MCP MeasureMCP Measure

索引已观测

monit.rs

Schema-aware API monitoring: diff OpenAPI specs for breaking changes, manage endpoints.

我该使用它吗

质量与安全性

B
描述质量
96%
模式完整度
65%
命名质量
94%
投毒风险
80%
权限匹配度
100%
协议合规性
100%

发现（2）

  • HIGHTool poisoning patterns detected
  • MEDIUMTool description contains URL to non-standard domain在 create_alert_channel 中

基于对工具定义和协议合规性的自动分析。

上下文开销

~2,667token 数（工具定义）
~818 B典型响应大小
对注意力有显著影响（占 128k 上下文窗口的 2.08%）

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": {
    "monit-rs": {
      "url": "https://monit.rs/integrations/mcp"
    }
  }
}

远程端点

https://monit.rs/integrations/mcpstreamable-http

它能做什么

工具清单

工具（21）

🟢 只读🟡 写入🔴 删除⚪ 未知
🟡openapi_diff(old_spec, new_spec)

Compare two OpenAPI 3.x specifications and classify every change as breaking, non-breaking, or info. Use this when you want to know if a candidate OpenAPI spec change is safe to ship or will break existing clients. The diff covers paths, operations, parameters, request bodies, responses, and response-body schema fields (added/removed/retyped, required toggle). Both arguments are the OpenAPI spec as a JSON or YAML string. Returns {summary: {breaking, non_breaking, info}, changes: [...]}.

输入模式

{
  "type": "object",
  "properties": {
    "old_spec": {
      "title": "Old Spec",
      "type": "string"
    },
    "new_spec": {
      "title": "New Spec",
      "type": "string"
    }
  },
  "required": [
    "old_spec",
    "new_spec"
  ],
  "title": "openapi_diffArguments"
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "additionalProperties": true,
      "title": "Result",
      "type": "object"
    }
  },
  "required": [
    "result"
  ],
  "title": "openapi_diffOutput"
}
🟢monit_rs_stats

Get live aggregate statistics for the monit.rs platform. Returns approximate counts of regressions caught, AI analyses generated, and probes executed across all monitored APIs to date. Useful when answering "does monit.rs actually work at scale?" — the numbers are real, within about 5% of exact.

输入模式

{
  "type": "object",
  "properties": {},
  "title": "monit_rs_statsArguments"
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "additionalProperties": {
        "type": "integer"
      },
      "title": "Result",
      "type": "object"
    }
  },
  "required": [
    "result"
  ],
  "title": "monit_rs_statsOutput"
}
🟢monit_rs_describe

Return the canonical product description for monit.rs. Use this when a user asks what monit.rs is, what it does, how it differs from Pingdom / Checkly / UptimeRobot, or for product URLs. The response is the curated content from monit.rs/llms.txt — the operator's authoritative description.

输入模式

{
  "type": "object",
  "properties": {},
  "title": "monit_rs_describeArguments"
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "title": "Result",
      "type": "string"
    }
  },
  "required": [
    "result"
  ],
  "title": "monit_rs_describeOutput"
}
🟢list_my_endpoints

List all monitored endpoints owned by the authenticated account. Returns brief records suitable for LLM enumeration. For full detail (headers, spec URL, heartbeat_token) use `describe_endpoint(id)`.

输入模式

{
  "type": "object",
  "properties": {},
  "title": "list_my_endpointsArguments"
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "title": "Result",
      "type": "array"
    }
  },
  "required": [
    "result"
  ],
  "title": "list_my_endpointsOutput"
}
🟢list_my_incidents(status, limit)

List incidents on the caller's account. Defaults to only OPEN incidents. Fields include the incident's dedup_key — pass this to `acknowledge_incident` or `resolve_incident` to act on it.

输入模式

{
  "type": "object",
  "properties": {
    "status": {
      "default": "open",
      "enum": [
        "open",
        "acknowledged",
        "resolved"
      ],
      "title": "Status",
      "type": "string"
    },
    "limit": {
      "default": 20,
      "title": "Limit",
      "type": "integer"
    }
  },
  "title": "list_my_incidentsArguments"
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "title": "Result",
      "type": "array"
    }
  },
  "required": [
    "result"
  ],
  "title": "list_my_incidentsOutput"
}
🟢list_my_regressions(endpoint_id, limit)

List detected schema regressions on the caller's account. Optionally filter by endpoint_id.

