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.
-
A live layered dependency map for bottom-up development — MCP server + terminal pane. Ghost the design first, then light nodes up from the bottom as they are built and verified.
npm MIT -
A live layered dependency map for bottom-up development — MCP server + terminal pane for Claude Code, Codex CLI and any MCP client. Ghost the design first, light nodes up as they are built and verified.
npm MIT ★ 116 -
Themeable SVG maps with zero runtime dependencies: Malaysia's 16 regions and 159 districts, a rotating globe, country maps. Library, CLI, MCP server, plain SVG/GeoJSON.
NOASSERTION -
A screen ↔ endpoint ↔ field dependency map: answers which screens break if you change an endpoint or a response field. Local-first, git-friendly, open source.
npm MIT -
clarityaui-mcpactive
Ask any codebase's structure over MCP — deterministic concept map, real dependency evidence, in seconds. Local, offline, no LLM, no API key. `npx clarityaui-mcp <repo>`.
npm SEE LICENSE IN LICENSE -
Understand any codebase: interactive dependency map, blast-radius analysis, CI drift gates and an MCP server for AI coding assistants. Offline, zero deps.
MIT ★ 1 -
reporosegithub.com/mibrahimpro/reporoseupdated this year
Repository scanner that builds a structural map of a codebase (functions, imports, exports, dependencies) and adds file descriptions of what the file does,, so anagentic AI can just read the map and know the project context
npm GPL-3.0-or-later -
Interactive, themeable SVG map of Malaysia (16 states + 159 districts) — library, CLI, and MCP server. Zero runtime dependencies.
npm MIT -
Local context cache and code map for AI agents, written in Rust. 100% offline, zero dependencies. MCP server included.
MIT ★ 2 -
A live, editable map of a .NET solution: projects, dependency injection, endpoints and request flows in one page.
MIT -
Multi-language repository map for agents and humans: MCP tools, dependency graphs, symbol indexes, impact review, and bounded source evidence.
npm MIT -
Give humans and AI agents the same map of your codebase: dependency graph, complexity and code-smell metrics, MCP server. Ten languages, Rust engine, VS Code + CLI.
AGPL-3.0 -
🔐 The secrets manager that understands your dependency graph. Maps Issuer → Credential → Project → Deployment → URL. Detects supply-chain risk in npm/Cargo deps. Free, open source, works offline.
AGPL-3.0 -
Open-source, local code intelligence and dependency graph for cross-repository impact analysis. Map APIs, events, schemas, packages, databases, and ownership for AI coding agents via MCP.
NOASSERTION ★ 4 -
Index maps your code offline: how your repositories depend on each other, what calls what inside a repo, and which docs describe which code, as HTML files you open in a browser.
pypi NOASSERTION ★ 4 -
Your codebase companion for JavaScript/TypeScript, in the browser, the terminal and your AI agent: a live dependency map, impact and call sites, affected tests and patch coverage, review order, new-only CI gates (SARIF, GitLab), git hooks, a status line a
npm MIT -
A living architecture map of any codebase, derived from its import graph and commit history: what depends on what, what changes together, and who knows the part you are about to touch. A VS Code extension and an MCP server. Nothing to write, nothing to keep up to date.
MIT -
The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Cut agent token costs by finding code without reading the repo, then keep large codebases off the complexity wall: blast radius, tests to run, quality deltas as you write. Every guess labelled, every loss published. Paddle out with a map.
Apache-2.0 ★ 2,543 -
hydragithub.com/iiTzGedo/hydraupdated this year
Make your homelab infrastructure queryable by AI. Profile compute, IoT, and network devices to enable intelligent capacity planning, dependency mapping, and operational insights.
★ 1 -
AiCodelensegithub.com/njaju021/AiCodelenseupdated this year
Give AI coding agents a map before they read your code. Statically maps your codebase structure and dependencies, enriches components with LLM summaries, and links Git commits/Jira tickets to nodes. Optimizes agent context windows and token usage with compact, queryable JSON blueprints.
★ 2 -
specdaggithub.com/japorto100/specdagupdated this year
A CLI and MCP server for validating, assembling, and rendering dependency maps in Event-Spec-Driven Development (ESDD)
-
Agentic toolchest for deconstructing codebases. MCP server + CLI analyzers for boundaries, dependencies, interfaces, and code maps. Pure Python, zero deps.
Apache-2.0 -
A Python AST Model Context Protocol (MCP) server for codebase architecture inspection, symbol search, import dependency mapping, and docstring coverage auditing.
-
CLI, MCP and TS library that turns source code into a map of files, symbols, references, and dependencies using tree-sitter.
npm MIT ★ 9 -
Auditable code intelligence for AI agents - map dependencies, predict change impact, select the right tests, and verify refactors before they ship.
AGPL-3.0 ★ 32 -
Airframe UI MCP — stdio server for Cursor, Claude Code, and other MCP hosts. Pattern search, markup validation, token lookup, and theme mapping. Dev dependency or npx.
npm MIT -
Shared memory for AI coding agents over MCP: content-hash file summaries, symbol map, notes, handoffs and agent-to-agent messaging. Zero dependencies, one SQLite file.
MIT -
The architecture diagram that draws itself. Maps every service, database, queue and third-party API in your code, with a link to the line behind each box. CLI, GitHub Action, MCP server. Zero dependencies.
MIT -
Git DAG indexing, AST symbol graphs, and hybrid semantic code search MCP server for AI coding agents (Claude Code, Cursor, Windsurf). Maps repositories into PostgreSQL + pgvector with recursive caller/callee dependency graphs and temporal recency decay.
MIT -
Self-hosted hub for teams using GitHub Spec Kit: a board of every spec in flight, a dependency map, an MCP server for coding agents, and a landing lock so agents take turns landing.
