A
licenseNot graded
qualityB
maintenanceAI-powered engineering-ops platform for service monitoring, metrics, and incident management, exposed to Claude via MCP so an agent can triage incidents and draft postmortems directly.
7
MIT
Agent Rescue Desk Production Triage
Server Details
Read-only triage for n8n, MCP, webhook, and AI agent workflow production failures.
If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
A4.3/5.0
Scored across 3 tools
Disambiguation5/5
Each tool has a distinct purpose: one describes the service offer, one provides intake requirements, and one triages incidents. No overlap.
Naming Consistency5/5
All tool names follow a consistent verb_noun pattern in snake_case (describe_rescue_offer, get_case_intake_requirements, triage_production_failure).
Tool Count5/5
Three tools is appropriate for the focused domain of describing the rescue service, providing intake requirements, and triaging failures.
Completeness4/5
The toolset covers key aspects: describing the offer, intake requirements, and triage. Missing a submit or status tool, but actions are handled via external URLs.
Available Tools
3 toolsdescribe_rescue_offerDescribe the 12-Hour Agent RescueARead-onlyIdempotentInspect
Returns the exact scope, price, service window, acceptance rules, private fit-review URL, and direct x402 purchase URL for the Agent Rescue Desk service.
Inputs: no named parameters.
get_case_intake_requirementsGet Rescue Case Intake RequirementsARead-onlyIdempotentInspect
Returns the minimum redacted evidence needed for a fixed-scope fit review and the public intake URL. It does not submit a case.
Inputs: no named parameters.
triage_production_failureTriage an AI Workflow Production FailureARead-onlyIdempotentInspect
Classifies one sanitized n8n, MCP, webhook, agent-tool-routing, retry, or general production incident and returns concrete next checks without echoing the submitted incident.
Inputs: incident (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Know when your n8n workflows, URLs, and AI apps break, before your customers do.
Read LogBrew errors, slow traces, logs, and product analytics, and triage issues with consent.
Read-only access to Auralogs production logs: search logs, inspect errors, review AI analyses.
Read-only production error evidence for coding agents investigating failures.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceMCP server for enterprise operations, enabling Sentry error triage, Linear issue sync, and Slack incident response with tools for parsing stacktraces, dispatching alerts, and generating postmortems.MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to investigate production incidents by exposing service health, logs, and deployment data through MCP tools.5 npmISC
- AlicenseNot gradedqualityDmaintenanceMCP server that provides guarded, audited, read-only access to ops tooling (alerts, metrics, logs, deploys, runbooks) and a triage agent that diagnoses incidents end-to-end with CI-verified root cause analysis.MIT
Try in Browser
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
Glama MCP Gateway
Add one secure layer between your agents and this server.