ops-agent-toolkit-mcp
MCP server providing read-only operational tools (logs, metrics, traces, service health, config) for troubleshooting an environment, with one exception for toggling chaos scenarios.
README
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).
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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.