MIT -
⚡ Zero-dependency Model Context Protocol (MCP) Server + Clay.com HTTP API Waterfall Pack + 7 Chained n8n Outbound Workflows for Google Maps, B2B Emails, Ad Pixels, Shopify & Technical SEO ($0.50-$1.50/1k).
MIT -
todo-mcpgithub.com/ks-tool/todo-mcpupdated this year
A backlog and a wiki in one SQLite file — CLI, TUI and MCP server over one core. Tasks with tags and dependencies, markdown wiki pages mapped to tasks both ways, commits linked by scanning git log. Built for a human and an LLM working the same project.
Apache-2.0 ★ 1 -
YouTube Extended Search — FlashDatano update data
# YouTube Extended Search — FlashData Search larger YouTube video result sets, with up to 700 requested results. Map recurring channels and topics from structured video records. Group a larger topic sample by channelId or channelUrl to see which creators appear repeatedly, retaining the underlying video IDs. [YouTube Extended Search API documentation and examples](https://flashdata.dev/docs/sources/youtube_search_extended?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_search_extended-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Extended Search listing](https://smithery.ai/servers/flashdata/youtube-extended-search) 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_search_extended`. 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_search_extended` without submitting a data query. After approving your data-call budget, try: > Search for 100 battery recycling videos, group the observed results by channel, and retain video IDs for later review. This server exposes `youtube_search_extended`, `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 max_results accepts 1–700, default 20. This is the extended-search product with its own higher rate, not repeated standard search or a guarantee of 700 returned records. The same supported filters are available. 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_search_extended", "arguments": { "query": "battery recycling", "max_results": 100 } } ``` ## Work with the output Read results[0].results and group by channelId or channelUrl. Keep the original video IDs and count observed results per channel; retain channel labels for review. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "source": "youtube_search_extended", "status": "done", "results": [ { "results": [ { "videoId": "dQw4w9WgXcQ", "title": "battery recycling", "channel": "Example", "channelId": "channel-one", "channelUrl": "https://www.youtube.com/@Example", "viewCount": 100, "duration": 90 }, { "videoId": "aqz-KE-bpKQ", "title": "battery recycling", "channel": "Example", "channelId": "channel-one", "channelUrl": "https://www.youtube.com/@Example", "viewCount": 100, "duration": 90 } ] } ], "created_at": "2026-10-12T00:00:00Z", "http_status": 200, "request_id": "fixture-request" } ``` ## Limits and result handling The request limit is 700, not a promise of 700 returned videos or pagination. Extended search has its own rate, higher than standard search. 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 -
A live map of how a big codebase fits together, for Claude Code and for you, with a local import index, an MCP server and the Map.
npm MIT -
A map of your codebase for AI agents: code graph, search, call paths and change impact. No API key.
npm MIT -
@codefundi/code-fundi-mcpgithub.com/code-fundi/code-fundi-mcpupdated this year
MCP server for CodeFundi: the codebase map and blast-radius guard for AI coding agents like Claude Code, Cursor, and Copilot.
npm MIT -
See how your code fits together, even as agents keep changing it. A zoomable, evidenced map of your repository: every flow, its Git history and blast radius, explained over MCP.
MIT ★ 22 -
isobaractive
See where the pressure builds in your code: interactive, framework-aware maps of any codebase, an MCP server for Claude and other agents, plus agent-ready graph.json and AGENTS.md (successor to codegraph).
npm SEE LICENSE IN LICENSE -
axon-progithub.com/talhamsajid/axon-proupdated this year
Enterprise-grade graph-powered code intelligence engine. Deep structural awareness for Laravel, PHP, Python, and JS. Powers AI agents with high-fidelity architectural context via MCP & Neo4j.
★ 30 -
See what your AI edits affect. Structural checks for AI code changes. Local call/import graphs and 28 MCP tools for impact, callers, and duplication. No LLM in the checks.
MIT -
See what your AI edits affect. Structural checks for AI code changes. Local call/import graphs and 28 MCP tools for impact, callers, and duplication. No LLM in the checks.
npm MIT -
Stop making your AI re-read your codebase. Stacklit maps your repo once and keeps the map fresh. In a 450-session test, agents ran 82% fewer grep and glob searches. Free, MIT, one Go binary. Sets up Claude Code, Cursor, Codex and 22 more.
npm MIT ★ 131 -
An AI tech lead in server form—this intelligent MCP agent validates your coding agent's strategy, analyzes impact, and catches critical issues before any code is written. Like having a senior engineer review every approach, ensuring thoughtful architecture and fewer regressions.
MIT ★ 7 -
Stacklit: AI Codebase Indexing 2026 – Zero-Setup Local Repo Mapping for Agents
★ 1 -
Index codebases for AI agents with one command. Build a local map of your repository without server requirements or setup.
-
Turn any codebase into an interactive architecture map in seconds. Zero-config CLI + MCP server for Claude Code & Claude Desktop (TS/JS, Python, Go, Rust).
MIT ★ 1 -
@egentica/codemapgithub.com/egentica/codemapupdated this year
A universal suite of MCP-native and node.js API tools for agentic AI, researchers, and developers to map, knowledge-graph, and work with structured code and other artifacts.
npm Apache-2.0 -
MCP server that maps any codebase — files, imports, SQL, APIs, infra — and tells you what a change breaks. On this repo one impact call is ~230 tokens; reading the same nine files is ~22,360. 9 tools, 25 adapters, 11 languages.
MIT -
CodeRadargithub.com/officialCodeWork/CodeRadarupdated this year
React & TypeScript static analysis that maps every UI component to the APIs, state, and events behind it — and serves that context to AI coding agents over MCP. Screenshot or ticket in; component, data lineage, user journeys, and blast radius out. Deterministic, no LLM in the core.
MIT