"Google Chat" matching MCP servers:

Enables AI IDEs to chat with, search, explain, refactor, and audit a local codebase without uploading source code, returning answers backed by file-and-line source citations, confidence scores, and severity labels, plus audit and board-ready strategic reports. Runs locally and standalone as an MCP server compatible with Claude, Cursor, Windsurf, and DeepSeek Harness.

AI-native architecture diagramming for MCP clients (Claude Code, Cursor, Windsurf). The calling agent authors the graph (nodes, groups, edges); Flowgraf validates it, lays it out deterministically with ELK, renders an SVG + Mermaid, and returns a link to a live, editable canvas you can refine by chat, drag, or one-click AI design review. Agent-authored ops — no API key and no LLM cost to the calle

Enables AI coding agents to discover, convert, and synchronize Draw.io C4 and UML diagrams into Mermaid Markdown, providing architectural context and guardrails during chat sessions.

Lets AI agents draw professional cloud architecture diagrams with the official AWS, Azure and Google Cloud icons, from a plain description, a JSON graph or Terraform code.

Exposes the Polaris architectural fitness-function control plane's REST API as grouped MCP tools over stdio, letting agents manage tribes, squads, fitness targets and functions, measurement sources, submissions, evaluations, waivers, insights, and events. Handles Google OIDC login and silent token refresh automatically, and submits measurements with an ingest API key.

Enables AI assistants to visualize cloud architecture diagrams, generate and import Terraform HCL, and manage infrastructure resources directly from chat through the CloudForge platform.

Enables LLMs to create and open diagrams in the draw.io editor, supporting inline chat previews via MCP Apps, direct editor opening with XML/CSV/Mermaid format support, and diagram export to PNG/SVG/PDF or browser URLs through multiple integration approaches.

Turns raw diagram source text into an interactive SVG rendered directly inline in Claude Desktop conversations, with pan, zoom, fit-to-width, copy-source and fullscreen controls instead of a static code block. It runs as a standalone local stdio server available to every conversation, so any diagram definition can be viewed and explored without leaving the chat.

Generate, edit, and export data-architecture diagrams from any MCP client. Typed tables with columns, column-level lineage, real tool icons, PNG export straight back into the chat.

An automated MCP server for Google Stitch that enables AI-driven UI design generation, accessibility audits, and design system management. It streamlines workflows for creating responsive screens, extracting design tokens, and maintaining visual consistency across professional web projects.

Enables AI assistants to generate interactive Excalidraw diagrams with viewport camera control and fullscreen editing directly in the chat.

An automated MCP server for Google Stitch that enables AI-driven UI design generation, screen management, and design system extraction. It provides 19 professional tools for creating consistent web interfaces, conducting accessibility audits, and exporting design tokens.

Enables users to create and interact with hand-drawn Excalidraw diagrams featuring smooth viewport camera control and interactive fullscreen editing. It uses the MCP Apps extension to render collaborative virtual whiteboards directly within supported AI chat interfaces.

Renders charts and diagrams as live interactive UI inside the chat, supporting ECharts for charts and Cytoscape for diagrams with streaming partial updates.

Enables users to create and interact with hand-drawn sketches and architecture diagrams directly within chat interfaces using Excalidraw. It leverages the Model Context Protocol to provide interactive HTML visualizations with smooth viewport control and fullscreen editing capabilities.

CodeGraph MCP is a powerful standalone tool that parses your entire C/C++ codebase into a semantic knowledge graph and seamlessly exposes it to AI coding assistants via the Model Context Protocol (MCP). By providing AI (like Claude Desktop, Cursor, or Google Antigravity) with a structural map of your project—including caller/callee relationships, file dependencies, and dynamic function definition

Enables modular MCP capabilities by organizing tools, resources, and prompts into composable sub-servers, exposed either all-in-one or as separate MCP endpoints.