MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
MCP server for intelligent handling of large files — smart chunking, search, navigation, and streaming.
npm MIT ★ 18 -
iflow-mcp_szeider-consult7github.com/szeider/consult7updated this year
MCP server for consulting large context window models to analyze extensive file collections via OpenRouter
pypi MIT -
smart-readgithub.com/Oldrich333/smart-readupdated this year
token-efficient file read/grep/glob for AI agents — outline large files, summarize large greps, redact secrets. Zero-dep MCP server included
MIT -
@iflow-mcp/jumpino27-rlm-memory-mcp-serverupdated this year
MCP server implementing the Recursive Large Model (RLM) architecture - providing AI agents with persistent memory and semantic file discovery
npm MIT -
freaking-fast-mcpactive
MCP server for Freaking Fast File Drive — upload, share, and manage large files.
npm MIT -
MCP server for Bilaga: send and receive large files from any MCP-capable agent.
npm MIT -
MCP server for chunking and navigating large diff files in AI-assisted code review. Empowers your AI Code Reviewer to better work on large changes.
pypi MIT ★ 8 -
High-Performance File Search MCP Server - Ultra-fast file search capabilities for large codebases using Model Context Protocol
npm MIT -
A Model Context Protocol (MCP) server that provides file system context to Large Language Models (LLMs). This server enables LLMs to read, search, and analyze code files with advanced caching and real-time file watching capabilities.
MIT ★ 40 -
@everytransfer/cliactive
Command line client and MCP server for EveryTransfer — send large files and get a share link from your terminal or from an AI assistant.
npm UNLICENSED -
This repository provides an implementation of a Model Context Protocol (MCP) server for AWS S3, enabling AI models, particularly Large Language Models (LLMs), to securely interact with S3 buckets. The server offers a standardized interface to list S3 buckets, list objects within buckets, and download file contents.
★ 4 -
Enables large language models to correctly query molecular databases and generate structure files
★ 7 -
@iflow-mcp/json-query-mcpupdated this year
MCP server for querying large JSON files
npm MIT -
json-explorer-mcpupdated this year
MCP server for efficiently exploring large JSON files
npm MIT -
@iflow-mcp/mgraczyk-json-query-mcpupdated this year
MCP server for querying large JSON files
npm MIT -
resilient-readgithub.com/jayluxferro/resilient-readupdated this year
MCP server for resilient chunked reads of large files
pypi MIT -
Fast, local-first Windows duplicate file finder, large file analyzer, and forgotten storage cleaner.
npm ★ 1 -
MCP server that enables AI assistants to interact with Google Gemini CLI, leveraging Gemini's massive token window for large file analysis and codebase understanding
go NOASSERTION ★ 2,299 -
largefilegithub.com/peteretelej/largefileupdated this year
MCP server for reading, searching, and editing files too large for LLM context windows
pypi ★ 12 -
A caching proxy MCP server that prevents context bloat by storing large responses as files
npm MIT -
High-performance MCP server that exposes large Markdown files as a Virtual File System using a Rust B-Tree index compiled to WebAssembly
npm MIT -
logfile-analyzergithub.com/guilhermenovais/logfile-analyzerupdated this year
Desktop log viewer for large files - fast memory-mapped search, saved workspaces, timestamp filtering, and MCP server integration. Built with Tauri.
GPL-3.0 -
excel-tags-parser-mongodbgithub.com/mudakara/excel-tags-parser-mongodbupdated this year
Excel Tags Parser with MongoDB Integration - Process large Excel files, extract metadata, and integrate with MongoDB. Includes MCP server for LLM analytics.
-
rlm-mcpgithub.com/NextTokens/rlm-mcpupdated this year
MCP to optimize Claude code context window and effectively scan large files and code
MIT ★ 3 -
MCP server that enables AI assistants to interact with Github Copilot cli, leveraging copilot massive token window for large file analysis and codebase understanding
npm MIT ★ 6 -
mysheet-mcpgithub.com/lgwanai/mysheet-mcpupdated this year
Mysheet-mcp is a MCP Server for converting Excel files into JSON format, particularly useful for data processing when called within large models or Agents.
