Skip to main content
Glama
Sign In
P12 SRE Ops MCP Server

P12 SRE Ops MCP Server

by amarshiv86
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

P12 · SRE Ops MCP Server

Custom MCP (Model Context Protocol) server exposing SRE tools as LLM-callable actions. Capstone project of the Staff SRE · AI Engineer Portfolio.

Where things live

What

Where

MCP server code

This repo (src/)

Interactive demo

HF Space

Tool examples + audit log

HF Dataset

Related MCP server: Datadog MCP Server

Tools exposed

Tool

Description

get_slo_status

SLO burn rate + error budget per service

get_runbook

Fetch runbook steps for an alert

query_alerts

Recent firing alerts by severity

create_incident

Create incident record

get_incident_timeline

Timeline of events for an incident

summarize_incident

LLM-generated incident summary

Use with Claude Desktop

{
  "mcpServers": {
    "sre-ops": {
      "command": "python",
      "args": ["-m", "src.mcp_server"],
      "cwd": "/path/to/p12-sre-mcp"
    }
  }
}

Then ask Claude: "What's burning right now?" — it calls query_alerts + get_slo_status automatically and synthesizes a response.

SRE additions

  • Every tool call audit logged (timestamp, latency, success — postmortem-ready)

  • Tool latency tracked — SLO: p95 < 500ms

  • Graceful fallback when tools fail

  • JSON-RPC 2.0 protocol compliance

  • Both stdio (Claude Desktop) and HTTP (HF Space demo) transports

Run locally

git clone https://github.com/amarshiv86/p12-sre-mcp
cd p12-sre-mcp
pip install -r requirements.txt

# Run tests
pytest tests/ -v

# Start MCP server (stdio transport)
python -m src.mcp_server

# Test with manual JSON-RPC call
echo '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}' | python -m src.mcp_server

Project structure

p12-sre-mcp/
├── src/
│   ├── tools.py        # 6 SRE tools + audit logging + timed_tool decorator
│   └── mcp_server.py   # JSON-RPC 2.0 stdio transport
├── tests/
│   └── test_mcp.py     # 20 tests (tools + MCP protocol)
├── hf_space/
│   ├── app.py          # Gradio demo — scenario runner + manual tool call
│   ├── README.md       # sdk_version: 5.29.0
│   └── requirements.txt
├── data/
│   ├── raw/tool_call_examples.jsonl
│   └── processed/sample_audit_log.json
├── .github/workflows/
│   ├── ci.yml
│   ├── deploy-hf-space.yml
│   └── deploy-hf-dataset.yml
└── requirements.txt

Stack

MCP Protocol · JSON-RPC 2.0 · Qwen2.5-0.5B · Gradio 5 · Audit logging · GitHub Actions

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    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

    ActivityInactive
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers

    • PilotOps MCP

      muhammedehab35
      F
      license
      Not graded
      quality
      D
      maintenance
      Enables AI-driven incident response by connecting Claude to monitoring tools like Prometheus, Grafana, Loki, PagerDuty, and Slack for automated investigation and runbook generation.
      9
      -

    • Datadog MCP Server

      bhayanak
      A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to interact with Datadog's observability platform via natural language, covering metrics, logs, APM, monitors, dashboards, incidents, and infrastructure.
      1,903 npm
      1
      MIT

    • newrelic-mcp-server

      paradox-vk
      F
      license
      Not graded
      quality
      D
      maintenance
      Provides New Relic observability tools for AI assistants, enabling discovery, data access, alerting, incident response, and performance analytics via natural language queries.
      -

    • semley

      msradam
      A
      license
      Not graded
      quality
      D
      maintenance
      Enables autonomous SRE incident investigation by allowing users to describe incidents in natural language. The agent follows a governed state machine to gather read-only evidence and produce grounded conclusions.
      MIT