"Local AI Agent Toolkit" matching MCP servers:

A private-by-default, local-first DAG editor that lets you build causal diagrams visually, validate cycles, and save/export as JSON, SVG, or PNG through MCP tools.

Enables AI agents to maintain a living flowchart of a project with 14 MCP tools, auto-layout, and a zero-dependency HTML viewer, providing visual status tracking with 7 color-coded states.

Enables AI coding agents to design, analyze, and evaluate agent system designs against a curated catalog of agent patterns, with retrieval, scoring, and refinement workflows.

A TypeScript stdio MCP server that lets agents read, import, propose connections for, and apply optimistic patches to versioned agent-draw diagram documents.

Enables coding agents to write repository documents (READMEs, RFCs, design docs, ADRs) from verified codebase facts, using a separate model for drafting and agent fact-checking for accuracy.

An MCP server that builds a local webpage to view AI plans, reports, and diagrams, so the AI only needs to send a URL pointer instead of long text. It provides three tools (view_plan, view_report, view_diagram) and tracks project changes for diff viewing.

🐍 🏠 - Code graph for AI agents over MCP: resolves Python and TypeScript calls to fully qualified names and reports the share it could not resolve instead of guessing. Multi-hop impact analysis, authz reachability audit, architectural drift against declared patterns. Local, SQLite. uvx codegraph-brain

Enables AI agents to generate and edit draw.io diagrams with real-time browser preview.

Enables auto-configuration and validation of React components against a glassmorphic design token system using an AST correction engine. It supports managing UI presets, enforcing design uniformity in Monaco IDE, and exporting tokens as CSS, Tailwind, or JavaScript variables.

Model Context Protocol (MCP) server for @imqueue — lets AI coding agents (Claude Code, Cursor and others) search the docs, scaffold typed services & clients and use @imqueue/cli live.

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

MCP server for AI Diagram Maker — generate software engineering diagrams from natural language, code, ASCII diagram, images, or Mermaid. Inline diagram rendering using MCP apps UI and diagram URL in responses. Works with Cursor, Claude Desktop, Claude Code, and any MCP-compatible AI.

diagramzu-mcp lets an AI client (Claude, Cursor, ChatGPT, etc.) author Mermaid diagrams in a shared workspace that a team can read, comment on, embed, and present at a clean URL — rather than just generating a one-off diagram. Hosted endpoint https://mcp.diagramzu.ai/mcp or local npx -y @diagramzu/mcp. Also listed in the official MCP registry as ai.diagramzu/mcp.

Connects Claude directly to Godot 4 projects to read and manipulate scenes, nodes, scripts, and assets within the editor. It enables real-time scene tree management, script editing, and resource configuration through a local Node.js bridge and GDScript plugin.

Generates engineer-grade SaaS specifications — design systems, database schemas, and RLS policies for AI build tools like Lovable, Cursor, and Claude Code. 4 tools, TypeScript, MIT licensed.

A comment-based spec-driven development MCP server that facilitates workflows from requirements creation to implementation via AI, using @spec-impl markers.

Provides design pattern templates and anti-pattern guidance to AI coding agents for correct pattern implementation.

Analyzes a local codebase and exposes its structure, per-file summaries, dependency graph, and complexity hotspots as tools for MCP clients like Claude.

Extracts deterministic architecture maps from codebases for AI agents, enabling queries about blast radius, routes, security findings, and production readiness without sending code anywhere.

An MCP server that lets AI agents drive FigJam boards through a local Figma plugin, bypassing API rate limits with 19 tools for reading, writing, and editing FigJam content.