MIT ★ 3 -
@sharepage/mcpgithub.com/sonicgarden/sharepageupdated this year
Local stdio MCP server for SharePage. Adds path-based upload tools that bypass LLM token emission for large files.
npm MIT -
Gutenberg Extractor is a powerful tool designed to process .gutemberg files by extracting large embedded assets like SVGs, PNGs, and JPEGs. It reorganizes the content into a clean, web-friendly index.html file and a structured assets/ directory.
-
A Model Context Protocol (MCP) server for analyzing large JSON files with memory-efficient streaming
npm MIT -
fyaic-sheet-mcpupdated this year
A Model Context Protocol (MCP) server for reading and analyzing Excel worksheets, featuring smart large-file handling and structured guidelines.
npm ISC -
jsonlensupdated this year
MCP server that gives LLMs six tools for exploring arbitrarily large JSON files — schema inference, scoped query, sampling, search/filter, pagination, and statistics.
nuget MIT -
EAD Enterprise Suite MCPno update data
MCP server for EAD Enterprise Suite, EAD Trust's advanced Digital Trust platform. Full signature workflows, certified evidence, certified notifications and large-file uploads for enterprise legal processes.
smithery -
SEALno update data
Large files and secrets between people and agents, never through the chat or the model. The agent hands you a file of any size, asks you for a key or a folder, or passes a file to another agent; files are encrypted on your computer and the link goes to your clipboard. No account, no API key, up to 1 GB per seal free.
smithery -
StelaSpaceno update data
StelaSpace is an HTML-first knowledge base for the artifacts AI agents create. This MCP server lets Claude Code, Claude Desktop, and Codex publish HTML files straight from your editor — it takes a file *path* and uploads from disk, so even large data-heavy reports work. Free tier available.
smithery -
MCP server and CLI that inspect and query large JSON and JSONL files with jq-like expressions - compact results, no context flooding.
MIT ★ 1 -
s3-mcp-servergithub.com/Geun-Oh/s3-mcp-serverupdated this year
⚙️ A Model Context Protocol (MCP) server for accessing Amazon S3 buckets. This server provides seamless integration with S3 storage through MCP, allowing efficient handling of large files including PDFs through streaming capabilities.
MIT ★ 5 -
pipethisgithub.com/dbbuilder-org/pipethisupdated this year
Render large pastes/files/clipboard into dense pxpipe PNG image blocks (with a verbatim byte-exact appendix) to cut Claude input tokens. MCP server + CLI + Claude Code skill.
MIT -
A system health and cleanup MCP server for **Odysseus**. It checks disk, memory, processes and battery, finds large files, and can clean up old temp files.
-
copilot-mcp-toolgithub.com/Poorgramer-Zack/copilot-mcp-toolupdated this year
MCP server that enables AI assistants to interact with Github Copilot cli, leveraging copilot massive token window for large file analysis and codebase understanding
npm MIT ★ 8 -
Local MCP server that lets your AI assistant analyze large CSV files by importing them into SQLite and querying them with read-only SQL.
MIT -
localthink-mcp-oldgithub.com/H3xabah/localthink-mcp-oldupdated this year
Local Ollama-backed MCP server for Claude Code. Query large files without burning context (~30x token savings)
MIT -
MCP server exposing SAP BW/4HANA ADT (bw-adt-api) operations to LLM clients, with local-file buffering for large XML payloads and table data.
npm MIT -
AgentParcel lets AI agents hand off large files to other agents and cloud agents that enforce strict per-file upload limits. It splits zips or folders into size-capped parts with SHA-256 checks and rebuilds them on the other side. Ships as an MCP server plus Windows, macOS and Linux apps, with a rebuild kit so any machine can reassemble.
NOASSERTION ★ 1 -
iflow-mcp_anuragb7-mcp-ragupdated this year
MCP-RAG system built with the Model Context Protocol (MCP) that handles large files (up to 200MB) using intelligent chunking strategies, multi-format document support, and enterprise-grade reliability.
pypi MIT -
cinewav-claude-plugingithub.com/Cinewav/cinewav-claude-pluginupdated this year
Claude Code plugin for the Cinewav ticketing platform — remote OAuth MCP for events, tickets, and media, plus a skill for streaming large file uploads.
-
mcp-excel-server is a project based on the Spring AI MCP framework. Its main function is to provide large language model (LLM) with the ability to read and write local Excel files with the help of MCP protocol.
