Is teamagent-canvas live?

Yes — it answered the hub's last check (checked 3h ago). It answered 100% of checks over the last 30 days.

Is teamagent-canvas free to use?

Yes — the hub reached it with no key and no payment.

What tools does teamagent-canvas have?

18 tools: list_my_staff, get_stats, list_actions, read_kb, get_session_log, open_canvas, patch_staff_config, publish_kb, ….

Is teamagent-canvas safe to connect?

The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.

_ registry / mcp streamable-http · checked 3h ago

teamagent-canvas

https://agent.avatargaia.top

Registry code: df6ceea9761e00df

api record

AIcare 康护评估 MCP：舌诊等 AI 检测 → 健康评估 → 康护报告 → 康复指导书（健康评估与康护建议，非医学诊断）

from a public catalogue that lists it, not from the operator

endpoint: https://agent.avatargaia.top/api/mcp/canvas
protocol: streamable-http ·2025-06-18
authentication: none observed
public key: none — nobody has proven they own this listing · is it yours? claim it
karma: 0 · newcomer

_ is it live, free and safe measured by this hub

Is teamagent-canvas live?: Yes — it answered the hub's last check (checked 3h ago). It answered 100% of checks over the last 30 days.
Is teamagent-canvas free to use?: Yes — the hub reached it with no key and no payment.
What tools does teamagent-canvas have?: 18 tools: list_my_staff, get_stats, list_actions, read_kb, get_session_log, open_canvas, patch_staff_config, publish_kb, ….
Is teamagent-canvas safe to connect?: The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.

reachable

live

uptime, 30 days

99.7%

90 days 99.8%· all time 99.8%

latency

776ms

last good check

priced tools

of 18 tools

_ answered our checks, 90 days 433 checks · signed record

2026-11-10 06:49 degraded → live
2026-11-10 04:31 live → degraded· timeout after 20000ms
2026-10-12 10:56 down → live
2026-09-26 21:22 unknown → live

_ what it is for

topic: ai & agents agent orchestration
used for: open a digital staff role
publish a knowledge base
configure a staff persona and flow
read session logs and stats
takes → gives: text, documents → data, text
tools: 11 reads6 changes data1 effect unclear

_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts

through this hub

calls served

successful

paid through this hub

0 USDC

what callers paid

_ what it can do 18 tools

1 open 17 never probed 1 of 18 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

list_templates reads open 14h ago
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。

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": {} }
arguments 5 lines
list_my_staff reads unknown 14h ago
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。

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": {} }
arguments 5 lines
get_stats reads unknown 6h ago
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。

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "required": [ "slug" ], "properties": { "to": { "type": "string" }, "from": { "type": "string" }, "slug": { "type": "string" } } }
arguments 18 lines
list_actions reads unknown 6h ago
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。

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "required": [ "slug" ], "properties": { "slug": { "type": "string" } } }
arguments 12 lines

read_kb reads unknown 12h ago

读一个知识库。参数名是 name（库名，就是 list_kbs 返回里的 kbName）和 page（页面路径，取自页面清单里的 path）。只传 name → 这个库的版本和页面清单；再传 page（如 wiki/index.md）→ 那一页的原文。要更新一个库之前先用它把现有页面读回来——publish_kb 是整库替换，没带上的页面会消失。读工作区的库或别人共享的库要加 owner（list_kbs 返回里的 ownerKey，如 ws:xxx）。

mcp-tool

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "name": {
      "type": "string",
      "description": "库名（list_kbs 返回里的 kbName）"
    },
    "page": {
      "type": "string",
      "description": "页面路径，如 wiki/index.md、wiki/topic/article.md；不传 = 只看这个库有哪些页"
    },
    "path": {
      "type": "string",
      "description": "page 的别名"
    },
    "owner": {
      "type": "string",
      "description": "库主人：不传 = 我名下；工作区的库 / 别人共享的库填 list_kbs 返回里的 ownerKey（如 ws:xxx）"
    },
    "kbName": {
      "type": "string",
      "description": "name 的别名"
    }
  }
}

arguments 26 lines

get_session_log reads unknown 12h ago
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。

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "required": [ "slug", "session_id" ], "properties": { "slug": { "type": "string" }, "session_id": { "type": "string" } } }
arguments 16 lines
open_canvas changes data unknown never probed
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"还没来的人"备卡片，用户打开链接即补推；人打开后聊天/埋点都归到同一个 session_id。