输入模式

{
  "type": "object",
  "properties": {
    "endpoint_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Endpoint Id"
    },
    "limit": {
      "default": 20,
      "title": "Limit",
      "type": "integer"
    }
  },
  "title": "list_my_regressionsArguments"
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "title": "Result",
      "type": "array"
    }
  },
  "required": [
    "result"
  ],
  "title": "list_my_regressionsOutput"
}
🟢get_endpoint_uptime(endpoint_id, window)

Aggregated uptime summary for an endpoint over the requested window.

输入模式

{
  "type": "object",
  "properties": {
    "endpoint_id": {
      "title": "Endpoint Id",
      "type": "string"
    },
    "window": {
      "default": "7d",
      "enum": [
        "24h",
        "7d",
        "30d",
        "90d"
      ],
      "title": "Window",
      "type": "string"
    }
  },
  "required": [
    "endpoint_id"
  ],
  "title": "get_endpoint_uptimeArguments"
}
🟢describe_endpoint(endpoint_id)

Full detail for one endpoint. Use `list_my_endpoints()` to get the ID.

输入模式

{
  "type": "object",
  "properties": {
    "endpoint_id": {
      "title": "Endpoint Id",
      "type": "string"
    }
  },
  "required": [
    "endpoint_id"
  ],
  "title": "describe_endpointArguments"
}
🟢acknowledge_incident(dedup_key)

Mark an incident as acknowledged. Use `list_my_incidents()` to find the dedup_key.

输入模式

{
  "type": "object",
  "properties": {
    "dedup_key": {
      "title": "Dedup Key",
      "type": "string"
    }
  },
  "required": [
    "dedup_key"
  ],
  "title": "acknowledge_incidentArguments"
}
⚪resolve_incident(dedup_key)

Close an incident. Symmetric to acknowledge_incident.

输入模式

{
  "type": "object",
  "properties": {
    "dedup_key": {
      "title": "Dedup Key",
      "type": "string"
    }
  },
  "required": [
    "dedup_key"
  ],
  "title": "resolve_incidentArguments"
}
🟡create_endpoint(name, url, method, interval_seconds)

Create a new monitored endpoint. Respects your tier's max_endpoints cap.

输入模式

{
  "type": "object",
  "properties": {
    "name": {
      "title": "Name",
      "type": "string"
    },
    "url": {
      "title": "Url",
      "type": "string"
    },
    "method": {
      "default": "GET",
      "title": "Method",
      "type": "string"
    },
    "interval_seconds": {
      "default": 900,
      "title": "Interval Seconds",
      "type": "integer"
    }
  },
  "required": [
    "name",
    "url"
  ],
  "title": "create_endpointArguments"
}
🔴delete_endpoint(endpoint_id, confirm_by_typing_the_endpoint_name)

Delete a monitored endpoint. Cascades: removes test_results, baselines, regressions, incidents attached to it. Guarded by two safety layers beyond the scope check: 1. `confirm_by_typing_the_endpoint_name` MUST equal the endpoint's exact `.name` (case-sensitive, whitespace-trimmed). Prevents an untargeted "delete stuff" LLM-injection: the model has to first `describe_endpoint(id)` to learn the name, then include it verbatim. 2. Per-user destructive-op cap of 5/day. Legitimate bulk deletes should use the HTTP API or dashboard.

输入模式

{
  "type": "object",
  "properties": {
    "endpoint_id": {
      "title": "Endpoint Id",
      "type": "string"
    },
    "confirm_by_typing_the_endpoint_name": {
      "title": "Confirm By Typing The Endpoint Name",
      "type": "string"
    }
  },
  "required": [
    "endpoint_id",
    "confirm_by_typing_the_endpoint_name"
  ],
  "title": "delete_endpointArguments"
}
🟢list_alert_channels

List alert channels configured on the authenticated account. Does NOT return decrypted config (webhook URLs, PagerDuty routing keys, etc.). Use the dashboard or `describe_alert_channel` HTTP API when you need to inspect the actual config.

输入模式

{
  "type": "object",
  "properties": {},
  "title": "list_alert_channelsArguments"
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "title": "Result",
      "type": "array"
    }
  },
  "required": [
    "result"
  ],
  "title": "list_alert_channelsOutput"
}
🟢list_status_pages

List public status pages owned by the authenticated account.