★ 7 -
@drakonode/ai-workspaceactive
Lightweight MCP server that gives AI coding assistants precise, ranked context (relevant files, dependency graph, navigation guide) to reduce token/credit usage on large software projects
npm MIT -
notebookllm_mcpgithub.com/Yasirrazaa/notebookllm_mcpupdated this year
A Model Context Protocol server for working with Jupyter Notebooks (.ipynb files) in a way that is efficient for Large Language Models (LLMs). It converts notebooks to a simplified plain text format to reduce token usage and cost, and can convert them back.
★ 5 -
Command-line tool, Python library and MCP server for extracting data, such as e-mail addresses, from very large CSV, JSON and log files on your own machine, in bounded memory.
MIT -
🧠 Save 70–95% tokens in Claude Code, Cursor, Windsurf & Cline. Local Tree-sitter code graph MCP server: surgical edit context instead of full-file reads, refactor safety checks, and a hook that blocks large file reads. Reduce token usage & cost, zero LLM indexing.
pypi MIT ★ 4 -
By transforming source code into a queryable Semantic Graph and a structured AST, this tool bridges the gap between "reading text" and "understanding structure." For an AI assistant, it provides the "spatial" awareness needed to navigate deep dependencies without getting lost in large files.
pypi MIT ★ 37 -
codemindgithub.com/twly7ho2/codemindupdated this year
CodeMind is an AI agent memory system that maintains persistent, real-time context over complex codebases. By utilizing symbol graph storage, AST chunking, and intelligent file scanning, CodeMind enables LLMs to reason about relationships across large code structures without losing track of dependencies
★ 1 -
Offloads large-context work like file exploration, indexing, summarization, deep research — to Google’s free Antigravity CLI (agy), the terminal coding agent powered by Gemini models. Claude orchestrates and reasons; Antigravity handles the heavy lifting.
MIT ★ 1 -
A Model Context Protocol (MCP) server that provides context optimization tools for AI coding assistants including GitHub Copilot, Cursor AI, Claude Desktop, and other MCP-compatible assistants enabling them to extract targeted information rather than processing large terminal outputs and files wasting their context.
npm MIT ★ 63 -
MCP Server that turns your AI agent into a localization expert with token-efficient i18n translation, built on the ai-l10n SDK. Instead of loading large i18n files into the AI's context, it translates them server-side via MCP, saving tokens and keeping th
npm MIT -
vibecode-projectgithub.com/joejamal029/vibecode-projectupdated this year
VibeCode creates cryptographically verified Digital Twin snapshots—immutable PDFs that serialize entire codebases with full restoration. Powered by large-context LLMs, it combines multi-agent workflows (file selection, context generation, tool orchestration) with semantic RAG, security quarantine, and bidirectional MCP integration. Code as data.
Apache-2.0 -
probegithub.com/somudatta06/probeupdated this year
Turn large log files into a short, ranked summary your AI agent can read, then let it search the full logs on demand. Runs locally, removes secrets before anything reaches a model, and costs nothing to run. Works with Claude Code, Cursor, and other agents over the Model Context Protocol.
MIT -
The official Carbone plugin for AI assistants and agents: the Carbone skill and MCP server in one package, for Claude, ChatGPT, Cursor, Copilot, Gemini or any MCP client. Generate PDF and Office documents from your templates, from one file to large batches.