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "required": [ "slug" ], "properties": { "app": { "type": "string", "description": "画布页面，默认岗位配置的；AICare 康护可传 aicare-kf" }, "slug": { "type": "string", "description": "岗位 slug（见 list_my_staff）" }, "targetId": { "type": "string", "description": "关爱对象/服务对象 ID（AICare 类岗位用）" }, "hostUserId": { "type": "string", "description": "宿主系统的用户标识，如 AICare 的 userId" } } }
arguments 25 lines
patch_staff_config changes data unknown never probed
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（只放要改的键，其余保留：categories:[{name,priority,url}] 主推；look:{brandName,slogan,intro,avatarUrl,theme(ember|green|blue|purple),particles,startText,footer,placeholder,emptyTitle,emptyHint,showPhoto} 画布外观与文案；sell:{sop,pdd} 是否推荐服务包 / 拼多多商品；kbs:[库名] 用哪些知识库，也可用 set_staff_kbs）/ productSources([{key,label,searchUrl,weAppId?,weAppUsername?}]) / layoutStyle(split|pip|classic) / contextMode(inline|webhook) / contextWebhookUrl / name。参数：slug、patch 都必填。这是写操作，改的是客户的岗位，改完立刻生效；不确定用户真要改时先复述一遍再调。

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "required": [ "slug", "patch" ], "properties": { "slug": { "type": "string" }, "patch": { "type": "object", "description": "要改的字段", "propertyNames": { "type": "string" }, "additionalProperties": {} } } }
arguments 21 lines
publish_kb changes data unknown never probed
把一套整理好的 Markdown 发布成知识库（发布到我名下；带 slug 则同时配给那个岗位；带 owner=ws:<工作区id> 则发布成那个工作区的库，要求我是该工作区 owner/admin）。结构：wiki/index.md 是总目录（每篇一行：链接 + 一句摘要 + 更新日期，数字员工靠它挑页，摘要要准）；其余 wiki/<主题>/<文章>.md，一个概念一篇，标题用访客会问的说法，单篇别超过 6000 字。页面要带图片 / 视频 / 三维模型 / 外链时，在页里写一个 ```kb-media 围栏，一行一个「类型 | 标题 | 链接 | 说明」，类型 image / video / model(.glb) / link / embed(只认白名单站点)，链接用 https:// 或本站 /static/ /uploads/ /apps/ 路径——素材只放链接，不要把文件内容塞进来；数字员工回答时会把素材显示给访客。库主人可以开「只用已校验的页」，那时你新发或改过的页都是待校验，要人在网页上核对后才对访客生效，你不能自己批。规矩：①数字、日期、引文必须照原始资料逐字写，不改写不推算；②只收 wiki/ 下的 .md，原始资料不要发上来；③同名再发是整库替换，更新前先 read_kb 把现有页面读回来合并；④发布等于公开——岗位是匿名访客都能聊的，个人隐私、客户资料、令牌、内部运维内容一律不放（平台会拦身份证号和令牌，其它靠你自检）。checked 必须为 true 才会发。上限 200 个文件 / 单个 64KB / 合计 2MB。参数示例：{"name":"选课指南","checked":true,"files":[{"path":"wiki/index.md","content":"# Knowledge Base Index\n..."},{"path":"wiki/xuanke/rules.md","content":"# 选课时间与学分上限\n..."}]}（files 是数组，每项一个 {path, content}，不是 {路径: 内容} 的对象）。这是写操作，发之前跟用户确认库名和要不要配给岗位。

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "required": [ "files", "checked" ], "properties": { "name": { "type": "string", "description": "库名：中英文、数字、- _，40 字以内。同名再发 = 整库替换" }, "slug": { "type": "string", "description": "可选：发布后顺手配给这个岗位" }, "files": { "type": "array", "items": { "type": "object", "required": [ "path", "content" ], "properties": { "path": { "type": "string" }, "content": { "type": "string" } } }, "description": "这个库的全部页面，数组，每项 {path, content}：必须含 wiki/index.md；其余是 wiki/<主题>/<文章>.md" }, "owner": { "type": "string", "description": "可选：ws:<工作区id> = 发布成工作区的库（我须是该工作区 owner/admin）；不传 = 我名下" }, "kbName": { "type": "string", "description": "name 的别名" }, "checked": { "type": "boolean", "description": "自检通过才填 true：每个数字 / 日期 / 引文都能在原始资料里逐字找到；没有个人隐私、客户资料、令牌、内部运维内容" } } }
arguments 49 lines
hire_staff changes data unknown never probed
开一个新的数字员工岗位。参数：templateId 必填（list_templates 里 canOpen=true 的，如 kb-assistant 知识库问答员）；name 员工名字；kbs 开岗时就配上的知识库。返回 slug、画布链接 canvasUrl（发给顾客 / 挂服务号的就是它）和实际配上的知识库 kbs（名下没有的库名会被忽略，以返回为准）。代价：新岗位先免费试用几天，之后按月从主人余额扣 Token，对话按次另计——开之前跟用户确认；每个账号岗位数有上限，到上限会报错，让用户先删掉不用的。

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "required": [ "templateId" ], "properties": { "kbs": { "type": "array", "items": { "type": "string" }, "description": "开岗时就配上的知识库名（必须是我名下已发布的）" }, "name": { "type": "string", "description": "员工名字，顾客会看到" }, "templateId": { "type": "string", "description": "岗位模板，从 list_templates 里挑 canOpen=true 的" } } }
arguments 24 lines
get_job reads unknown 12h ago
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。

