"How to work with local files" matching MCP servers:

Enables AI assistants to access and interact with Cursor/VS Code Local History data for file recovery and enhanced context awareness. Provides tools to browse file history, search across snapshots, and restore previous versions of files.

Safe local MCP server for Windows to list, read, search, patch, backup, and verify code files in allowed folders, with Git integration and dry-run diffs.

Enables AI-driven semantic code search using Windsurf's reverse-engineered SWE-grep protocol to query local codebases with natural language. It executes local search tools like ripgrep and tree-node-cli to return relevant file paths and line ranges to MCP-compatible clients.

A codebase-memory MCP server for AI coding agents with hybrid semantic+BM25 code search, structural outlines, a work journal, and gaze-and-think deep reasoning over a local LanceDB database.

MCP server connecting Claude Code to LM Studio, delegating token-expensive tasks to a local model while keeping the cloud model in control. It reduces cloud context usage by reading files locally and returning only the processed results.

Enables structured, iterative reasoning for complex problem-solving with features like confidence tracking, revision mechanisms, and branching support. Provides flexible validation and multiple output formats for systematic analysis and decision-making tasks.

Provides AI coding assistants with persistent memory, AST-based project indexing, and tools for live context management and hallucination detection. It enables saving lessons to local files, trimming conversation history, and verifying code symbols to prevent errors.

Enables codebase indexing and searching with symbolic and full-text search, supporting multiple programming languages, designed to work on any architecture including ARM64.

A fully local RAG MCP server for semantic code search and code intelligence, using AST-level chunking and hybrid search to pinpoint functions, classes, and APIs. No cloud, no API keys, zero setup.

locidx

Analyzes codebases from local directories, GitHub, and Azure DevOps, providing intelligent context to AI coding assistants through repository structure, critical files, and semantic maps.

Reduces Claude's context window costs by automatically summarizing inactive files to their public interfaces using AST parsing, keeping only the full contents of the currently active file.

Local MCP server and CLI for Access layout files, rendered to SVG without Microsoft Access. Enables visual verification of form/report layout changes.

Generates DeepWiki-style documentation for private code repositories with RAG-based Q\&A capabilities, semantic code search, and multi-language AST parsing. Supports local LLMs (Ollama) or cloud providers for privacy-focused codebase analysis.

MCP server that indexes TypeScript/React project symbols in memory, enabling agents to find definitions, references, and dependencies without reading the whole repo. Also includes a local visual dashboard with no outbound network calls.

Enables users to retrieve, validate, and analyze XSD files from URLs or local paths, integrating with any LLM model.

Enables intelligent handling of large files through smart chunking, search with regex support, line navigation, and streaming capabilities without loading entire files into memory.

A secure MCP server that exposes local repository context to ChatGPT/Codex with read-only access, path validation, and no generic shell.

An MCP server that enables AI agents to move TypeScript files and directories while automatically updating all affected imports using a persistent tsserver instance. This ensures atomic, error-free refactoring that maintains project integrity without manual intervention or wasted tokens.

Indexes any TypeScript / React / Next.js repo into a queryable code graph and exposes 13 MCP tools — who-renders, who-calls, find-references, blast-radius, find-cycles, dead-code orphans, and local semantic search — so agents query structure instead of reading whole files. Built on ts-morph, so edges are resolved, not grepped.