"How to modify local files" matching MCP servers:

An MCP server that dynamically registers prompt templates from local files and serves them to clients with the assistant role.

Enables LLM clients to query local markdown engineering documentation by indexing files into ChromaDB with Ollama embeddings and exposing a search_internal_docs tool over stdio, all offline and privacy-first.

Enables local analysis of unstructured documents (PDF, DOCX, PPTX, SVG, PNG) by extracting text and structure with citation anchors, and verifies summaries against source material before a human approves saving a report.

Enables local conversion of PDFs to Markdown, with automatic OCR fallback for scanned pages, image extraction, and page-by-page structure preservation.

Enables read-only scanning and text extraction from PDF, DOCX, PPTX, SVG, and PNG files in a local folder, providing the raw text to AI models for summarization or analysis without an external LLM API.

Local-first context retrieval engine that serves precise documentation chunks to coding agents via MCP, ensuring high-confidence context for code generation.

A Model Context Protocol server for querying and reading articles from a how-to documentation portal, with search and retrieval tools scoped to the token's user permissions.

Enables parsing PDF files from local paths or URLs into structured JSON or Markdown format using NetMind's AI-powered PDF extraction service.

Teaches AI coding agents how to reason correctly about MetaMask Embedded Wallets / Web3Auth architecture, SDK choice, key derivation, auth flows, and common integration pitfalls.

MCP server for API discovery from .mind spec files, enabling AI assistants to list, inspect, and call APIs defined in OpenAPI specs.

Enables local document search and reading across formats like docx, pdf, md, and more, providing tools for listing, searching, and reading documents.

Enables AI assistants to read local documents by converting PDFs, Office files, images, and audio to Markdown on-device, without uploading them.

Exposes design system component documentation to LLM clients via MCP, allowing listing and retrieving component contexts from Markdown files with YAML frontmatter.

Serves Markdown skill and rule files from a local directory to AI agents on demand, letting them list and fetch specific instructions without context bloat.

Look up how engineers actually pronounce project / product / jargon names (kubectl, nginx, JSON, Pydantic, JWT) — 1452+ entries with IPA, respelling, source citation, and confidence level.

Enables AI agents to search a local folder of Markdown, AsciiDoc, and text files through a SQLite FTS5 keyword index, returning the most relevant sections with file paths, line ranges, and heading breadcrumbs instead of grepping through a repo. It also exposes tools to list indexed documents and refresh the index incrementally, all offline with no dependencies, network calls, or embeddings.

Enables AI agents to ingest documentation from websites or local files and perform semantic search over the indexed content using pgvector-backed embeddings.

Fetches glasz-style spec files (product.md, tech.md, test-plan.md, and INDEX.md) from GitHub repositories, enabling LLMs to answer questions about features, stories, and acceptance criteria without cloning or pasting files.

Converts PDF files from local storage or URLs to structured Markdown format using Mistral AI's OCR API, preserving document structure and extracting images.

Enables MCP clients to read and, when explicitly enabled, modify Hudu IT documentation—companies, articles, assets, asset layouts, and password resources—through curated read tools, bounded paginated list operations, and policy-gated write/delete dispatch over the node-hudu SDK. Supports stdio and HTTP transports with per-caller credentials, read-only defaults, secret-read restrictions, resource-level search scoping, and redaction of credential fields.