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.
-
Server-side form sessions: load, edit and save schematized JSON documents through json-layout MCP tools.
npm MIT -
MCP server for creating and editing Elastic Dashboard layout JSON files
npm MIT -
Read and edit Simulink .slx models without MATLAB. A plugin for Claude Code, Codex, CodeBuddy and Qoder with two MCP servers: slxread parses structure, parameters, wiring, Stateflow and layout, with semantic diff; slxwrite builds or patches models from JSON specs and tidies layouts.
★ 1 -
Official TypeScript SDK, CLI, and MCP server for Apiryner — JSON layout-based random data generation API
npm MIT -
Semantic linter and layout formatter for n8n workflow JSON: CLI, MCP server and rule-author API in one package
npm MIT -
CLI + MCP server that mutates Construct 3 projects (event sheets, layouts, objectTypes) stored as on-disk JSON, via SID-addressed recipes and a read-side extracted/ generator pipeline.
npm MIT-0 -
MCP server for managing JSON translation files. Query, set, add, delete, rename, move, list, and search i18n keys across locales — designed for AI agents like Claude Code and Cursor. Supports flat and namespaced (i18next-style) directory layouts.
npm ★ 2 -
Interactive, step-by-step diagrams and one-page answers from JSON: automatic layout, orthogonal edge routing and a validator. One offline HTML file; CLI, MCP server and browser playground.
npm MIT -
network-diagram-mcpgithub.com/den-indance/network-diagram-mcpupdated this year
MCP server that lets AI agents (Claude, Cursor, Claude Desktop) build and edit network topology diagrams in NetMap. 44 tools: CRUD, multi-sheet, nmap/CSV import, smart auto-layout, one-click SSH/web, JSON/PNG/PDF export. Open-source successor to netViz.
npm MIT ★ 4 -
NetMap — Network Diagram MCPno update data
Visual network topology editor with AI agent integration via the Model Context Protocol. Open-source successor to netViz (CA Technologies, 1990–2012). Try it live: https://map.den.dance/ What makes it different: • One-click ops dashboard — click any web port (80/443/8080/…) on a node card to open the service in a new tab. Click an SSH port to drop `ssh user@host -p port` into your clipboard AND launch your system SSH handler (Terminal/iTerm/Termius/PuTTY). Your diagram is also your jump host. • AI agents edit the map — 44 MCP tools. Claude / Cursor / Claude Desktop session can build a diagram for you, search across nodes/ports/notes, run smart auto-layouts, export PNG/PDF — all by talking to the open browser tab. • `nmap -oX` import — run a network scan, hand the XML to the agent, get a map with nodes auto-typed from OS fingerprint + port profile (router/switch/firewall/server/printer/…). • CSV inventory import — drop in your asset spreadsheet, auto-detects columns (name/ip/type/ports/notes; aliases like `hostname`/`description` accepted). • Operator-grade node cards — per-node: open ports with service names, Docker services, DNS domains, free-form notes. All searchable cross-entity via the agent. • Smart auto-layout — force-directed (deterministic via seed), cluster-by-type, cluster-by-connection. • Multi-sheet, local-first — multiple maps in one workspace, everything in localStorage. No login, no cloud. Export JSON/PNG/PDF.
smithery -
MCP tools for AI agents from OpenAPI documents annotated with x-agent
npm AGPL-3.0-only -
frameforgegithub.com/pedroanisio/frameforgeupdated this year
FrameForge aims to be an agent-native visual-authoring tool — one structured, programmable foundation (SDK + MCP) for producing professional visual assets across documents, decks, diagrams, books, and letters today, extending toward UIs, vector graphics, logos, and design systems.
MIT -
Turn images into structured information for AI agents. OCR, image understanding, colours, layout, CLI and MCP.
Apache-2.0 -
Browser-based RDF/ontology knowledge graph editor — load RDF from files, URLs or SPARQL endpoints; author nodes and edges on the canvas; run OWL-RL reasoning; apply multi-algorithm layout and clustering. AI-native via MCP tool surface and relay bridge. Fully client-side, no backend required.
NOASSERTION ★ 265