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

Delegates mechanical text-to-text tasks to a local LLM to save Claude subscription quota, reading files server-side so large content never enters Claude's context.

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.

Provides safe local-model MCP support tools (summarization, classification, critique, draft) for a cloud owner agent, with strict boundary guards to prevent risky actions.

A local AI agent workspace that allows users to interact with simulated data files via custom slash commands and context mentions, powered by Google GenAI SDK and MCP.

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.

Enables any MCP client to delegate a scoped task to a local Ollama model that runs its own tool-calling loop for file operations and web search, with an allow-listed folder security model.

Enables MCP-capable assistants such as Codex and Claude to delegate bounded text work — summaries, structured extraction, classification, rewrites, code drafts and log digestion — to locally hosted Ollama models, with conservative routing that keeps small or sensitive tasks with the caller and private-result artifacts for sensitive output.

Provides a local-first AI workspace for chatting, invoking skills, managing projects, and integrating MCP tools, with all data stored on the user's machine.

Enables MCP clients to generate and edit images using local Stable Diffusion models in ComfyUI, with tools for text-to-image, img2img, ControlNet, UI frames, upscaling, and background removal—no cloud API or API key required.

Gives Claude Code, Claude Desktop, Cursor and any other MCP client a local sound studio that turns plain-language requests into background music, instrument loops and sound effects, then re-styles, regenerates or extends them and exports seamless loops, fades and loudness-normalized WAV, OGG or FLAC files. Everything runs on Apple Silicon with no cloud service and no API key.

Enables MCP clients such as Codex and Claude Code to delegate bounded coding tasks to a local Ollama Qwen model, with workspace, branch, and command guardrails plus safe file editing and test execution.

MCP server that lets Claude Code delegate mechanical tasks to a local LLM for summarization, classification, extraction, and drafting.

Enables coding agents to ask focused questions about local screenshots, video, audio, and music and receive compact text reports on OCR, layout, timestamps, sounds, and music description. Media stays on the machine and raw files are never loaded into the agent's context, with support for cropping, interval sampling, and durable background jobs.

Exposes locally hosted MLX models as MCP tools for Claude Desktop and Codex, with optional SearXNG search augmentation for private local inference.

Turns a single image of an object into a textured 3D model (GLB with web-ready copy and six-view previews) on your own NVIDIA GPU, returning the written files and a preview. Runs locally as an MCP tool or, optionally, offloads the job to hosted GPUs with an API key.

Enables local coding agents to delegate reasoning, planning, review, derivation, and diagnosis tasks to ChatGPT Web through Chrome DevTools Protocol, with security guards and evidence-based verification.

Processes large files, error logs, and codebase searches locally via Ollama to reduce token consumption in Cursor by up to 80%.

Enables MCP clients to generate images using local ComfyUI with FLUX.2 Klein models optimized for Apple Silicon, plus model management and system diagnostics.

Enables submitting audio via URL or Base64 for local Whisper transcription, then checking job status and results or deleting transcription jobs. It provides asynchronous job handling and SSRF-protected downloads/callbacks without cloud API calls.

Enables delegating mechanical or high-volume subtasks to a local LLM through an MCP tool, letting the assistant query the local model without using its own output tokens for content.

Enables running MCP tools against local MLX models on your Mac, with hardware-aware configuration, CLI streaming, and a dashboard for routing and monitoring.

Enables MCP clients like Claude Code to delegate coding tasks to a local model through a configurable coding-agent CLI backed by any OpenAI-compatible endpoint, with tools for health checks, task execution, and context-aware file modifications.

Enables orchestrating models to delegate reading and answering questions about local files to a local LLM, avoiding sending file contents through the orchestrator's context.

fixRAgent triages one photo of a building problem: what it is, how urgent (EMERGENCY, TODAY, THIS WEEK or WHENEVER), which trade to call, and what to tell the resident. Remote server at https://fixragent.com/mcp with three tools: try_sample, assess_property_photo, get_triage_profile. No key needed to start.

Hands local video files to Gemini's native video understanding for detailed, timestamped descriptions, and also supports image/media viewing with frame extraction.

Lets MCP clients delegate private or bulk text tasks to a local OpenAI-compatible LLM while keeping data on the machine.

Hardened MCP bridge to the full Ollama ecosystem — local and cloud models. 6 tools covering health, model management, chat, and generation with SSRF mitigation, singleton HTTP client, and structured error handling. Two deps, one file.

A machine-facing licensing and settlement rail for AI agent content access. search_pockets and list_pockets work with no key. pull_content needs a funded key and returns HTTP 402 with a registration URL when it has none. Every access, paid or refused, writes its own row with a receipt on both sides. $0.0025 default per pull, owners set their own. 85% to the creator.

A local MCP server that enables Claude Code and Claude Desktop to generate and edit images via OpenAI's Images API, saving finished files into the project and returning previews for iterative refinement.

Enables AI assistants to perform Google searches with real, resolvable sources and transparent search terms.