"File system requirements: mounted directory, persistent state, and full R/W access" matching MCP servers:

Graph-native bounded working memory for coding agents with typed memories, causal retrieval, current-vs-stale state queries, and compact small-model briefs.

A Model Context Protocol server that enables LLMs to read, search, and analyze code files with advanced caching and real-time file watching capabilities.

Enables AI agents to develop within a local project workspace by reading and modifying files, running commands and tests, checking Git state, and persisting progress as history sessions that can be restored in later conversations.

Enables users to generate complete, production-ready software projects from simple ideas by coordinating 8 specialized AI agents through the Model Context Protocol.

Enables AI clients to send prompts to a local Codex App Server via MCP, returning text responses and supporting persistent session reuse.

Enables code execution in isolated Docker containers with persistent IPython, Node.js, or R kernels, supporting file import/export and cross-session transfers via MCP tools.

MCP server that enables Claude Code to delegate tasks to DeepSeek and other LLMs, offering 20 tools for code review, analysis, testing, and code generation.

Bridges Claude AI with Xcode, enabling AI-powered code assistance, project management, and automated development tasks securely on your local machine.

dev-brain-mcp

Transforms your IDE into an autonomous multi-agent coding assistant that orchestrates complex codebase refactoring using LangGraph and LiteLLM.

Autonomous game development framework that lets AI agents program, design scenes, and run visual QA on Godot 4.x projects — all through the Model Context Protocol (MCP).

Enables Claude Code to use GLM (Zhipu) as a cheap, full-capability subagent for file editing, code generation, and bash commands, with automatic routing between Opus and GLM based on task complexity.

MCP server that packages DeepSeek agents as callable tools, offering a bare model for quick Q&A and a full agent capable of executing real coding and file-modifying tasks in a workspace.

Provides MCP tools to create, run commands in, checkpoint, and delete durable cloud environments, giving coding agents persistent state between calls.

Enables delegating coding tasks to Claude Code, Codex or OpenCode agents over the Agent Client Protocol, running a prompt to completion in a chosen directory and returning the agent's result. Also supports follow-up messages, background turns, session listing, cancellation, and harness discovery with configurable permission policies.

Wraps the Claude Agent SDK as MCP servers, letting you spawn multiple specialized Claude Code agents — each with its own model, tools, system prompt, and personality — from any MCP client.

Enables AI assistants to write and execute C# code directly inside Autodesk Civil 3D, providing full API access through code generation and execution.

Provides AI coding agents a full abap2UI5 development loop—writing ABAP classes, validating views, deploying, and running apps headless with screenshots—all locally without an SAP system.

Enables Codex to use an installed Devin CLI as an additional worker by starting, polling, and cancelling bounded tasks through local MCP tools. It runs as a local stdio server in a given working directory, so jobs execute with the Devin account's model and permissions while Codex's own routing rules still decide when to delegate.

Enables coding agents to search and retrieve persistent repository memory created by Cliper, providing context, gaps, architecture, and timeline information via MCP tools.