"Exploring RAG through defined workspaces" matching MCP servers:

Implements a RAG workflow that integrates with any custom knowledge base and can be triggered directly from the Cursor IDE.

Agentic RAG server for document management, hybrid search, question answering with citations, and analytical code execution, powered by LanceDB and Pydantic AI.

Enables AI agents to perform software engineering tasks inside an isolated, deterministic sandbox—exploring repositories, reproducing failures, applying patches, running tests, and verifying solutions against hidden suites through MCP tools.

Enables AI agents to run Jest/TypeScript tests in isolated workspaces for Test-Driven Development workflows.

Enables ChatGPT web to interact with local Windows/WSL shell and code workspaces via an MCP server, providing file access, shell execution, and snapshot-based workspace management with per-command authorization.

MCP server that integrates Conductor Cloud with Hermes Agent, enabling Hermes to create sandboxed coding workspaces, dispatch tasks to developer agents (Claude, Codex, Cursor, ACP), and monitor or retrieve session results via MCP tools.

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 AI agents to control VSCode workspaces, including file operations, terminal commands, search, and workspace management.

Enables AI assistants to interact with Replit workspaces directly, including managing repls, file operations, environment variables, and deployments without constant user intervention.

It lets MCP clients evaluate a single Emacs Lisp form in an already-running Emacs instance through one tool, enabling agents to discover and invoke built-in, package, and user-defined capabilities from the live runtime.

A Model Context Protocol server that enables AI agents to retrieve and understand entire codebases at once, providing tools to analyze local workspaces or remote GitHub repositories.

Enables Claude Desktop to act as a planning agent while delegating coding tasks to OpenCode CLI, returning execution status, file diffs, and output, with support for continuing sessions and opening workspaces in IDEs.

Provides pre-defined prompt templates for AI assistants to generate comprehensive plans for TypeScript projects, API architectures, and GitHub workflows.

Windows 11 local MCP bridge enabling authorized access to development workspaces, command execution, and UAC-gated admin operations for ChatGPT-like clients.

MCP server for exploring the ECMAScript specification and its implementation, enabling semantic search of spec sections, JavaScript execution in engine262, and access to a knowledge graph linking spec sections to implementation functions.

An intelligent codebase processing server that provides agentic RAG capabilities for code repositories, enabling semantic search and contextual understanding through self-evaluating retrieval loops.

Enables AI assistants to inspect and control a live Roblox client through an executor, including reading console output, exploring the instance tree, decompiling scripts, monitoring remote traffic, and running Luau code.

A lightweight bridge extension that enables Claude Desktop to connect to VSCode workspaces via Model Context Protocol, allowing Claude to read and write files, create directories, and list contents in your workspace.

Enables AI clients to securely operate isolated coding workspaces with file, command, Git, and deployment tools via authenticated remote MCP.

Provides dynamic, context-aware code assistant skills through hybrid RAG (vector + knowledge graph), enabling runtime skill discovery, automatic toolchain-based recommendations, and on-demand loading from multiple git repositories.