"Applications or tools with full local file system access" matching MCP servers:

Enables AI agents to execute any SQL command (including DDL/DML) on a PostgreSQL database with zero restrictions, allowing full database control and dynamic database switching.

Provides tools for searching and reading local files, supporting metadata filters, PDF full-text keyword search, and sandboxed file access.

A read-only MCP server that provides document awareness for agents by parsing local files into structured profiles, blocks, chunks, and search results, enabling agents to understand and cite document content without dealing with raw file formats.

MCP server that allows AI agents to read, search, summarize, and answer questions about local PDF, DOCX, XLSX, and TXT files through five tools.

Enables integration with financial transaction data through REST APIs, PostgreSQL databases, and document storage systems. Demonstrates agentic AI capabilities by connecting to Alpha Vantage API and managing financial data through natural language interactions.

Provides file system access for resume matching through JSON-RPC, enabling semantic search and workflow orchestration with LangGraph.

Enables natural-language search over locally indexed files such as markdown, text, images, videos, and PDFs, and retrieves indexed text or media metadata by path. It lets Cursor query a local embedding index built with Gemini and SQLite.

Local-first knowledge system for reasoning agents, exposing facts, evidence, documents, retrieval, and audit history through a thin stdio MCP server.

Enables read-only semantic search over a local document corpus with on-device embeddings and a local Chroma store, featuring symlink-hardened file access and structured error handling.

This server provides an API to query Large Language Models using context from local files, supporting various models and file types for context-aware responses.

Enables Claude Desktop to retrieve only the most relevant sections from locally indexed documents, reducing context-window and token usage during conversations. Indexing and search run entirely on the user's machine using SQLite FTS5, with no network connection or telemetry.

A plugin that allows Dify to connect to multiple MCP (Model Control Protocol) servers using HTTP with Server-Sent Events transport, supporting custom configurations for URLs, headers, and timeouts.

Automates file system operations through natural language commands using a combination of LLM (Ollama), MCP tools, and a Python bridge agent.

MCP server for a modular RAG system that enables natural language question answering over enterprise documents with intent-aware routing, adaptive retrieval, and citation-backed responses.

Enables AI tools to search and manage a private local knowledge base via MCP or HTTP, using local Chinese semantic retrieval without sending data externally.

A local-first document retrieval MCP server that enables AI coding tools like Codex to search private local documents via semantic search and keyword boost, supporting ingestion of PDF, DOCX, TXT, Markdown, and HTML files.

MCP server that enables local hybrid semantic and keyword search over private PDF, DOCX, Markdown, and text documents without sending data to embedding APIs.

Privacy-first local document search using semantic search. Runs entirely on your machine with no cloud services, supporting PDF, DOCX, TXT, and Markdown files.

Enables developers to index and search their own local PDF, DOCX, Markdown, and text documents from an MCP client or terminal, combining semantic similarity with keyword matching for exact technical terms. Everything runs on the user's machine with no API key, Docker, or external database, so private documents stay private and work offline after the initial model download.

Enables full-text search and contextual lookup across local DSH session logs, workspace documents, skills, and persona files using an offline SQLite FTS5 index with Chinese bigram tokenization, plus incremental indexing and status statistics.

Enables MCP clients to search, read, and record reviewed conclusions from policy-gated allowlisted files, with sanitized chunks and create-only drafts or append-only lessons, without granting general filesystem or execution access. It supports lexical ranking and optional loopback embeddings while rejecting likely credentials and raw challenge flags.

About Your task manager is the best agent memory you're not using. An agent-native context layer over your existing task app.

A local MCP server that indexes codebases using Tree-sitter AST parsing and LanceDB, enabling AI models to search across repositories with sub-second latency.

A local-first MCP server for PageIndex — the vectorless, reasoning-based RAG framework. It lets local AI agents index and query local PDF and Markdown documents through a self-hosted PageIndex installation, without requiring any PageIndex cloud API key.

Local-first temporal knowledge graph with six read-only MCP retrieval tools. Supports Ollama and embedded LadybugDB; additions use a separate CLI proposal queue with human approval and explicit application.

Turns local code repositories into a queryable dependency graph built from AST parsing and git co-edit history, then exposes it alongside an Obsidian vault as persistent memory. Enables context retrieval, impact analysis of proposed changes, and curation of durable prose knowledge through full-text search and Personalized PageRank classification—all fully offline without API keys or embeddings.

Enables MCP clients to administer a local LM Studio instance: loading, estimating, downloading, configuring and unloading models, running chat and embedding inference, diagnosing the server, engines and hardware, and managing MCP connectors with conflict-safe configuration. It also builds a local document index supporting citation-checked search and answers grounded in TXT, Markdown, PDF and DOCX files.

Pre-trade risk validation and position sizing for AI trading agents via G-formula and Iron Fist.

MCP server for compressing AI embeddings by 5-7x using TurboQuant (PolarQuant + QJL), with tools to compress, decompress, estimate savings, and embed+compress vectors.

Provides fully local long-term memory for AI agents by enabling semantic search over notes and session logs using Ollama embeddings, with no external APIs or databases.