Canvas AIGC
A MCP server that bridges web canvas with local Codex/Claude, exposing 23 tools for reading, creating, modifying, connecting, and generating canvas content via local HTTP bridge and stdio MCP.
README
Canvas AIGC
Canvas AIGC 是连接网站、网页画布与本机 Codex / Claude 的 MCP 服务。v0.3 通过本地 HTTP 桥接按浏览器会话隔离网站和画布状态,并通过 stdio MCP 暴露 38 个画布及站点工具。
环境要求
- Node.js 18 或更高版本
- 已安装并登录 Codex CLI,或已配置 Claude Agent SDK 所需凭据
- 本地 Infinite Canvas 默认运行在
http://localhost:3000
快速启动
直接启动本地桥接服务:
npx -y github:3108482409song-commits/Canvas-AIGC
默认输出:
Canvas AIGC
Local URL: http://127.0.0.1:17371
Connect token: <token>
配置保存在 ~/.canvas-aigc/config.json。服务只监听 127.0.0.1,网页必须携带正确 token,首次成功连接后会记录允许访问的网页 Origin。
Codex MCP
codex mcp add canvas-aigc -- npx -y github:3108482409song-commits/Canvas-AIGC mcp
MCP 启动时会自动检测并拉起本地 HTTP 桥接服务,不需要另外启动第二个进程。注册或更新后需要开启新的 Codex 对话加载工具。
也可以在 ~/.codex/config.toml 中手动配置:
[mcp_servers.canvas-aigc]
command = "npx"
args = ["-y", "github:3108482409song-commits/Canvas-AIGC", "mcp"]
startup_timeout_sec = 60
tool_timeout_sec = 90
Claude MCP
claude mcp add --scope user --transport stdio canvas-aigc -- npx -y github:3108482409song-commits/Canvas-AIGC mcp
主要工具
site_navigate、canvas_list_projectsworkbench_image_get_config、workbench_image_generateworkbench_video_get_config、workbench_video_generateprompts_search、assets_list、assets_addcanvas_get_capabilities、canvas_list_sessions、canvas_use_sessioncanvas_get_state、canvas_get_selection、canvas_export_snapshotcanvas_get_nodescanvas_create_node、canvas_create_text_node、canvas_create_text_nodescanvas_create_image_prompt_flow、canvas_create_generation_flowcanvas_generate_text、canvas_generate_image、canvas_generate_video、canvas_generate_audiocanvas_update_node、canvas_move_nodes、canvas_resize_nodecanvas_delete_nodes、canvas_connect_nodes、canvas_select_nodescanvas_set_viewport、canvas_run_generation、canvas_apply_opscanvas_get_generation_status、canvas_wait_generation、canvas_cancel_generation
画布写入仍由网页 Agent 侧边栏按手动或自动模式处理,MCP 不绕过确认流程。每次画布写入都校验目标会话和 revision,批量操作返回逐项结果;生成工具只表示任务已排队,需要通过状态或等待工具取得真实结果。生成流程会创建提示词文本节点和对应的文本、图片、视频或音频目标节点,不再创建配置节点。导演台节点可以读取,但不能通过 MCP 创建。
站点工具由当前已连接的网页会话执行,不要求页面处于画布,也不参与画布 revision 或生成任务记账。离开画布页面后,服务会清除该网页会话旧的画布上下文,后续画布工具会明确拒绝执行,直至网页重新进入画布并上报状态。
本地开发
npm install
npm run dev
源码位于 src/,协议层使用官方 @modelcontextprotocol/sdk,工具入参使用 zod 校验。
License
AGPL-3.0-only。维护与派生说明见 NOTICE。
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.