Rudow MCP Server
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., "@Rudow MCP Server Why is checkout failing right now?"
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.
Rudow MCP Server
Rudow watches your app's logs and tells you what's broken. This Model Context Protocol server lets your AI assistant — Claude, Cursor, Windsurf, VS Code and others — query your Rudow projects directly: logs, metrics, incidents and semantic search.
Ask things like:
"Why is checkout failing right now?"
"What's our p95 latency on
/api/ordersover the last 24 hours?""Show me the errors around 14:32 yesterday."
"Are there any open incidents?"
Get an MCP key
Sign in to the Rudow dashboard.
Go to Settings → Account → MCP keys and click Create MCP key.
Pick which projects the key can reach, then copy the key (it starts with
alogmcp_and is shown once).
Related MCP server: Datadog MCP Server
Connect
There are two ways to connect. Both use the same key and give the same tools.
Option 1: hosted server (recommended)
If your client supports remote MCP servers, point it at:
URL:
https://mcp.rudow.ai/mcp(Streamable HTTP)Header:
Authorization: Bearer <your MCP key>
Claude Code
claude mcp add --transport http rudow https://mcp.rudow.ai/mcp \
--header "Authorization: Bearer alogmcp_..."Cursor (.cursor/mcp.json)
{
"mcpServers": {
"rudow": {
"url": "https://mcp.rudow.ai/mcp",
"headers": { "Authorization": "Bearer alogmcp_..." }
}
}
}Option 2: local package (stdio)
For clients that only run local servers, use this package. It runs on your machine and forwards each tool call to the hosted server.
Claude Desktop (claude_desktop_config.json), Cursor, Windsurf and most other clients:
{
"mcpServers": {
"rudow": {
"command": "npx",
"args": ["-y", "rudow-mcp-server"],
"env": { "RUDOW_MCP_KEY": "alogmcp_..." }
}
}
}Claude Code
claude mcp add rudow --env RUDOW_MCP_KEY=alogmcp_... -- npx -y rudow-mcp-serverDocker
docker build -t rudow-mcp-server .
docker run -i --rm -e RUDOW_MCP_KEY=alogmcp_... rudow-mcp-serverTools
Start with list_projects. Every other data tool takes the project_id it returns.
Tool | What it does |
| Lists the projects your key can access. |
| Setup info for Rudow's SDKs, so your assistant can add logging to your codebase. |
| Incidents Rudow detected, newest first. |
| Why an incident fired, top error groups and timeline. |
| Log entries filtered by level, source, text and time. |
| A time-balanced sample over a large window. |
| Counts grouped by level, source, status or route. |
| Finds logs by meaning, from a plain-English description. |
| The log lines just before and after a timestamp. |
| Health overview: volume, error rate, latency, top routes and process metrics. |
| Requests, error rate, latency and top error routes. |
| Volume, error rate and latency over time. |
| Latency percentiles (p50–p99). |
| Busiest and most-failing routes. |
| Breakdown of log levels. |
| Deep dive into one route. |
| Rejected ingest requests, for SDK and payload issues. |
Full input schemas are in src/tools.ts.
All tools are read-only. Your key only reaches the projects you chose when you created it, and you can revoke it from the dashboard at any time.
Configuration
Variable | Required | Default |
| yes | — |
| no |
|
Development
npm install
npm test # build and run tests
RUDOW_MCP_KEY=alogmcp_... npm run check-tools # compare src/tools.ts with the hosted serverLicense
Available Tools
17 toolsaggregate_logsBInspect
Count log entries grouped by a dimension over a recent window. Call this to spot trends, e.g. error rate or status-code distribution.
Inputs: project_id (required), minutes, group_by.
failed_ingest_summaryAInspect
Summary of failed ingest requests over a recent window: count of validation failures, most recent failure, and error details. Use this to troubleshoot SDK/client issues or payload format problems.
Inputs: project_id (required), minutes.
fetch_windowAInspect
Fetch the log entries immediately before and after a timestamp, to see the context around a specific event.
Inputs: around_iso (required), project_id (required), n.
get_incidentBInspect
Full detail of one incident: why it fired (signals with observed vs usual), top error groups, timeline.
Inputs: project_id (required), incident_id (required).
list_incidentsCInspect
List incidents Rudow detected for this project (newest first). Use to answer what's broken now or recently.
Inputs: project_id (required), status.
list_projectsAInspect
List the projects you have access to. Call this first to get a project_id to pass to the other tools.
Inputs: no named parameters.
list_sdksAInspect
Get setup info for Rudow's client SDKs (Node.js backend, Python backend) — package name, install command, a minimal config/usage snippet, and how to obtain a project ingest API key. Use this to help a user add logging to their own codebase: install the right package for their stack and write the snippet into their code yourself — this tool only returns information, it does not install anything or touch the user's files. It never creates or reveals an ingest API key; the user must generate one manually from the dashboard (see key_instructions in the result) and paste it in themselves.
