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 Json navigator for allowing Ai using json files > 10MB
★ 1 -
Resource-bounded JSON exploration, result handles, pagination, and path selection for LLMs in MCP.
npm Apache-2.0 -
A Go symbol and call-graph database backed by SQLite. Query symbols, callers, callees, blast radius, dead code, and interface implementors as structured JSON — typed code navigation for AI agents (MCP) and humans.
go Apache-2.0 ★ 18 -
Give your coding agent a map: local repository context, code graphs, stateful navigation and JSON-LD evidence through 18 stdio MCP tools.
NOASSERTION -
A read-only MCP server that lets AI coding agents navigate .NET code the way the compiler sees it. It loads a solution into Roslyn and answers who calls a method, what implements an interface or what breaks when a signature changes, with short, capped JSON. Symbols from NuGet packages and the framework are decompiled to C#, and file edits are picked up live.
nuget MIT -
Structure-aware tools for AI agents. Tree-sitter code editing, web page navigation, search. No daemon, no JSON, just stdin.
go MIT ★ 5 -
IDE-style navigation for structured data — code, JSON, YAML. Jump to definitions, find callers, follow references. Available as an MCP server or a mounted folder.
go Apache-2.0 ★ 46 -
A typed node graph for n8n workflows. Lets AI agents and humans navigate, check and safely rename nodes with far fewer tokens than raw JSON. CLI, MCP server and offline graph viewer.
npm MIT ★ 4 -
Local MCP server (stdio) that extracts live pages and multi-step flows into compact Semantic JSON with Playwright-native locators, observed behavior (navigations, requests) and snapshot diffs, for consistent AI-generated Playwright tests.
npm MIT -
Business data as geometry that AI agents navigate: an MCP server for anomaly, drift, root-cause and chain investigation. Stdio or local HTTP, snapshot sessions, branches, compact JSON for agent context.
Apache-2.0 -
DaemonsMCP is a comprehensive C# MCP service that provides LLMs with secure, full-featured access to explore, read, and write to local codebases. Built on MCPSharp for reliable transport and JSON-RPC communication, it gives your AI assistant the ability to see, navigate, understand, and modify your project files just like a developer would.
MIT ★ 6 -
YouTube Metadata — FlashDatano update data
# YouTube Metadata — FlashData Read YouTube video details, descriptions, statistics and available chapters. Inspect formats or prepare timestamped chapter navigation. Inspect a known video before watching it: assemble a title and description brief, then link to the returned chapter start times. [YouTube Metadata API documentation and examples](https://flashdata.dev/docs/sources/youtube_metadata?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_metadata-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Metadata listing](https://smithery.ai/servers/flashdata/youtube-metadata) 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_metadata`. 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 current account-plan rate. Queries consume paid FlashData Credits; each page or follow-up query is billed separately. 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_metadata` without submitting a data query. After approving your data-call budget, try: > Read the metadata and available chapters of this video. Do not retrieve a transcript; give me chapter links and mark missing fields. This server exposes `youtube_metadata`, `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 is an 11-character YouTube ID. include_formats and include_chapters are booleans, both default true. Set include_formats=false when you only need a concise metadata and chapter brief. 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_metadata", "arguments": { "video_id": "dQw4w9WgXcQ", "include_formats": false, "include_chapters": true } } ``` ## Work with the output Read results[0], including title, description and chapters when present. Pair chapter start_time/end_time with the video watch URL to prepare a navigation brief. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "source": "youtube_metadata", "status": "done", "results": [ { "videoId": "dQw4w9WgXcQ", "title": "Example video", "channel": "Example", "channelId": "channel-one", "channelUrl": "https://www.youtube.com/@Example", "viewCount": 100, "duration": 90, "chapters": [ { "title": "Introduction", "start_time": 0, "end_time": 30 } ], "description": "Example description" } ], "created_at": "2026-10-12T00:00:00Z", "http_status": 200, "request_id": "fixture-request" } ``` ## Limits and result handling Fields and chapters may be absent. Metadata does not include a transcript; transcript retrieval is a separate paid call. 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 -
The SeaLagom API kit: OpenAPI spec, JSON schemas, Python and JavaScript clients, MCP server, tool definitions for every AI platform, scripts for any system
NOASSERTION -
Code-intelligence engine for AI coding agents — single Rust binary indexes any repo into a queryable graph over MCP, CLI, and JSON.
Apache-2.0 ★ 4 -
Heuristic C/C++ project scanner and local workbench: inventory, SQLite index, five relationship graphs, CLI, and MCP. compile_commands.json only supplies include paths. Not a compiler, and not C++ Insights.
Apache-2.0 -
codebeamgithub.com/clement-tourriere/codebeamupdated this year
Local-first code search engine with a web UI, MCP server, and JSON API — lexical (Zoekt), symbol (ctags), and structural (ast-grep) search across your GitHub, GitLab, and local repositories. Single self-contained binary.
MIT ★ 4 -
Static code map generator (MAP.md + map.json) powered by tree-sitter — a Claude Code /map plugin and MCP server that gives coding agents call graphs, file outlines, and impacted-test lookups without spending tokens on parsing.
pypi MIT ★ 6 -
A local-first code map for humans and AI. One scan → one bundle.json: browse it as a map in your browser, or query it over MCP to save tokens (32 code languages + 6 file-level formats, plus .dll/.exe/.jar via built-in decompilers). Single exe, nothing to install.
MIT ★ 3