RetraceKit
Official remote MCP for RetraceKit. List the project, read issues and incidents, change status, and request AI explanations from Cursor, Claude, Codex, and VS Code.
Ads
Overview
RetraceKit exposes a remote MCP server at https://api.retracekit.cloud/mcp. Agents in Cursor, Claude Code, Codex, VS Code, and other MCP clients can list the project, read issues and incidents, change status, and request AI explanations — the same triage surface as the app.
Use the same project API key as the SDK (from project settings). No separate MCP token. Any Streamable HTTP client needs that URL and the header Authorization: Bearer . Set RETRACE_KIT_API_KEY to the project API key (same value as SDK apiKey), then restart or reload MCP if tools do not appear.
Issue statuses: OPEN, RESOLVED, IGNORED. Manual incident statuses: INVESTIGATING, RESOLVED, ACTIVE.
Issue ref: {projectKey}-{issueKey} — e.g. PRO-123. Incident ref: {projectKey}-I{incidentKey} — e.g. PRO-I1. List tools take projectKey (not UUID). Detail and status tools take the human-readable ref.
Related crashes cluster into one incident by route, release, or session so you triage the outage once.
Capabilities
- list_projects
Return the authenticated RetraceKit project for this API key.
- list_issues
List issues in a project. Takes projectKey (not UUID). Issue refs look like PRO-123.
- get_issue
Get one issue by human-readable ref, e.g. PRO-123.
- update_issue_status
Set issue status to OPEN, RESOLVED, or IGNORED.
- list_incidents
List incidents in a project. Takes projectKey.
- get_incident
Get one incident by ref, e.g. PRO-I1.
- update_incident_status
Set manual incident status to INVESTIGATING, RESOLVED, or ACTIVE.
- list_issue_incidents
List incidents linked to an issue.
- explain_issue
AI brief for an issue from stack, breadcrumbs, and release context.
- explain_incident
AI brief for an incident cluster — title and summary of the outage.
Installation
Remote Streamable HTTP — no local package. URL: https://api.retracekit.cloud/mcp Header: Authorization: Bearer <RETRACE_KIT_API_KEY> Use the same project API key as the SDK (project settings in the app). Docs: https://retracekit.cloud/docs/mcp
Configuration
{
"mcpServers": {
"retracekit": {
"url": "https://api.retracekit.cloud/mcp",
"headers": {
"Authorization": "Bearer ${env:RETRACE_KIT_API_KEY}"
}
}
}
}Paste into ~/.cursor/mcp.json or .cursor/mcp.json
Supported clients
- Cursor
- Claude Desktop
- VS Code
Tags
- monitoring
- observability-incident
- errors
Related MCP servers
Monitoring
cloudsealed/cloudsealed-mcp
Two deterministic, rule-based analysis engines for agents: cloud billing cost anomaly detection (rolling-median + MAD, resistant to the masking effect) and auditable architecture risk scoring (single point of failure, coupling, scalability gap) with a rule-by-rule breakdown for every score. `uvx cloudsealed-mcp`
Monitoring
arsentev-ai/contextburn
Run efficiency for Claude Code sessions: the share of paid tokens that became model output versus re-reading context already sent, by tokens and cost-weighted. Reads local transcripts, makes no network calls.
Monitoring
seancrecord/scvd-general-store-repo (scvd-tab)
Agent tool spend tracker. Local JSONL storage, consent-gated, nothing leaves the file. Free MCP server. `npx scvd-tab`
Monitoring
FailEcho/failecho
Cross-agent failure intelligence. Before an agent retries a failed tool call, `check_tool_failure` reports whether other agents are hitting the same failure right now and which recovery actually worked, with a Wilson-score confidence. Privacy-by-schema: no prompts, keys, or payloads stored. Hosted remote server at `https://failecho.com/mcp`, or self-host.
Monitoring
AIops-tools/Endpoint-AIops
Governed managed-endpoint fleet operations (thin-client/VDI) — login-storm and patch/config-drift analysis, inventory, and guardrailed remediation (13 tools) with unbypassable audit logging (MCP + CLI), budget/runaway guards, and undo/rollback.
Monitoring
magna-nz/tallybook
Prices every Claude Code and Codex session already on disk and lets the agent ask what it's spending mid-session: cost by session, sub-agent and model, week-on-week comparison, and plain-English findings with applyable patches. No proxy, no API key, nothing leaves the machine. Install: `brew install --cask magna-nz/tap/tallybook`.
Monitoring
iris-eval/mcp-server
Iris scores every agent run for quality, safety, and cost — on your machine, with no SDK and no account. Most agent projects check quality by running a few remembered prompts and eyeballing the output. Iris replaces that with numbers you can audit: your agent's runs land in a SQLite database on your disk, 13 built-in rules score them deterministically — PII, prompt injection, hallucination markers, cost thresholds — free, with no LLM calls, and an optional LLM judge with a hard per-eval cost cap handles the semantic questions. Every rule is inspectable and editable, because a judge you can't audit is just vibes with a number on it. MIT licensed, no telemetry; your traces never leave your machine.
6 tools · deploy_rule, evaluate_output
Monitoring
last9/last9-mcp-server
Your AI agent doesn't know what's broken in production. This fixes that. Last9 MCP Server connects Claude, Cursor, Windsurf, and any other MCP-capable AI assistant directly to your production observability data — logs, metrics, traces, exceptions, database queries, alerts, and deployments. The agent stops guessing and starts reading the actual signal. No binary to install. No tokens to manage. One URL, OAuth in your browser, done. Find your org slug in your Last9 URL: app.last9.io/<org_slug>/... Type /mcp, select last9, authenticate. That's it.
6 tools · get_alerts, get_database_slow_queries