io.github.AvatarGaia/canvas-mcp
REMOTE · AGENT.AVATARGAIA.TOP · 2 COMPONENTS
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。
Available components
Last scanned (13 hours ago)
Scores higher than 62% of remote servers
Reachable. Last reached 21 Nov 2026.
Category AI and Machine Learning
Recent critical change
Authorization (21 Oct 2026). See the changelog before you install this server.
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security57
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (patch_staff_config). See how to fix → View diagnostics → Fail
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability66
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 3582 tokens (~199/item across 18 items; 18 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage84
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 52% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 18 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Nov 26 0
- Stability: 0.97 → pass security
- 19 Nov 26 0
- Stability: pass → 0.97 functional
- 11 Nov 26 0
- Stability: 0.97 → pass security
- 10 Nov 26 0
- Stability: pass → 0.97 functional
- 6 Nov 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 5 Nov 26 0
- Stability: 0.97 → pass security
- 4 Nov 26 0
- Stability: pass → 0.97 functional
- 21 Oct 26 0
- Authorization: unverified → fail ▼ critical
- Stability: unverified → pass ▲ security
- Injection markers: unverified → pass ▲ security
- TLS certificate: unverified → pass ▲ security
- Tool “list_kbs” rewrote its description, which is the text the model reads security
- Tool “publish_kb” rewrote its description, which is the text the model reads security
- Tool “read_kb” rewrote its description, which is the text the model reads security
- Tool “set_staff_kbs” rewrote its description, which is the text the model reads security
- Schema quality: 177 → 199 ▼ functional
- Tool coverage: unverified → 100 ▲ functional
- “publish_kb” added an optional parameter “owner” cosmetic
- “read_kb” added an optional parameter “owner” cosmetic
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Probed https://agent.avatargaia.top/api/mcp/canvas
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=agent.avatargaia.top | CN=YR2,O=Let's Encrypt,C=US | 16 Nov 2026 | 14 Feb 2027 | RSA 2048 | SHA256-RSA | 66c0d7fb2061101a403cb4f8bb016856800 |
| SANs: agent.avatargaia.top | ||||||
| CN=YR2,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | 4ebd24947e24d394802d84a52fd5b319 |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of agent.avatargaia.top. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| top. | DS published | 41508 | 13 | Verified |
| avatargaia.top. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://agent.avatargaia.top/api/mcp/canvas | Verified | 200 | |
| http (plaintext) | http://agent.avatargaia.top/api/mcp/canvas | HTTPS enforced | 301 | https://agent.avatargaia.top/api/mcp/canvas |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
canvas_action 执行岗位动作 ~387
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)。
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | 动作 id,见 list_actions |
| hostUserId | string | – | 宿主用户标识,可选 |
| params | object | – | 按 list_actions 给的 JSON Schema 填 |
| session_id | string | – | 可选,open_canvas 给的会话 ID,动作记录会挂到该会话 |
| slug | string | yes | – |
No output schema declared.
No examples provided.
get_job 查长任务 ~88
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。
| Name | Type | Req | Description |
|---|---|---|---|
| job_id | string | yes | – |
No output schema declared.
No examples provided.
get_session_log 会话完整记录 ~112
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。
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | yes | – |
| slug | string | yes | – |
No output schema declared.
No examples provided.
get_staff_config 读岗位配置 ~86
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。
| Name | Type | Req | Description |
|---|---|---|---|
| slug | string | yes | – |
No output schema declared.
No examples provided.
get_stats 岗位统计 ~113
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。
| Name | Type | Req | Description |
|---|---|---|---|
| from | string | – | – |
| slug | string | yes | – |
| to | string | – | – |
No output schema declared.
No examples provided.
hire_staff 开一个数字员工 ~224
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。
| Name | Type | Req | Description |
|---|---|---|---|
| kbs | array | – | 开岗时就配上的知识库名(必须是我名下已发布的) |
| name | string | – | 员工名字,顾客会看到 |
| templateId | string | yes | 岗位模板,从 list_templates 里挑 canOpen=true 的 |
No output schema declared.
No examples provided.
list_actions 岗位可用动作 ~83
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。
| Name | Type | Req | Description |
|---|---|---|---|
| slug | string | yes | – |
No output schema declared.
