Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@SREGym Incident Replay Gate Replay the latest incident and score my SRE agent's response."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Prove your SRE agent can resolve incidents before production.
SREGym Incident Replay Gate is a paid hosted remote MCP for SREGym. It exposes Streamable HTTP tool calls, bearer-token access, public server-card metadata, usage logs, and receipt-oriented JSON for AI agent workflows.
Website: https://sregymgate.clauxel.com/?utm_source=github&utm_medium=directory&utm_campaign=sbl202605r27
MCP endpoint: https://sregymgate.clauxel.com/mcp
Server card: https://sregymgate.clauxel.com/server-card.json
Registry name: com.clauxel.sregymgate/sregymgate-mcp
Related MCP server: Sentinel MCP
This is a paid hosted remote MCP. Production calls require a bearer token issued from the product website.
Authorization: Bearer <token>Unauthenticated browser visits to /mcp return a clear JSON error instead of internal details.
run_incident_replay
score_sre_agent
export_incident_verdict
compare_runbook_versions
Open the website and choose a plan.
Create or request an API token.
Add the endpoint to an MCP client that supports Streamable HTTP remote servers.
Send JSON-RPC requests with the bearer token.
Product page: https://sregymgate.clauxel.com/?utm_source=github&utm_medium=directory&utm_campaign=sbl202605r27
Server card: https://sregymgate.clauxel.com/server-card.json
MCP endpoint: https://sregymgate.clauxel.com/mcp
This repository is a public documentation and directory-submission reference for the hosted service. It does not contain the private production source code.
This server cannot be deployed
AI agent run monitoring with incident replay and SLA receipts.
MCP-native AI SRE: ask what's broken in production, get a reviewed GitHub fix PR.
Synthetic checks, nightly regression replay and model-drift alerts for AI agents
Remote MCP for A2A failure replay MCP, structured receipts, audit logs, and reviewer-ready evidence.