JointJS MCP Server

The JointJS MCP Server gives your AI coding assistant direct access to up-to-date JointJS documentation, API references, and working demo code. Instead of relying on the AI's training data — which has a knowledge cut-off and may reflect outdated APIs — the server queries a continuously updated hybrid search index (semantic + keyword) built from the official JointJS documentation and demo repositories, optimised for accurate, LLM-friendly retrieval.

- Always current.Documentation is kept up-to-date in a dedicated index, so you get the latest API changes, deprecation notices, and migration guides — not a frozen snapshot from the model's training window.
- Versioned.Every query can be scoped to a specific JointJS version, so the assistant gives answers that match the version you are actually using.
- Reduces hallucination.The assistant grounds its answers in retrieved source text rather than recalling potentially incorrect training data about JointJS internals.
- Demo-first workflow.Full, runnable demo projects are indexed and retrievable by framework (TypeScript, JavaScript, React, Angular), so you can paste working code directly into your project.
- No setup cost.The server is hosted athttps://mcp.jointjs.com/mcp— there is nothing to install or maintain on your end.

- Claude Desktop
- Claude Code (CLI)
- Cursor
- VS Code (Copilot)
- OpenAI Codex / ChatGPT
- Other clients
- Open Settings → Connectors.
- Click Add custom connector.
- Enterhttps://mcp.jointjs.com/mcp.
- Save/enable it.

The server exposes the tools listed below. The AI assistant invokes them automatically when it determines they are relevant, but you can also prompt it explicitly (e.g. "search the JointJS docs for...").

Search JointJS documentation, API reference, guides, and migration notes using a natural-language query.

When to use:conceptual questions, API option semantics, compatibility guidance, migration notes, or any question whose answer is best found in prose documentation.

Retrieve the full Markdown content of a specific documentation page by its path.

When to use:whensearch_docsreturns a filename you want to read in full, or when you know the exact path of a documentation page.

Search JointJS demo projects and example code using a natural-language query. Returns a ranked list of demos withdemo_idvalues you can pass toget_demo_code. The AI assistant automatically selects and calls these tools when relevant. You can optionally guide it with prompts like: "Search JointJS demos for...".

When to use:when you want a complete, runnable example or need to see how a feature is implemented end-to-end.

Retrieve all source files of a JointJS demo. Text files (.ts,.tsx,.js,.jsx,.json,.md,.css,.html) are returned inline; binary assets (fonts, images) are returned as GitHub links.

Very large demos may be truncated depending on the client's context limits.

When to use:aftersearch_demosidentifies a relevant demo, call this tool to fetch its full source so the assistant can adapt it for your project.

List all JointJS documentation versions available on the server.

When to use:to discover which version strings are valid for theversionparameter ofsearch_docsorsearch_demos.

- Ask specific, implementation-focused questions

"How do I add a collapsible minimap in my JointJS diagram?"

"Explain how link validation works and show a demo"

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Local stdio MCP server that lets AI coding agents read and maintain structured architecture, rules, and decisions directly from your repository.

Official Context7 MCP server that brings up-to-date, version-specific library documentation and code examples into AI coding prompts.

Remote, no-auth MCP server providing AI-powered codebase context and answers

Official Svelte MCP server, provides docs and suggestions on the generated code.

Documentation and assembly review for @nhtio/adk.

Structured .aide spec files that give AI agents progressive disclosure into your codebase architecture. 6 MCP tools, 8 slash commands, TUI wizard, multi-IDE support.

Assists AI developers with requirement clarification, module design, and technical architecture.

AmazingMCP — MCP Server for .NET / C# Codebases

An MCP server that gives AI agents deep understanding of C# codebases via Roslyn — type search, dependency graphs, usage analysis, and architecture overviews, all from a live in-memory compilation.

Automatically generates documentation for code repositories by analyzing directory structures and code files using the OpenRouter API.

MCP server that ingests project docs once and lets Claude search by meaning instead of reading everything — saving tokens on large codebases