Skip to main content
Glama
Jeromefromcn

ops-agent-toolkit-mcp

by Jeromefromcn
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

ops-agent-toolkit-mcp

MCP server exposing read-only ops tools to an agent troubleshooting the lab-environment sandbox.

Tools

Tool

Backend

Purpose

search_logs(service, keyword, minutes_ago)

Loki

Search service logs by keyword and time window

query_metric(service, metric_name, minutes_ago)

Prometheus

Get a metric's summary (mean/peak/threshold), not raw series

get_trace(trace_id) / search_traces(service, error_only)

Jaeger

Fetch or search distributed traces, formatted as a span tree

get_service_health(service)

Consul

Check service registration/health status

get_service_config(service)

Consul KV

Read a service's current config

toggle_chaos_scenario(service, scenario, enabled)

Consul KV

Enable/disable a fault scenario

See ROADMAP.md for planned additions (Kafka tools, multi-agent permission scoping, K8s tools).

Related MCP server: MCP Observability Server

Run locally (stdio mode)

pip install -r requirements.txt
python server.py

Run as a container (HTTP/SSE mode)

docker build -t ops-lab/mcp-toolkit:dev .

Intended to run inside the lab-environment docker-compose network, so it can reach Loki/Prometheus/Jaeger/Consul by service name.

Design principles

  • Read-only by default. The one exception is toggle_chaos_scenario, scoped to chaos toggle keys only. No tool restarts services, rolls back deployments, or writes real app config. Further write-capable tools require explicit discussion.

  • Parameterized, not raw passthrough. Never expose PromQL/LogQL directly to the model.

  • Every call is audited — tool name, args, duration, and a result preview are logged.

  • One tool, one job. Keep tool boundaries narrow so the agent composes them itself.

Roadmap

See ROADMAP.md.

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivitySlowing
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • mcp-grafana

    romaine-life
    F
    license
    Not graded
    quality
    D
    maintenance
    In-cluster MCP server for read-only diagnostics of Grafana, Prometheus, Alertmanager, and Loki, enabling metric queries, alert listings, and log queries through Grafana datasource proxies with Kubernetes RBAC authentication.
    -

  • MCP Observability Server

    Sushma243
    F
    license
    Not graded
    quality
    C
    maintenance
    MCP server for observability that provides tools for log search, metrics inspection, SQL querying, incident summaries, and service discovery.
    -

  • datadog-aws-mcp

    edxmorales
    A
    license
    Not graded
    quality
    B
    maintenance
    A read-only MCP server that exposes tools to query Datadog monitors and logs, and AWS CloudWatch Logs, and to group recurring errors by fingerprint. Designed for use with Claude Code to diagnose issues and propose fixes.
    MIT

  • enterprise-mcp

    dbett4
    A
    license
    Not graded
    quality
    A
    maintenance
    An MCP server exposing scoped, read-only enterprise operations tools with fail-closed credential handling. It returns opaque approval IDs for mutations and requires a separate operator approval command to release one-time capabilities.
    MIT