerful open-source Cairo code generator.

A simple MCP server that provides a tool to fetch current weather information for cities using the Open-Meteo API, communicating through stdin/stdout.

Connects Roblox Studio to AI coding editors via the Model Context Protocol, allowing AI agents to understand and interact with live Roblox Studio sessions through scene manipulation, scripting, and optional Roblox Open Cloud API integration.

Exposes the Jupyter notebooks open in VS Code to MCP-compatible AI agents, letting them edit cells in the open editor and execute them in the live kernel without file conflicts. Agents can make partial edits, track stale cells, inspect variables, and manage kernels while preserving the user's interpreter choices and unsaved work.

Enables users to automate local FlexSim modeling through DSH's MCP client bridge: open models, execute verified UTF-8 scripts, inspect diagnostics and exported CSV data, and save models safely with overwrite protection and backups.

Enables LLMs to automate SolidWorks (open/save parts, modify dimensions, export STEP) via COM, and optionally generate geometry using build123d code-CAD with PNG previews.

Archive Agent is an open-source semantic file tracker with OCR + AI search (RAG) and MCP capability.

Enables running Claude Skills locally on your Mac with sandboxed execution, supporting document processing and integration with MCP-compatible AI tools while ensuring data privacy.

MCP server that gives any LLM a managed Docker workspace with live browser, terminal, code execution, document skills, and autonomous sub-agents.

Enables agents to open or connect to a Colab browser tab and use notebook tools, resources, prompts, and progress through a local stdio session.

Protect against malicious open source packages 🤖

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.

Gru-sandbox(gbox) is an open source project that provides a self-hostable sandbox for MCP integration or other AI agent usecases.

Drives a live ArcGIS Pro session from Claude via arcpy, enabling layer listing, dataset description, geoprocessing, and project inspection directly against an open project.

Enables AI agents to control a live Blender session for scene/object manipulation, rendering, code execution, and PolyHaven asset/texture management. It also supports runtime switching among Ollama, LM Studio, llama.cpp, OpenAI-compatible, and Azure backends.

Enables LLM clients to work with Vantage to inspect and modify scene state, open/save files, probe object properties, and run VScript payloads.

Enables natural language control of Blender 3D through local AI models, allowing MCP clients to create, modify, and render scenes, apply materials, and execute Python code in Blender.

Lets AI agents drive a live Blender session — reading scene and object data, creating, modifying and deleting objects, setting materials, rendering images, executing code, and downloading PolyHaven assets. Prompts flow through a swappable, provider-agnostic LLM backend (Ollama, LM Studio, llama.cpp, OpenAI-compatible, Azure) that can be reconfigured at runtime without restarting.

Enables Open WebUI to execute bash commands for coding tasks in a persistent projects workspace, with configurable timeouts and output limits.

Enables natural language control of Siemens NX for text-to-CAD modeling, generating .prt files via NX Open API. Currently supports basic solids, booleans, and fillets in batch mode.

Enables AI agents to control a live Blender session — inspecting and editing scenes, objects and materials, rendering images, executing code, and pulling PolyHaven assets — through MCP tools. It also routes prompts to a provider-agnostic LLM backend (Ollama, LM Studio, llama.cpp, OpenAI-compatible, or Azure) that can be switched at runtime.

An MCP Server that enables natural language interaction with the Open Policy Agent REST API, allowing users to manage policies, decisions, and data through conversational interfaces.

An open-source network operations integration platform that connects large language models with network devices through the Model Context Protocol, allowing AI assistants to perform network configuration, diagnostics, and management tasks.

Enables AI agents to control a live Blender session via MCP tools for scene and object operations, rendering, code execution, and PolyHaven asset management. It supports provider-agnostic LLM backends that can be configured at startup or switched at runtime.

Enables AI agents to control a live Blender session with scene/object manipulation, rendering, PolyHaven asset tools, and runtime-switchable LLM provider backends.

Enables AI agents to drive a live Blender session over MCP — inspecting scenes, creating, modifying and deleting objects, applying materials, rendering images, importing PolyHaven assets, and executing code — while routing prompts through a provider-agnostic LLM backend (Ollama, LM Studio, llama.cpp, OpenAI-compatible, Azure) that can be switched at runtime.

Lets your AI find the open-source tool it needs on GitHub and install it as an MCP tool, in a sandbox, after you approve. Reads only the folders you grant; no network unless allowed.

Enables AI agents to drive a running Roblox Studio in real time over a single WebSocket, executing whole Luau programs, installing in-engine controllers, hot-patching scripts during live playtests, and receiving errors, assertions and other events as pushes. It also reaches Roblox Open Cloud for the open place and answers visual questions via a vision sidecar, exposing all of this through nine MCP tools.

Connects an AI agent to an open CSI ETABS model through the official COM API, enabling natural-language requests for model queries, analysis, design checks, and report extraction while the agent searches API methods and runs sandboxed Python against the live model.

Enables an LLM to orchestrate multiple downstream MCP tools inside one isolated sandbox in a single turn, filtering intermediate results in memory and returning only the final output to cut context tokens.