P12 SRE Ops MCP Server
Enables SRE operations through natural language, providing tools to query SLO status, fetch runbooks, query alerts, and manage incidents with audit logging and latency tracking.
README
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 |
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
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.