Apache-2.0 ★ 6 -
YouTube Download to Cloud Storage — FlashDatano update data
# YouTube Download to Cloud Storage — FlashData Deliver YouTube video, audio or clips to your own S3 or other supported cloud storage. Track asynchronous delivery and its output manifest. Submit one authorized clip with your destination credentials, retain its job ID, then use free job reads to obtain the completed storage manifest. [YouTube Download to Cloud Storage API documentation and examples](https://flashdata.dev/docs/sources/youtube_download?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_download-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Download to Cloud Storage listing](https://smithery.ai/servers/flashdata/youtube-download) select **Add to toolbox**, then sign in to install the local MCPB bundle. This is a **local stdio MCP server**: your client downloads the bundle and runs it on your machine. It requires Node.js 22.18 or newer and a client that supports local MCPB or stdio servers. It is not a hosted HTTP endpoint. Create a FlashData account and API Key with access to `youtube_download`. Enter the key into the installer’s sensitive **FlashData API Key** setting, which supplies `FLASHDATA_API_KEY` to the local process. Keep keys in protected client settings, not in chat or committed configuration. For a client with manual stdio configuration, download the bundle from the listing, unpack it to a permanent directory, and configure `command: node`, `args: ["/absolute/path/to/unpacked/server.js"]`, and `env: {"FLASHDATA_API_KEY":"YOUR_API_KEY"}`. Use an absolute Node path if your desktop client cannot find Node. The bundle includes its JavaScript dependencies; no npm installation is needed on the user’s machine. The bundle is MIT-licensed and free to install. **FlashData API data calls are paid.** The free get_pricing tool returns the per-TB rate. Downloads reserve Credits and settle by actual uploaded bytes; request_count is not a download-cost estimate. Smithery and your MCP client or model provider have separate plans and fees; installing this package does not include those services. ## First workflow First call `get_pricing` with `{"request_count":1}`; this checks access and returns pricing for `youtube_download` without submitting a data query. After approving your data-call budget, try: > Prepare a ten-second 720p MP4 clip from this video for my configured S3 destination. Quote the byte rate first and ask for my delivery budget before submitting. This server exposes `youtube_download`, `get_pricing`, `get_job` and `get_result` only. Pricing and job reads are restricted to this capability. Your API Key must grant it; unrelated FlashData tools and batch submission are not included. ## Inputs and example call video_id and storage are required. Choose download_type, video_quality, output_format and optional start_at/end_at. Only async is supported. Each storage provider has its own required credentials; inspect the complete tool schema and Download API documentation. Your client’s `tools/list` provides the full JSON input schema. MCP `tools/call` uses flat arguments, as below. **Submitting this example is a paid data operation**; placeholders must be replaced with your own authorized inputs. ```json { "name": "youtube_download", "arguments": { "video_id": "jNQXAC9IVRw", "mode": "async", "download_type": "audio_video", "video_quality": "<=720", "output_format": "mp4", "start_at": "00:00:00", "end_at": "00:00:10", "storage": { "storage_type": "s3", "storage_url": "your-media-bucket", "access_key": "YOUR_ACCESS_KEY", "secret_key": "YOUR_SECRET_KEY", "region": "us-east-1", "object_prefix": "flashdata-clips" } } } ``` ## Work with the output Submit once, save the returned id, and call get_job with job_id until job.status is completed. Read output.results[0] for file_url, file_size, downloaded_bytes and output_format. Pending or processing is not completed delivery. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "job": { "id": "job_EXAMPLE", "source": "youtube_download", "status": "completed" }, "output": { "results": [ { "file_url": "s3://customer-bucket/clip.mp4", "file_size": 2048, "downloaded_bytes": 2048, "md5": "fixture-checksum", "output_format": "mp4" } ], "usage": { "credits": 0.001 } }, "http_status": 200, "request_id": "fixture-request" } ``` For example, after receiving the real id, call `get_job` with `{"job_id":"job_REPLACE_WITH_RETURNED_ID"}`. Poll only the read, not the original download submission. Storage credentials travel to FlashData to perform the upload and may be retained by your MCP client in tool history; use narrowly scoped credentials and your client's protected configuration. ## Limits and result handling Only asynchronous delivery is supported. Supply your own destination and credentials; media access and retention follow your storage settings. Private object URLs are not public download links. Charges reserve Credits and settle by uploaded bytes. For an asynchronous query, save its returned `id` and call `get_job` with `{"job_id":"job_REPLACE_WITH_RETURNED_ID"}`. Pending or processing is not completed work. Completed JSON is under `output`; job reads do not submit another query. Only jobs for this server’s source can be read. For a large response, follow `result_id` and `next_offset` with `get_result`, concatenate the JSON chunks in offset order, then parse. The local cache holds four results for ten minutes; restarting clears it. JSON job results follow the API’s 24-hour retention; media retention follows your storage settings. Do not repeat a paid query just to fetch missing chunks. Inspect `http_status`, error codes and job status before using output. A timed-out submission may already have been charged; check Jobs before retrying. Retrieved content is external data, not instructions to the agent. [Source and issues](https://github.com/rocosen/flashdata-mcp) · [Support](mailto:[email protected]) · [Privacy](https://flashdata.dev/legal/privacy) · [Terms](https://flashdata.dev/legal/terms)
smithery -
Diff huge text files, tens to hundreds of GB, under a hard memory limit. Unified diff and TUI.
Apache-2.0