Skip to content
Agentmart
Submit a tool

Observability MCP

Unified observability gateway for AI agents — Prometheus, Loki & more, with anomaly detection.

Connector by ThoTischner · GitHub account verified by the MCP Registry

IndexedApache-2.0Local (stdio)★ 7
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/thotischner-observability-mcp

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Unified observability gateway for AI agents — Prometheus, Loki & more, with anomaly detection.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.

Tools
10 read · 0 write · 0 delete · 2 not yet classified
Secrets
None asked for
Install scripts
None found
Runs as
Node.js package

Tools by what they do 12

Read from the source code; the running server may list different tools.

Read 10 · Look things up without changing anything.

  • detect_anomalies
  • get_anomaly_history
  • get_blast_radius
  • get_service_health
  • get_topology
  • list_services
  • list_sources
  • query_logs
  • query_metrics
  • query_traces

Not yet classified 2 · We could not tell from the name and description.

  • enrich_ips
  • generate_postmortem

Secrets and settings it asks for

Other settings (environment variables or headers).

  • LOKI_URL
  • MCP_TRANSPORT
  • PROMETHEUS_URL

Network hosts it talks to 8

  • api.datadoghq.com · found in code
  • github.com · found in code
  • glama.ai · found in code
  • helm.sh · found in code
  • host.docker.internal · found in code
  • raw.githubusercontent.com · found in code
  • rdap.org · found in code
  • thotischner.github.io · found in code

Files it touches

  • /tmp/oidc-dcr.json
  • /tmp/postmortems.jsonl
  • /tmp/scim.json
  • /var/lib/observability-mcp/scim.json
  • Your home directory (~)
  • Any path the agent passes to its tools

Tools (12)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • detect_anomalies

    Scan for anomalies across all monitored services (or a specific service). Detects metric deviations using z-score analysis against recent baseline, checks log error spikes, and correlates signals across metrics and logs. Returns anomalies with severity ratings and cross-signal correlations.

  • enrich_ips
  • generate_postmortem

    Stitch the gateway's primitives (anomaly history, blast-radius, traces, log highlights) into a single markdown post-mortem report for one service over a given window. When to use: after an incident, when the operator or LLM wants 'one document the on-call can read in 60 seconds' instead of poking the individual tools. Prerequisites: anomaly history requires OMCP_ANOMALY_HISTORY_REMOTE_WRITE configured AND a Prometheus source pointed at the same TSDB (see docs/anomaly-history.md). Traces require a Tempo / Jaeger source. Blast-radius requires a topology provider. Behavior: read-only. Returns BOT…

  • get_anomaly_history

    Replay historical anomaly scores for a service from the TSDB the gateway writes to (omcp_anomaly_score series). When to use: post-mortem reconstruction (what did the gateway see at 03:42?), trend analysis on detector noise, or pulling context for the LLM when an incident is reviewed after the fact. Prerequisites: the operator must have OMCP_ANOMALY_HISTORY_REMOTE_WRITE configured AND a Prometheus connector pointed at the same TSDB so the round-trip closes. Behavior: read-only. Returns the time-series of scores with per-method/severity labels. Empty result means either no anomalies in the windo…

  • get_blast_radius
  • get_service_health

    Get an aggregated health overview for a service combining metrics AND logs. Returns a health score (0-100), status (healthy/degraded/critical), key metric values, log error summary, detected anomalies, and cross-signal correlations.

  • get_topology
  • list_services

    List all monitored services discovered across all connected backends. Returns service names, their data sources, and signal types (metrics/logs).

  • list_sources

    List all configured observability backends and their connection status. Use this to discover what data sources are available.

  • query_logs

    Query logs for a service over a given timeframe. Returns log entries with a summary including error/warning counts and top error patterns. Filter by log level, a free-text/regex search, OR structured `labels` (exact-match on backend-extracted fields like method/status/url/environment — far more reliable than regex on structured JSON logs).

  • query_metrics

    Query a specific metric for a service over a given timeframe. Returns time-series data with pre-computed summary statistics (current, average, min, max, trend). Available metrics: cpu, memory, error_rate, request_rate, latency_p99, latency_p50, latency_avg.

  • query_traces

    Query distributed traces for a service over a given timeframe. Returns ranked trace summaries with duration, error status, and span count, plus a p50/p95 duration aggregate across the returned set. When to use: investigating tail-latency outliers, walking call chains across services for a known time window, or pulling related traces for an anomaly the metric/log tools surfaced first. Behavior: read-only; results may be capped via `limit` (default 50). `filter` accepts the backend's native query language (e.g. TraceQL on Tempo). When `errorsOnly=true`, only traces with at least one error span a…

Compare and alternatives

    Featured in

    Signals

    Stars
    7
    Forks
    1
    Open issues
    0
    Last commit
    Oct 19, 2026 (9 days ago)
    Last release
    Oct 19, 2026 (9 days ago)

    From GitHub (fetched Oct 24, 2026).

    Details

    Registry name
    io.github.ThoTischner/observability-mcp
    Version
    3.9.14
    Auth
    No auth
    Packages
    npm @thotischner/observability-mcp
    License
    Apache-2.0
    Repository
    github.com/ThoTischner/observability-mcp
    First seen
    Oct 24, 2026
    Last checked
    Oct 24, 2026
    Source
    Official MCP Registrygithub-graphql
    Cite this page

    Observability MCP. Agent Mart. https://agentmart.dev/connectors/thotischner-observability-mcp (last updated 2026-10-24)