Index / MCP servers / io.github.AvatarGaia/canvas-mcp

io.github.AvatarGaia/canvas-mcp MCP server

io.github.AvatarGaia/canvas-mcp is a remote MCP server that gives an AI agent 13 tools, among them canvas_action, get_job, get_session_log. It answers at https://agent.avatargaia.top/api/mcp/canvas over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 5 of 5 times since 12 September 2026; the last check, on 18 October 2026, succeeded.

Status

Answering

Tools

Reliability

5 of 5 checks

Response time

3306 ms

Transport

streamable HTTP

Last checked

18 October 2026

TeamAgent Canvas MCP（服务端 0.4.0）：91 个工具——开岗、改配置、跑动作、看数据、发布并配知识库。可匿名试用，带 Key 解锁全部。

Description as the publisher wrote it.

The 13 tools io.github.AvatarGaia/canvas-mcp offers

Tool	What it does
`canvas_action`	执行一个岗位动作（如 AICare 的 preflight / list_checks / gen_report / run_detection / resolve_user）。参数：slug、action 必填；params 按 list_actions 的 schema 填；session_id 想让结果落在某次会话里就带；hostUserId 宿主用户标识可选。返回 {ok, mode:"sync", data} 直接用；{ok, mode:"job", jobId, Inputs: slug, action, params, session_id, hostUserId
`get_job`	按 job_id 查长任务：queued / running / done(带 result) / failed(带 error)。建议每 3 秒查一次。error 是人话（如"关爱对象不存在或已删除"），照原话转述给用户，不要改写成"系统繁忙"，也不要拿同参数重试。 Inputs: job_id
`get_session_log`	单个会话按时间正序的完整流水：用户消息 / AI 回复(带 tokens) / 埋点 / 动作调用 / 推屏。参数：slug 和 session_id 两个都必填（slug 用于显式鉴权）。调用前先从 list_sessions 或 open_canvas 拿到合法 session_id。隐私边界：只能读自己岗位的记录。需要有效 Key，匿名不开。 Inputs: slug, session_id
`get_staff_config`	读岗位配置：personaPrompt / serviceFlow / promotionConfig / productSources / contextMode / layoutStyle / templateId / llmMode（只说是否 BYOK，不给密钥）/ tts。参数：slug 必填。改之前先读，否则会用"想当然的人设"覆盖客户调过的版本。 Inputs: slug
`get_stats`	岗位一段时间的汇总：会话数、真人对话轮数、埋点数、动作调用数、tokens、按日曲线。参数：slug 必填；from/to ISO 时间，默认最近 30 天。用户问"这岗位最近怎么样/今天多少人来"就用它，不要靠聊天历史猜数字。需要有效 Key，匿名不开。 Inputs: slug, from, to
`list_actions`	列出这个岗位（按其模板）能做的动作：id / title / description / cost / credits / anonymous / job / params(JSON Schema)。参数：slug 必填。调 canvas_action 前先调它，不要猜 action 名——各岗位动作集不同，params 按它给的 schema 填。 Inputs: slug
`list_my_staff`	列出我名下的数字员工岗位（slug / 名称 / 模板 / 画布链接）。用户问"我有哪些岗位"用它；后续所有按岗位操作的工具都要 slug，slug 一律从这里拿，不要凭记忆拼。参数：无。
`list_sessions`	岗位的访客会话列表（最近优先）：session_id、宿主用户标识、轮数、时间。参数：slug 必填；q 按宿主用户标识模糊搜；from/to；limit；cursor 翻页传上一页返回的 nextCursor。想看"最近都服务了哪些人"用它，再拿 session_id 看明细。需要有效 Key，匿名不开。 Inputs: slug, q, from, to, limit, cursor
`list_templates`	列出可开岗的数字员工模板。用于：想知道"系统能开哪些岗位"、或用户要开通新岗位时。返回每个模板的 templateId / 名称 / 说明 / canOpen / missingHandlers / 动作清单。别用它找"已开好的岗位"——那是 list_my_staff。canOpen=false 的模板不可开通（缺实现），别推荐用户选。参数：无。
`open_canvas`	为岗位生成画布链接 + 会话 ID。用于用户需要"看得见的界面"（看报告/看商品/做检测）。参数：slug 必填；hostUserId 宿主用户标识（强烈建议带，会话归属和离线补推都靠它）；targetId 关爱/业务对象；app 指定画布页（如 aicare-kf）。返回 {url, session_id}——把 session_id 存下来，get_session_log / push_screen 都用它。会话在返回时已建立：现在就能 push_screen 给"还没来 Inputs: slug, hostUserId, targetId, app
`patch_staff_config`	局部修改岗位配置，patch 只放要改的字段：personaPrompt(人设) / serviceFlow(服务流程，一行一步) / promotionConfig({categories:[{name,priority,url}]}) / productSources([{key,label,searchUrl,weAppId?,weAppUsername?}]) / layoutStyle(split\|pip\|classic) / contextMode(inline\| Inputs: slug, patch
`push_screen`	把内容推到某个画布会话的屏上。参数：session_id 必填（来自 open_canvas 或 list_sessions）；content 必填，写成一条"助手回复"文本，可含 ```canvas-md（Markdown 卡片）/ ```canvas-html（完整 HTML 文档）/ ```canvas（JSON 块）围栏，围栏外文字显示为字幕；speak=true 朗读字幕；title 可选。会话在线立即上屏；不在线（含还没人打开过的）存为待展示，该会话或同岗位同一 Inputs: session_id, content, speak, title
`query_events`	跨会话按类型拉事件（倒序）：type = chat_user / chat_assistant / track / action_call / page_open / push。参数：slug 必填；type、from/to、limit(≤500)。每条带 source（mcp / page / server，看得出谁发起的）；action_call 的 payload 有 params/ok/ms/credits/cached/jobId——计费与排障的证据链；push 的 Inputs: slug, type, from, to, limit

