{
  "listings": [
    {
      "slug": "axiom",
      "name": "Axiom MCP Server",
      "company": "Axiom, Inc.",
      "grade": "BB",
      "fit": "yes",
      "why": "Header auth with a personal access token whose expiry is optional runs without a browser; fixed APL queries run as given with no model call; cost limits cap spend per hour and day.",
      "source": "https://axiom.co/docs/console/intelligence/mcp-server",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/axiom"
    },
    {
      "slug": "better-stack",
      "name": "Better Stack",
      "company": "Better Stack, Inc.",
      "grade": "C",
      "fit": "yes",
      "why": "A team API token in the Authorization header runs without a browser, and fixed SQL goes straight to Execute query with no model call.",
      "source": "https://betterstack.com/docs/getting-started/integrations/mcp/",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/better-stack"
    },
    {
      "slug": "causely",
      "name": "Causely MCP server",
      "company": "Causely, Inc.",
      "grade": "E",
      "fit": "yes",
      "why": "A personal or tenant-wide token in X-Causely-Client-Basic skips the browser; tools take structured arguments, so fixed calls need no model call, and team_health or get_environment_health give a digest.",
      "source": "https://docs.causely.ai/agent-integration/mcp-server/",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/causely"
    },
    {
      "slug": "cronitor-mcp",
      "name": "Cronitor MCP server",
      "company": "Cronitor",
      "grade": "C",
      "fit": "yes",
      "why": "The long-lived SDK Integration key works as a Bearer header with no browser; get_status gives an account rollup with failing monitors and list_issues a summary mode, with no model call per query.",
      "source": "https://cronitor.io/docs/mcp-server",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/cronitor-mcp"
    },
    {
      "slug": "datadog-mcp",
      "name": "Datadog MCP Server",
      "company": "Datadog, Inc.",
      "grade": "D",
      "fit": "yes",
      "why": "API and application keys sent as headers run without a browser, queries are passed as written, and the burst limit is 50 calls per 10 seconds.",
      "source": "https://docs.datadoghq.com/bits_ai/mcp_server/setup/",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/datadog-mcp"
    },
    {
      "slug": "grafana-mcp-server",
      "name": "Grafana MCP Server",
      "company": "Raintank Inc., d/b/a Grafana Labs",
      "grade": "BB",
      "fit": "yes",
      "why": "A service account token in GRAFANA_SERVICE_ACCOUNT_TOKEN runs unattended, and fixed PromQL or LogQL run as written with no model call.",
      "source": "https://github.com/grafana/mcp-grafana",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/grafana-mcp-server"
    },
    {
      "slug": "honeycomb-mcp",
      "name": "Honeycomb MCP",
      "company": "Hound Technology, Inc. d/b/a Honeycomb",
      "grade": "B",
      "fit": "yes",
      "why": "A Management API key sent as Authorization: Bearer KEY_ID:SECRET_KEY serves unattended agents, and run_query takes a fixed spec with no model call; run_query allows 100 calls a minute.",
      "source": "https://docs.honeycomb.io/integrations/mcp/configuration-guide",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/honeycomb-mcp"
    },
    {
      "slug": "incident-io",
      "name": "incident.io API",
      "company": "Pineapple Technology Ltd.",
      "grade": "B",
      "fit": "yes",
      "why": "API keys authenticate as a service actor and don't expire until deleted; incident_list, alert_list and incident_stats take structured filters, so a fixed digest needs no model call per query.",
      "source": "https://docs.incident.io/ai/remote-mcp.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/incident-io"
    },
    {
      "slug": "new-relic",
      "name": "New Relic MCP Server",
      "company": "New Relic, Inc.",
      "grade": "B",
      "fit": "yes",
      "why": "A User API key works for automated scripts without a browser, and execute_nrql_query runs fixed NRQL with no model call; the AI analysis tools are OAuth only.",
      "source": "https://docs.newrelic.com/docs/agentic-ai/mcp/overview/",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/new-relic"
    },
    {
      "slug": "pagerduty-mcp",
      "name": "PagerDuty MCP Server",
      "company": "PagerDuty, Inc.",
      "grade": "E",
      "fit": "yes",
      "why": "A User API key in Authorization: Token token= or an app OAuth token from client credentials runs unattended, and browse calls take structured filters with no model call.",
      "source": "https://docs.pagerduty.com/ai-automation/advance/pagerduty-mcp-server.md",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/pagerduty-mcp"
    },
    {
      "slug": "rootly-mcp",
      "name": "Rootly MCP Server",
      "company": "Rootly Inc.",
      "grade": "C",
      "fit": "yes",
      "why": "A Global, Team or Personal API token as a Bearer header runs unattended, and list tools take structured filters with no model call.",
      "source": "https://docs.rootly.com/integrations/mcp-server",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/rootly-mcp"
    },
    {
      "slug": "sentry-mcp",
      "name": "Sentry MCP",
      "company": "Functional Software, Inc. d/b/a Sentry",
      "grade": "B",
      "fit": "caveat",
      "why": "A Sentry-Bearer token header now works on the hosted server, and acc-01 runs a daily digest, but search tools add a model call per query and the maintainers declined a raw query field (#471).",
      "source": "https://github.com/getsentry/sentry-mcp",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/sentry-mcp"
    }
  ],
  "marks": "yes: the docs show it does the job as the success test says. caveat: it does the job with a limit an agent should know. no: it doesn't do this job. unchecked: we couldn't read it.",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "useCase": {
    "accounts": 7,
    "after": [
      "messaging.post-summary",
      "email.send",
      "observability.investigate-alert"
    ],
    "area": "developer",
    "asks": [
      "send me a daily digest of new errors",
      "check the logs every morning",
      "tell me if anything looks off overnight",
      "run these queries every day"
    ],
    "before": [
      "webhooks.schedule-call"
    ],
    "blockers": [
      "browser sign-in that expires and needs a person",
      "LLM token cost of reading raw high-volume streams",
      "natural-language-only query tools that add a model call per query"
    ],
    "capabilities": [
      "observability.errors",
      "observability.logs",
      "observability.metrics",
      "events.schedule"
    ],
    "category": "observability",
    "categoryName": "Observability \u0026 incidents",
    "checked": "2026-11-15",
    "companies": {
      "fit": 11,
      "fitWithLimit": 1,
      "tagged": 20
    },
    "competition": "crowded",
    "fits": [
      "axiom",
      "better-stack",
      "causely",
      "cronitor-mcp",
      "datadog-mcp",
      "grafana-mcp-server",
      "honeycomb-mcp",
      "incident-io",
      "new-relic",
      "pagerduty-mcp",
      "rootly-mcp"
    ],
    "fitsWithLimit": [
      "sentry-mcp"
    ],
    "id": "observability.scheduled-watch",
    "listings": {
      "caveat": 1,
      "no": 0,
      "notRead": 0,
      "tagged": 20,
      "unchecked": 0,
      "yes": 11
    },
    "name": "Watch signals on a schedule and report anomalies",
    "status": "draft",
    "success": "The run completes unattended with a non-interactive credential, runs the fixed queries without an extra LLM call per query, and sends a digest that lists only new or changed findings with links.",
    "url": "https://www.anchorterminal.com/api/v1/use-cases/observability.scheduled-watch.json",
    "weight": 14,
    "weightBasis": "7 of 42 accounts, mostly from the Agentic Monitoring thread; that thread also argues against agents reading raw streams (acc-27)"
  }
}