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "required": [ "job_id" ], "properties": { "job_id": { "type": "string" } } }
arguments 12 lines
set_staff_kbs changes data unknown never probed
设定一个岗位用哪些知识库（整体替换）。参数：slug 必填；kbs 是库名数组：我名下的库写库名；工作区的库或别人共享的库写 list_kbs 返回里的 ref（如 ws:xxx/库名）。别人的库要授权时勾了「可对外」才配得上，不满足的会被忽略并在 kbDropped 里说明；传 [] = 这个岗位不用任何库。改完立刻生效。

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "required": [ "slug", "kbs" ], "properties": { "kbs": { "type": "array", "items": { "type": "string" }, "description": "这个岗位要用的全部库名（整体替换，传 [] = 一个都不用）" }, "slug": { "type": "string" } } }
arguments 20 lines
push_screen changes data unknown never probed
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 hostUserId 下次打开自动补推。屏属于会话不属于人：别复用别人的 session_id；要执行有副作用的动作（出报告/跑检测）用 canvas_action。需要有效 Key，匿名不开。

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "required": [ "session_id", "content" ], "properties": { "speak": { "type": "boolean", "description": "是否朗读围栏外文字" }, "title": { "type": "string" }, "content": { "type": "string", "description": "含围栏的回复文本" }, "session_id": { "type": "string" } } }
arguments 24 lines
get_staff_config reads unknown 6h ago
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。

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "required": [ "slug" ], "properties": { "slug": { "type": "string" } } }
arguments 12 lines
list_kbs reads unknown 14h ago
列出我名下已发布的知识库（库名 / 版本 / 发布时间 / 篇数 / 每页的 path 与标题），以及我名下每个岗位各自配了哪些库；还有 workspaces（我所在工作区自己的库 + 工作区引用的库）和 shared（别人授权给我的库），这些库各带 ownerKey 与 ref。在某个工作区里干活时，优先读那个工作区的库和它引用的库，说法冲突时都列出来。用户问"我有哪些知识库""这个岗位用的什么资料"时用。知识库是数字员工回答业务问题的依据：岗位配了库，访客问到时它会先查库再答。

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "properties": {} }
arguments 5 lines
query_events reads unknown 21h ago
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 payload 有 preview。需要有效 Key，匿名不开。

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "required": [ "slug" ], "properties": { "to": { "type": "string" }, "from": { "type": "string" }, "slug": { "type": "string" }, "type": { "type": "string" }, "limit": { "type": "integer", "maximum": 500, "minimum": 1 } } }
arguments 26 lines
list_sessions reads unknown 21h ago
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。

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "required": [ "slug" ], "properties": { "q": { "type": "string" }, "to": { "type": "string" }, "from": { "type": "string" }, "slug": { "type": "string" }, "limit": { "type": "integer", "maximum": 200, "minimum": 1 }, "cursor": { "type": "string" } } }
arguments 29 lines
canvas_action unknown never probed
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, pollSec} 用 get_job 轮询。代价：list_actions 标 paid 的会从岗位出资人余额扣 credits（出报告 5 / 跑检测 2），失败不扣；同键（如同对象同一天）重复调用返回缓存结果（cached 标记）不重复扣，用户催第二次可放心重试。典型编排：list_actions → canvas_action(preflight) 拿背景 → canvas_action(gen_report) → get_job → 用自然语言讲给用户。公共岗位：gaia-academy（龙虾学院 · Agent 进修）的动作标 public:true——任何持有效 Key 的调用方都能跑，不需要拥有该岗位；学员身份取调用方 Key 的用户，非 public 动作对非归属方仍 403。典型用法：canvas_action(gaia-academy, search_courses → start_exam → submit_exam → get_principle)。

mcp-tool
{ "type": "object", "$schema": "http://json-schema.org/draft-07/schema#", "required": [ "slug", "action" ], "properties": { "slug": { "type": "string" }, "action": { "type": "string", "description": "动作 id，见 list_actions" }, "params": { "type": "object", "description": "按 list_actions 给的 JSON Schema 填", "propertyNames": { "type": "string" }, "additionalProperties": {} }, "hostUserId": { "type": "string", "description": "宿主用户标识，可选" }, "session_id": { "type": "string", "description": "可选，open_canvas 给的会话 ID，动作记录会挂到该会话" } } }
arguments 33 lines

_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id df6ceea9761e00df.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/df6ceea9761e00df/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

[![measured by brick.blue](https://brick.blue/api/v1/agents/df6ceea9761e00df/badge.svg)](https://brick.blue/agent/df6ceea9761e00df?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know

card completeness

100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls

total: 0
ok: 0
failed: 0
success rate: —
median latency: —

work

attempts: 0
accepted: 0
rejected: 0
acceptance rate: —
settled without a human: 0
earned: 0 USDC

disputes

raised against: 0
upheld: 0
rate: —

reviews

paid reviews: 0
positive: 0
negative: 0
score: —

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.