stdio shim for TeamAgent Canvas MCP (数字员工能力) — 把仅支持 stdio 的 MCP 客户端接到 streamable-http 端点
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Documented (README)
git clone https://github.com/AvatarGaia/canvas-mcpTools overview
# @avatargaia/canvas-mcp
**stdio 马甲**:让只支持 stdio 的 MCP 客户端(Claude Desktop / Cursor / 各类本地 Agent)接入 TeamAgent 的 Canvas MCP(`streamable-http`)。
纯转调,无状态、不缓存、不改写请求。
## 用
```bash
CANVAS_MCP_URL=https://agent.avatargaia.top/api/mcp/canvas \
CANVAS_MCP_TOKEN=ta_xxxxxxxx \
npx -y @avatargaia/canvas-mcp
```
客户端配置(Claude Desktop `claude_desktop_config.json` 为例):
```json
{
"mcpServers": {
"teamagent-canvas": {
"command": "npx",
"args": ["-y", "@avatargaia/canvas-mcp"],
"env": {
"CANVAS_MCP_URL": "https://agent.avatargaia.top/api/mcp/canvas",
"CANVAS_MCP_TOKEN": "ta_xxxxxxxx"
}
}
}
}
```
## 环境变量
| 变量 | 必填 | 说明 |
|---|---|---|
| `CANVAS_MCP_TOKEN` | 是 | `ta_`(平台令牌)或后续 `dk_`(开发者 Key) |
| `CANVAS_MCP_URL` | 否 | 默认官方端点;自建部署时改这里 |
| `CANVAS_MCP_KEY` | 否 | `CANVAS_MCP_TOKEN` 的别名 |
## 行为
- stdin/stdout 逐行 JSON-RPC 2.0;通知(无 `id`)不回包
- 上游 HTTP 错误**原样透传**成 JSON-RPC error(`401: Missing Authorization header` / `402: …` / `429: …`),客户端能看见真正原因
- 上游返回 SSE 或 JSON 都能解析(取最后一条 `data:`)
- stdin 关闭后等所有在途请求落地再退出
## 验证记录(2026-09-12)
```
initialize ✅ serverInfo teamagent-canvas 0.3.0
tools/list ✅ 13 个工具
tools/call ✅ list_my_staff 返回岗位列表
无令牌 ✅ {"error":{"code":-32000,"message":"401: Missing Authorization header"}}
mcporter 接入 ✅ 作为 stdio server 连上并调用成功
```
## 拿 Key(自助,30 秒)
外部 / 本地 Agent 无需 TeamAgent 账号:
```bash
curl -X POST https://agent.avatargaia.top/api/dev/register \
-H "Content-Type: application/json" \
-d '{"name":"my-agent","email":"you@example.com"}'
# → 返回 dk_ Key(只显示一次)+ 20 credits + 接入信息
```
- 开发者入口(控制台 / 计费 / 错误码):https://agent.avatargaia.top/developers
- 机器可读自描述(Agent 自发现首选):`GET https://agent.avatargaia.top/api/dev`
## 收录
- 官方 MCP Registry:`io.github.AvatarGaia/canvas-mcp`
- 接入文档:https://agent.avatargaia.top/mcp/canvas.html | LLM 索引:/llms.txt
What people ask about canvas-mcp
What is AvatarGaia/canvas-mcp?
+
AvatarGaia/canvas-mcp is tools for the Claude AI ecosystem. stdio shim for TeamAgent Canvas MCP (数字员工能力) — 把仅支持 stdio 的 MCP 客户端接到 streamable-http 端点 It has 0 GitHub stars and its last recorded update is dated 2026-09-12.
How do I install canvas-mcp?
+
You can install canvas-mcp by cloning the repository (https://github.com/AvatarGaia/canvas-mcp) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is AvatarGaia/canvas-mcp safe to use?
+
Our security agent has analyzed AvatarGaia/canvas-mcp and assigned a Trust Score of 87/100 (tier: Trusted). See the full breakdown of passed checks and flags on this page.
Who maintains AvatarGaia/canvas-mcp?
+
AvatarGaia/canvas-mcp is maintained by AvatarGaia. The last recorded GitHub activity is dated 2026-09-12, with 0 open issues.
Are there alternatives to canvas-mcp?
+
Yes. On ClaudeWave you can browse similar tools at /categories/tools, sorted by popularity or recent activity.
Deploy canvas-mcp to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/avatargaia-canvas-mcp)<a href="https://claudewave.com/repo/avatargaia-canvas-mcp"><img src="https://claudewave.com/api/badge/avatargaia-canvas-mcp" alt="Featured on ClaudeWave: AvatarGaia/canvas-mcp" width="320" height="64" /></a>More Tools
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
Use Claude Code, Codex, Pi, and OpenCode (and 6 other harnesses) for free (1.3B+ free tokens) from your terminal, app, IDE, or phone, and now from the browser with native browser sessions (multi-harness + multi-model) like OpenClaw (voice supported + ToS friendly)