"Arc" matching MCP servers:

MCP server for Archicad automation, enabling AI assistants to run Python scripts against running Archicad instances via the Tapir JSON API for complex workflows.

A proxy MCP server that wraps MCP-for-Unity, correcting transport inaccuracies and restricting tool usage for reliable Unity integration.

A local MCP server that enables AI clients to read ArcGIS Pro project information and execute ArcPy geoprocessing in the native ArcGIS Pro Python environment.

apc-mcp is a Model Context Protocol server that brings audio plugin development workflows into any MCP-compatible client by wrapping CMake, ctest, clang-format, pluginval, and clap-validator into a clean tool interface for building, testing, linting, validating, and scaffolding JUCE, CLAP, VST3, and ARA plugin projects.

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

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

A dynamic tool management platform that allows creating, editing, and executing Python code tools via a web UI, exposing them as MCP tools through Streamable HTTP.

ArcAgent MCP server for bounty discovery, workspace execution, and verified coding submissions

Enables interaction with Arcanna's AI-powered security use cases, allowing users to manage jobs and integrations, query security events, provide feedback for model training, and generate/execute Python code for security automation.

Ephemeral MicroVM-isolated code execution for AI agents. Run Python, Node, or bash — fresh hardware-isolated VM per call, hard-purged after. No state persists between calls.

A FastMCP server that dynamically loads tools from Python/YAML file pairs, acting as a stand-in for the Tools Framework in agentic-assembly-framework.

Enables AI assistants to compile, run, lint, and format ArxLang code directly through ArxNode without manual terminal commands.

Enables efficient AI agent operations through sandboxed Python code execution with progressive tool discovery, PII tokenization, and skills persistence, achieving up to 98.7% token reduction by processing data in a sandbox rather than in context.