Add io.github.AvatarGaia/canvas-mcp to your AI client

Every block below points at https://agent.avatargaia.top/api/mcp/canvas. Pick your client and copy.

Claude Code: one command in your terminal

claude mcp add --transport http io-github-avatargaia-canvas-mcp https://agent.avatargaia.top/api/mcp/canvas

Claude Desktop: claude_desktop_config.json

{
  "mcpServers": {
    "io-github-avatargaia-canvas-mcp": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://agent.avatargaia.top/api/mcp/canvas"]
    }
  }
}

Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json in a project

{
  "mcpServers": {
    "io-github-avatargaia-canvas-mcp": {
      "url": "https://agent.avatargaia.top/api/mcp/canvas"
    }
  }
}

VS Code and GitHub Copilot: .vscode/mcp.json

{
  "servers": {
    "io-github-avatargaia-canvas-mcp": {
      "type": "http",
      "url": "https://agent.avatargaia.top/api/mcp/canvas"
    }
  }
}

Zed: Zed settings.json

{
  "context_servers": {
    "io-github-avatargaia-canvas-mcp": {
      "url": "https://agent.avatargaia.top/api/mcp/canvas"
    }
  }
}

Windsurf: ~/.codeium/mcp_config.json

{
  "mcpServers": {
    "io-github-avatargaia-canvas-mcp": {
      "serverUrl": "https://agent.avatargaia.top/api/mcp/canvas"
    }
  }
}

JetBrains AI Assistant: Settings, Tools, AI Assistant, MCP, New MCP Server, as JSON

{
  "mcpServers": {
    "io-github-avatargaia-canvas-mcp": {
      "url": "https://agent.avatargaia.top/api/mcp/canvas"
    }
  }
}

Continue: .continue/mcpServers/neuronto.yaml

name: io.github.AvatarGaia/canvas-mcp
version: 0.0.1
schema: v1
mcpServers:
  - name: io.github.AvatarGaia/canvas-mcp
    type: streamable-http
    url: https://agent.avatargaia.top/api/mcp/canvas

Gemini CLI: ~/.gemini/settings.json

{
  "mcpServers": {
    "io-github-avatargaia-canvas-mcp": {
      "httpUrl": "https://agent.avatargaia.top/api/mcp/canvas"
    }
  }
}

Codex CLI: MCP server config

{
  "mcpServers": {
    "io-github-avatargaia-canvas-mcp": {
      "type": "http",
      "url": "https://agent.avatargaia.top/api/mcp/canvas"
    }
  }
}

Warp: MCP servers, + Add, paste JSON

{
  "mcpServers": {
    "io-github-avatargaia-canvas-mcp": {
      "url": "https://agent.avatargaia.top/api/mcp/canvas"
    }
  }
}

Goose: a one-click extension link

goose://extension?url=https%3A%2F%2Fagent.avatargaia.top%2Fapi%2Fmcp%2Fcanvas&type=streamable_http&id=io-github-avatargaia-canvas-mcp&name=io.github.AvatarGaia/canvas-mcp

Is io.github.AvatarGaia/canvas-mcp up right now?

It answered our last check on 18 October 2026 in 3306 ms. Over 5 checks since 12 September 2026 it answered 5. Status here comes from Neuronto's own probes, not from the publisher.

MCP servers similar to io.github.AvatarGaia/canvas-mcp

Remoet24 tools Tldraw6 tools Pocket Agent4 tools MCP Knowledge279 tools Developer Toolkit2 tools Server4Agent0 tools

Questions about io.github.AvatarGaia/canvas-mcp

How many tools does io.github.AvatarGaia/canvas-mcp have?

13, as returned by the server's own tools/list on 24 September 2026: canvas_action, get_job, get_session_log, get_staff_config, get_stats, list_actions, list_my_staff, list_sessions, and 5 more.

Is io.github.AvatarGaia/canvas-mcp down?

It answered our last check on 18 October 2026 in 3306 ms. Over 5 checks since 12 September 2026 it answered 5.

How do I add io.github.AvatarGaia/canvas-mcp to Cursor?

Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://agent.avatargaia.top/api/mcp/canvas. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.

Does io.github.AvatarGaia/canvas-mcp need an API key?

It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.

Where this comes from

Publisher: io.github.avatargaia. Endpoint host: agent.avatargaia.top. ARD identifier: urn:air:io.github.avatargaia:mcp:canvas-mcp. First indexed 12 September 2026. The tools are exactly what the server returned; nothing on this page is inferred from its name. Ranking in Neuronto search is never for sale.

Is this your server? Get a message the day it stops answering or its tools change: monitoring, 14 days free. Or claim the domain to manage how it is listed.