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 file cache for AI coding agents. Re-reads cost ~40 tokens instead of the whole file; changed files come back as diffs. Works with Claude Code, Cursor, Codex and VS Code.
MIT ★ 3 -
Persistent memory for visual intelligence. MCP server for the Phototology registry: analyze photos with composable lenses, enrich files with EXIF/IPTC/XMP metadata, and look up cached results for free. Works with local files. Analyze once. Remember foreve
npm MIT -
pandaclipgithub.com/xfloukiex-lab/pandaclipupdated this year
One local-first MCP server for agent working state — clipboard history & snippets, TTL cache, file-organizer overlay, and a knowledge graph — plus a live desktop activity lens. 40 tools, SQLite everywhere, no daemons. Apache-2.0.
Apache-2.0 ★ 6 -
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 -
🌐 Multi-provider AI translation tool for JSON i18n files. Features: Google Gemini & Ollama support, incremental caching, multi-file deduplication, MCP server, batch processing, and cross-platform compatibility. Ideal for developers managing multilingual applications.
NOASSERTION ★ 5 -
Fast JSON i18n translator with AI support (Google Gemini, OpenAI & Ollama), incremental caching, multi-file deduplication, and MCP support
npm CC-BY-NC-SA-4.0 WITH Commercial-Attribution -
Local-first agent memory MCP - cross-agent brain with token-saving file diff cache. By Synapse Arrows.
npm MIT ★ 16 -
⚡ High-performance linter, cache-layout optimizer, and garbage collector for AI agent instruction files (AGENTS.md, CLAUDE.md, .cursorrules) in Rust.
MIT ★ 4 -
Lint and explain Dockerfiles and compose files over MCP, statically (no Docker daemon): 47 rules with line numbers and concrete fixes, layer-cache analysis, .dockerignore checks, fix previews. Secrets redacted.
MIT -
CoinGecko market data and price feeds with a file-first store, SQLite cache, CLI, and MCP server
npm MIT -
A Model Context Protocol (MCP) server for enhanced shell command execution — RTK token minimization, persistent caching, execution logging, and safe file writes for AI coding agents
MIT ★ 2 -
MCP server for developers V2 — file operations, git integration, shell execution, and smart caching. Works with Claude Desktop, Cursor, and any MCP-compatible client. https://www.npmjs.com/package/mcp-dev-tools
MIT -
Open-source MCP server giving AI agents Brazilian market data (prices, dividends, fundamentals, CVM filings, FII reports, macro series) through one read-only SQL tool over a local DuckDB cache.
MIT ★ 1 -
claude-real-videono update data
Let any LLM agent actually watch videos. The watch_video tool takes a URL or local file and returns scene-aware keyframes fused with a timestamped transcript, processed 100% locally (ffmpeg + Whisper), cached per source. Requires Python 3.10+ and ffmpeg; runs via uvx from PyPI (claude-real-video).
smithery -
Was I hit by an npm supply-chain attack? Scan every lock file, global install and the npm cache for known-malicious package versions. Pre-install guard, pre-open repo audit, MCP server.
npm Apache-2.0 ★ 15 -
designintelupdated this year
Local MCP server for Figma — syncs design files into a searchable local cache so Cursor, Claude, Copilot and other AI tools build from your real designs. No login, no per-seat cost, unlimited requests.
npm MIT -
Nexus Mods MCP server - 135 tools over REST API v1 + GraphQL API v2 (search, mod/file data, downloads, comments, collections, user management) with built-in TTL cache, OAuth2 (PKCE) and zero-install uvx setup. Works with every MCP harness.
MIT ★ 3 -
MCP server for OpenGrok code search — 25 tools for full-text search, symbol definitions, references, file history, and annotations across AOSP-scale codebases. Built in Rust with async reqwest client, in-memory TTL cache, and rate limiting. Supports token, HTTP Basic auth, and custom CA certificates.
GPL-3.0 ★ 2 -
MCP server for the AI Patent Search Generator — patent dossiers, prosecution history, Office Action AI analysis, citation/family/CPC lookups, and Google Patents search. Works in Claude Code, Claude Desktop, Cursor, ChatGPT-with-MCP, and any other MCP-compatible client. ## Tools (11) - **dossier** — full patent intelligence: bibliographic, claims, citations, family, classifications, examiner stats. 3 credits fresh; free on 24h cache hit. - **prosecution** — USPTO file-wrapper documents (Office Actions, responses, amendments). Free. - **oa_analyze** — AI analysis of USPTO Office Actions (rejection grounds, cited prior art, suggested response arguments). First 5/application free; 1 credit each thereafter. - **search** — multi-strategy patent search against Google Patents (telescoping / onion-ring / faceted). 1 credit. - **query** — Boolean query generator (manual paste into Google Patents). 1 credit. - **similar** — Google Patents similar-documents ranking. Free. - **citations** — backward + forward citation graph, examiner-cited flagged. Free. - **family** — patent family (continuations, divisionals, foreign counterparts). Free. - **examiner** — name, art unit, allowance rate, average pendency. Free. - **cpc** — CPC classification code lookup. Free. - **balance** — credit + subscription status. Free. Requires an API key minted from the AI Patent Search Generator Chrome extension's Admin tab.
smithery -
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 -
0pi-mcp-servergithub.com/dizzydes/0pi-mcp-serverupdated this year
Dropbox and pastebin for AI agents. Open and free. Useful for caching contexts and bridging multi-agent workflows
MIT ★ 1 -
Free up space on your Mac without fear. Disk cleaner that knows what recreates itself: folder catalog, MCP server docs and release notes.
NOASSERTION ★ 1 -
Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API. One File. Pure Swift
npm Apache-2.0 ★ 810 -
MinniMemoryMCP: an MCP server that shrinks what Claude Code and Codex load every turn. It splits your memory files (CLAUDE.md, AGENTS.md) into a small AlwaysOnMemory part and OnDemandMemory files that load only when a task needs them: init, apply, undo, d
npm SEE LICENSE IN LICENSE -
codenavgithub.com/ajacobm/codenavupdated this year
Data Science platform for code structure analysis, trace event-action chains through graph queries; perform code diagnostics and more! Notebooks, Force-directed graph visuals; follow your agent as it updates your files.
MIT ★ 1 -
Give your AI coding agent persistent memory — stop re-reading files every conversation. MCP server for Claude Code, Claude Desktop, Cursor, and other AI coding tools.
pypi MIT -
Persistent codebase memory for AI coding agents — Claude Code, Codex, Cursor, Cline, Continue and any MCP client. Learns which files go together from how you work and serves compact, ranked context: the gold file on 40 of 40 public-benchmark queries to keyword ripgrep's 32 of 40, at 31-67× fewer tokens than ripgrep and 51-242× fewer than pasting every source file (a larger 150-question eval misses 10). Local-first, no telemetry by default.
pypi MIT AND LicenseRef-NeuralMind-Commercial -
ftp-mcpgithub.com/Kynlos/ftp-mcpupdated this year
MCP server for FTP/SFTP — smart sync, diff patching, caching, and security controls for AI coding assistants.
MIT ★ 3 -
Fast native C++ storage intelligence engine, disk analyzer, and app cache inspector (Zalo/Dev tools) for Windows, scripts, and AI agents.
MIT ★ 2