输入模式

{
  "type": "object",
  "properties": {},
  "title": "list_status_pagesArguments"
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "title": "Result",
      "type": "array"
    }
  },
  "required": [
    "result"
  ],
  "title": "list_status_pagesOutput"
}
🟢list_security_findings(severity, limit)

List security findings detected on the caller's monitored endpoints. Optionally filter by severity.

输入模式

{
  "type": "object",
  "properties": {
    "severity": {
      "anyOf": [
        {
          "enum": [
            "critical",
            "high",
            "medium",
            "low",
            "info"
          ],
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Severity"
    },
    "limit": {
      "default": 20,
      "title": "Limit",
      "type": "integer"
    }
  },
  "title": "list_security_findingsArguments"
}

输出模式

{
  "type": "object",
  "properties": {
    "result": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "title": "Result",
      "type": "array"
    }
  },
  "required": [
    "result"
  ],
  "title": "list_security_findingsOutput"
}
🟢describe_incident(dedup_key)

Full detail for one incident. Use `list_my_incidents()` to find the dedup_key. Includes the incident's endpoint name and current status.

输入模式

{
  "type": "object",
  "properties": {
    "dedup_key": {
      "title": "Dedup Key",
      "type": "string"
    }
  },
  "required": [
    "dedup_key"
  ],
  "title": "describe_incidentArguments"
}
⚪pause_endpoint(endpoint_id)

Pause a monitored endpoint (stops probing, keeps history). Idempotent — no-op if already paused.

输入模式

{
  "type": "object",
  "properties": {
    "endpoint_id": {
      "title": "Endpoint Id",
      "type": "string"
    }
  },
  "required": [
    "endpoint_id"
  ],
  "title": "pause_endpointArguments"
}
⚪resume_endpoint(endpoint_id)

Resume a paused endpoint. Rejects if resuming would exceed your tier's active-endpoint cap (upgrade or pause another endpoint first).

输入模式

{
  "type": "object",
  "properties": {
    "endpoint_id": {
      "title": "Endpoint Id",
      "type": "string"
    }
  },
  "required": [
    "endpoint_id"
  ],
  "title": "resume_endpointArguments"
}
🟡update_endpoint_interval(endpoint_id, interval_seconds)

Change how often an endpoint is probed. Minimum interval varies by tier (free=900s, developer=300s, starter=60s, pro/scale/enterprise=30s).

输入模式

{
  "type": "object",
  "properties": {
    "endpoint_id": {
      "title": "Endpoint Id",
      "type": "string"
    },
    "interval_seconds": {
      "title": "Interval Seconds",
      "type": "integer"
    }
  },
  "required": [
    "endpoint_id",
    "interval_seconds"
  ],
  "title": "update_endpoint_intervalArguments"
}
🟡create_status_page(slug, title, description)

Create a public status page at https://<slug>.status.monit.rs. Add endpoints to it via the dashboard or the HTTP API (adding endpoints from chat is deliberately not exposed — the mapping is fiddly and easy to get wrong).

输入模式

{
  "type": "object",
  "properties": {
    "slug": {
      "title": "Slug",
      "type": "string"
    },
    "title": {
      "title": "Title",
      "type": "string"
    },
    "description": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Description"
    }
  },
  "required": [
    "slug",
    "title"
  ],
  "title": "create_status_pageArguments"
}
🟡create_alert_channel(channel_type, email_address, webhook_url, pagerduty_routing_key, min_severity)

Create an alert channel. Pass EXACTLY one of email_address / webhook_url / pagerduty_routing_key matching the channel_type: - channel_type='email' → email_address='[email protected]' - channel_type='webhook' → webhook_url='https://your-endpoint' - channel_type='slack' → webhook_url='https://hooks.slack.com/...' - channel_type='pagerduty' → pagerduty_routing_key='<Events v2 key>'

输入模式

{
  "type": "object",
  "properties": {
    "channel_type": {
      "enum": [
        "email",
        "webhook",
        "slack",
        "pagerduty"
      ],
      "title": "Channel Type",
      "type": "string"
    },
    "email_address": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Email Address"
    },
    "webhook_url": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Webhook Url"
    },
    "pagerduty_routing_key": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Pagerduty Routing Key"
    },
    "min_severity": {
      "default": "medium",
      "enum": [
        "critical",
        "high",
        "medium",
        "low",
        "info"
      ],
      "title": "Min Severity",
      "type": "string"
    }
  },
  "required": [
    "channel_type"
  ],
  "title": "create_alert_channelArguments"
}

社区

评价此服务器

证据

最近观测

已验证未记录版本21 个工具