Agent Watch
Monitoring for the agent economy — liveness, latency, trust scoring for MCP endpoints
我该使用它吗
质量与安全性
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"agent-watch": {
"url": "https://agent-watch-api-production.up.railway.app/mcp/"
}
}
}远程端点
https://agent-watch-api-production.up.railway.app/mcp/streamable-http它能做什么
工具清单
工具（8）
🟢aw_health
Liveness check for the Agent Watch API. Returns ok, service name, and version. Call this first to verify connectivity before using other tools.
输入模式
{
"type": "object",
"properties": {},
"title": "aw_healthArguments"
}🟢aw_check_endpoint(url, timeout)
Probe an MCP or HTTP-402 endpoint now and get its trust verdict. Performs a real MCP initialize handshake (not a ping), measures p50/p95 latency, counts tools, hashes the tool schema (for drift detection), and checks RFC 9728 auth metadata. Returns: alive (bool), name, tool_count, latency_p50_ms, tool_schema_hash, auth_metadata_present, and error detail when dead. Use before wiring any new MCP server into your client. Args: url: the MCP or HTTP-402 endpoint URL to probe (e.g. https://host/mcp/) timeout: probe timeout in seconds (default 30)
输入模式
{
"type": "object",
"properties": {
"url": {
"title": "Url",
"type": "string"
},
"timeout": {
"default": 30,
"title": "Timeout",
"type": "integer"
}
},
"required": [
"url"
],
"title": "aw_check_endpointArguments"
}🟢aw_census
Full-census summary of the official MCP registry: 7,454 endpoints probed with real MCP handshakes. Returns alive/dead/unknown counts and percentages. States: alive = MCP initialize succeeded; dead = no answer; unknown = answered but auth-gated (401/403/402) or redirecting — liveness unprovable without credentials. Use to quantify how much of the MCP ecosystem is actually reachable.
输入模式
{
"type": "object",
"properties": {},
"title": "aw_censusArguments"
}🟢aw_list_monitored
List all endpoints in the Agent Watch census with their registry names. Returns count and the full endpoint list (URLs). Combine with aw_alerts to find which of these are dead. Read-only.
输入模式
{
"type": "object",
"properties": {},
"title": "aw_list_monitoredArguments"
}🟢aw_alerts
Show dead endpoints across the monitored registry (alive=false). Returns up to 500 dead endpoints with names. Use after aw_census or aw_list_monitored to get the actionable dead list. Read-only.
输入模式
{
"type": "object",
"properties": {},
"title": "aw_alertsArguments"
}🟡aw_watch(email, urls, watch_token)
Add endpoints to your personal watchlist (probed immediately, then every 6h). Plan-limited by the email used at checkout: free 5, Builder ($19/mo) 50, Team ($99/mo) 500 endpoints. Alerts fire on alive→dead transitions and tool-schema drift. Already-watched URLs are returned without re-probing. Args: email: the email your subscription is under (free tier works too) urls: endpoint URLs to add to your watchlist watch_token: issued at registration, delivered in your onboarding email — required
输入模式
{
"type": "object",
"properties": {
"email": {
"title": "Email",
"type": "string"
},
"urls": {
"items": {},
"title": "Urls",
"type": "array"
},
"watch_token": {
"default": "",
"title": "Watch Token",
"type": "string"
}
},
"required": [
"email",
"urls"
],
"title": "aw_watchArguments"
}🟢skills_list_tool
List this product's skills. Each entry carries the SKILL.md URI, its name and description, verbatim frontmatter, and a per-file sha256 manifest. Read a body with `read_skill`.
输入模式
{
"type": "object",
"properties": {},
"title": "skills_list_toolArguments"
}🟢read_skill(uri)
Read a product skill file by its skill:// URI. Args: uri: e.g. skill://<product>/<skill-name>/SKILL.md Get valid URIs from `skills_list_tool`.
输入模式
{
"type": "object",
"properties": {
"uri": {
"title": "Uri",
"type": "string"
}
},
"required": [
"uri"
],
"title": "read_skillArguments"
}社区
证据