Rudow MCP Server
UPDATE REQUEST for pending submission ID 19072 (submitted 2026-11-17): please change the contact email from hello@prenzio.com to support@pankow.ai. This is NOT a new listing, it is a contact-email correction for the existing pending submission. Hosted, read-only MCP server for production logs. AI agents ask questions about logs in plain English and get answers, with no write access and no query language to learn. 17 read-only tools.
Hosted MCP Server
npx add-mcp 'https://mcp.rudow.ai/mcp'Installs into Claude Code, Codex, Cursor and more
Documentation
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, Claude Code, Cursor, VS Code, Windsurf and others) work with your Rudow projects directly: query logs, metrics and incidents, and set Rudow up in your codebase.
Ask things like:
- "Add Rudow logging to this app."
- "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? Draft the post-mortem for the one that just resolved."
Connect (recommended: browser sign-in)
Point your client at the hosted server. There's no key to copy: the first time you use it, your client opens a Rudow page in your browser, you log in and click Allow, and you're connected.
- URL:
https://mcp.rudow.ai/mcp(Streamable HTTP)
Claude Code
claude mcp add --transport http rudow https://mcp.rudow.ai/mcp
Then run /mcp in Claude Code and pick Rudow to sign in.
Claude (desktop and web): Settings → Connectors → Add custom connector → paste https://mcp.rudow.ai/mcp → Connect. Rudow is also in Claude's connector directory.
Cursor: Add to Cursor, or in .cursor/mcp.json:
{ "mcpServers": { "rudow": { "url": "https://mcp.rudow.ai/mcp" } } }
VS Code: Add to VS Code
For a team: commit this as .mcp.json in your repo. Each teammate signs in with their own Rudow account, and no keys are stored in the file.
{ "mcpServers": { "rudow": { "type": "http", "url": "https://mcp.rudow.ai/mcp" } } }
When you sign in, Rudow shows which app is asking, where it will return to, and lets you allow all your projects or only some. Signed-in apps are listed in the dashboard under Settings → Account → Connected apps, where Disconnect cuts them off immediately.
Connect with an MCP key
For scripts, CI, or clients without browser sign-in.
- Sign in to the Rudow dashboard.
- Go to Settings → Account, under Use an MCP key instead, and create a key.
- Choose Read & write (includes the setup and incident tools) or Read only, pick which projects it can reach, and copy the key. It starts with
alogmcp_and is shown once.
Hosted server with a key
- URL:
https://mcp.rudow.ai/mcp - Header:
Authorization: Bearer <your MCP key>
claude mcp add --transport http rudow https://mcp.rudow.ai/mcp \
--header "Authorization: Bearer alogmcp_..."
{
"mcpServers": {
"rudow": {
"url": "https://mcp.rudow.ai/mcp",
"headers": { "Authorization": "Bearer alogmcp_..." }
}
}
}
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 with your key.
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-server
Docker
docker build -t rudow-mcp-server .
docker run -i --rm -e RUDOW_MCP_KEY=alogmcp_... rudow-mcp-server
Set up Rudow from your editor
With browser sign-in or a Read & write key, ask "add Rudow logging to this app". Your assistant will:
- Create a Rudow project (
create_project). - Write the project's ingest key to your app's
.envasRUDOW_API_KEY. The key is shown once and never again; keep.envout of git. - Install the SDK (
@rudow/node-loggerfor Node.js,rudowfor Python) and add the setup code (list_sdks). - Confirm logs are arriving (
check_ingestion).
Normal plan limits apply. A connection limited to specific projects can't create new ones.
Tools
Start with list_projects. Every other project tool takes the project_id it returns.
Read (every connection and key)
| Tool | What it does |
|---|---|
list_projects | Lists the projects you can access. |
list_sdks | Setup info for Rudow's SDKs, so your assistant can add logging to your codebase. |
list_incidents | Incidents Rudow detected, newest first. |
get_incident | Why an incident fired, top error groups and timeline. |
query_logs | Log entries filtered by level, source, text and time. |
query_logs_batched | A time-balanced sample over a large window. |
aggregate_logs | Counts grouped by level, source, status or route. |
semantic_search | Finds logs by meaning, from a plain-English description. |
fetch_window | The log lines just before and after a timestamp. |
metrics_summary | Health overview: volume, error rate, latency, top routes and process metrics. |
metrics_overview | Requests, error rate, latency and top error routes. |
metrics_trends | Volume, error rate and latency over time. |
metrics_distributions | Latency percentiles (p50–p99). |
metrics_routes | Busiest and most-failing routes. |
metrics_levels | Breakdown of log levels. |
route_drilldown | Deep dive into one route. |
failed_ingest_summary | Rejected ingest requests, for SDK and payload issues. |
Setup and incident actions (browser sign-in or a Read & write key)
| Tool | What it does |
|---|---|
create_project | Creates a project and returns its first ingest key, once. |
create_ingest_key | Creates another ingest key for a project, shown once. |
check_ingestion | Is the project receiving logs? A short verdict. |
resolve_incident | Resolves an incident, or marks it a false alarm. |
request_postmortem | Asks Rudow to draft (or regenerate) an incident's post-mortem. |
update_postmortem | Edits a post-mortem: sections, what to fix, action items, status. |
With a Read only key, the hosted server lists only the read tools, and this package returns "this MCP key is read-only" if a setup tool is called. Full input schemas are in src/tools.ts.
The MCP server can't sign you up, invite or remove teammates, delete projects or change billing. Those stay in the dashboard. Every connection only reaches the projects you allowed, and you can disconnect it or revoke its key at any time.
Configuration (local package)
| Variable | Required | Default |
|---|---|---|
RUDOW_MCP_KEY | yes | — |
RUDOW_MCP_URL | no | https://mcp.rudow.ai/mcp |
Development
npm install
npm test # build and run tests
RUDOW_MCP_KEY=alogmcp_... npm run check-tools # compare src/tools.ts with the hosted server (use a Read & write key)