No examples provided.
list_kbs 我的知识库 ~167
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。
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_my_staff 我名下的岗位 ~72
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。
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_sessions 会话列表 ~141
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。
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | string | – | – |
| from | string | – | – |
| limit | integer | – | – |
| q | string | – | – |
| slug | string | yes | – |
| to | string | – | – |
No output schema declared.
No examples provided.
list_templates 岗位模板清单 ~103
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。
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
open_canvas 打开画布(拿链接和会话) ~258
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。
| Name | Type | Req | Description |
|---|---|---|---|
| app | string | – | 画布页面,默认岗位配置的;AICare 康护可传 aicare-kf |
| hostUserId | string | – | 宿主系统的用户标识,如 AICare 的 userId |
| slug | string | yes | 岗位 slug(见 list_my_staff) |
| targetId | string | – | 关爱对象/服务对象 ID(AICare 类岗位用) |
No output schema declared.
No examples provided.
patch_staff_config 改岗位配置 ~253
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。
| Name | Type | Req | Description |
|---|---|---|---|
| patch | object | yes | 要改的字段 |
| slug | string | yes | – |
No output schema declared.
No examples provided.
publish_kb 发布知识库 ~721
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。
| Name | Type | Req | Description |
|---|---|---|---|
| checked | boolean | yes | 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 |
| files | array | yes | 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 |
| kbName | string | – | name 的别名 |
| name | string | – | 库名:中英文、数字、- _,40 字以内。同名再发 = 整库替换 |
| owner | string | – | 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 |
| slug | string | – | 可选:发布后顺手配给这个岗位 |
No output schema declared.
No examples provided.
push_screen 推内容到画布 ~224
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。
| Name | Type | Req | Description |
|---|---|---|---|
| content | string | yes | 含围栏的回复文本 |
| session_id | string | yes | – |
| speak | boolean | – | 是否朗读围栏外文字 |
| title | string | – | – |
No output schema declared.
No examples provided.
query_events 按类型查事件 ~148
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。
| Name | Type | Req | Description |
|---|---|---|---|
| from | string | – | – |
| limit | integer | – | – |
| slug | string | yes | – |
| to | string | – | – |
| type | string | – | – |
No output schema declared.
No examples provided.
read_kb 读知识库 ~246
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)。
| Name | Type | Req | Description |
|---|---|---|---|
| kbName | string | – | name 的别名 |
| name | string | – | 库名(list_kbs 返回里的 kbName) |
| owner | string | – | 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) |
| page | string | – | 页面路径,如 wiki/index.md、wiki/topic/article.md;不传 = 只看这个库有哪些页 |
| path | string | – | page 的别名 |
No output schema declared.
No examples provided.
set_staff_kbs 给岗位配知识库 ~156
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。
| Name | Type | Req | Description |
|---|---|---|---|
| kbs | array | yes | 这个岗位要用的全部库名(整体替换,传 [] = 一个都不用) |
| slug | string | yes | – |
No output schema declared.
No examples provided.
How do I install the io.github.AvatarGaia/canvas-mcp server?
io.github.AvatarGaia/canvas-mcp is a hosted endpoint at https://agent.avatargaia.top/api/mcp/canvas, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · agent.avatargaia.top
claude mcp add --transport http avatargaia-canvas-mcp 'https://agent.avatargaia.top/api/mcp/canvas'
What is the io.github.AvatarGaia/canvas-mcp server?
io.github.AvatarGaia/canvas-mcp is listed in the public MCP registry as io.github.AvatarGaia/canvas-mcp. 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。 This page covers its hosted endpoint (https://agent.avatargaia.top/api/mcp/canvas).
Is the io.github.AvatarGaia/canvas-mcp server safe to use?
io.github.AvatarGaia/canvas-mcp scores 75 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the io.github.AvatarGaia/canvas-mcp server expose?
io.github.AvatarGaia/canvas-mcp exposes 18 tools: list_templates, list_my_staff, open_canvas, get_staff_config, patch_staff_config, and 13 more. Their descriptions and schemas cost roughly 3,582 tokens of context every time the server is loaded.
Does the io.github.AvatarGaia/canvas-mcp server require authentication?
No. We connected to io.github.AvatarGaia/canvas-mcp without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the io.github.AvatarGaia/canvas-mcp server still maintained?
io.github.AvatarGaia/canvas-mcp is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the io.github.AvatarGaia/canvas-mcp server?
VerifyMCP ran 13 checks on io.github.AvatarGaia/canvas-mcp, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.