Inputs: no named parameters.
metrics_distributionsAInspect
Response time distribution: histogram showing the spread of latencies (p50, p75, p90, p95, p99). Use this to understand if latency is consistent or if there are outliers and slow queries.
Inputs: project_id (required), minutes.
metrics_levelsAInspect
Distribution of log levels: count and percentage of debug, info, warn, error, and fatal entries. Use this to understand the severity profile of logs and if error rates are elevated.
Inputs: project_id (required), minutes.
metrics_overviewAInspect
Overview section of metrics: total requests, error count & rate, average/p95 latency, and top error routes. Use this for a quick health snapshot focused on request volume and performance.
Inputs: project_id (required), minutes.
metrics_routesBInspect
Top routes by request volume and error count. Shows which endpoints are getting the most traffic and which are failing most often. Use this to identify hot spots and problem areas.
Inputs: project_id (required), minutes.
metrics_summaryAInspect
Computed health overview from telemetry: request volume, error rate (4xx/5xx), average and p95 latency, the top routes by traffic and errors, and the latest process metrics (memory, event-loop lag, uptime). Call this to answer how the app is performing or whether it is healthy.
Inputs: project_id (required), minutes.
metrics_trendsAInspect
Trends section: request volume, error rate, and latency over time in bucketed intervals. Call this to understand how performance has changed and spot degradation or recovery patterns.
Inputs: project_id (required), minutes.
query_logsBInspect
Fetch matching log entries for this project, newest first. Use to inspect specific errors or recent activity. Call this when you need the actual log lines.
Inputs: project_id (required), text, level, limit, +3 more.
query_logs_batchedAInspect
Fetch a time-bucketed sample over a larger window. Useful when logs are high-volume: returns a balanced slice across time buckets instead of only the very latest lines.
Inputs: project_id (required), text, limit, minutes, +2 more.
route_drilldownAInspect
Deep dive into a specific route: request count, error rate, average and p95 latency, errors by status code. Call this after seeing a problematic route in metrics_routes to get details.
Inputs: route (required), project_id (required), minutes.
semantic_searchAInspect
Find log entries whose meaning is similar to a natural-language description, using vector similarity (not substring matching). Use this when the user describes a problem in their own words rather than citing exact log text — e.g. 'requests failing because the database was down'. Covers all logs once they have been embedded (a background job embeds new logs shortly after ingest).
Inputs: query (required), project_id (required), limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 17 tools
Most tools have distinct purposes, but metrics_summary and metrics_overview clearly overlap — summary is described as a superset of the overview content, so an agent could easily pick the wrong one. The six-tool metrics_* family (summary/overview/trends/distributions/routes/levels) also has blurry boundaries between 'health snapshot' and 'computed health overview.'
All snake_case, which is good, but verb conventions vary: list_/get_/query_/fetch_/aggregate_ for retrieval plus bare-noun-prefixed metrics_* and semantic_search/route_drilldown. Still readable and predictable enough to map names to intent.
17 tools for an observability/logging server is on the heavy side, and the metrics area is split into six separate tools where a composite or parameterized tool could reduce surface area. Individually each earns some place, but the metrics fan-out feels like over-decomposition.
Coverage is broad for the domain: logs (latest, sampled, aggregate, semantic, contextual), metrics, incidents, route drilldown, ingest failures, SDK onboarding, and project listing. The main gap is incident lifecycle actions (acknowledge/resolve) and any write/config operations, but core read workflows are well covered.
Maintenance
Related MCP Connectors
Lets AI agents analyze API metrics, request logs, and traces, and manage apps and alerts.
Manage uptime monitors and incidents and search logs, metrics and traces from an AI assistant.
Read-only access to a Lumin project's logs, metrics, uptime checks, alerts and infrastructure.
Read-only AI coding tools for change verification, release readiness, capacity, and guidance.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to query and manage Datadog observability data including metrics, logs, traces, and monitors through natural language. Supports read-only operations by default for security.MIT
- AlicenseAqualityCmaintenanceEnables AI assistants to access full Datadog observability, including log search, APM trace filtering, smart sampling, and cross-correlation between logs, traces, and metrics.231,992 npm6Apache 2.0
- FlicenseNot gradedqualityAmaintenanceEnables AI agents to query and debug trace, session, exception, prompt, dataset, score, and metric data, with selective tool loading and read-only operation for safer local observability workflows.-
- FlicenseNot gradedqualityAmaintenanceEnables AI agents and developers to query trace, session, exception, routing, prompt, dataset, score, and metrics data for debugging, triage, and observability, with selective tool loading and a read-only mode.-