Thin MCP server for GrowthBook — skill loader + authenticated API passthrough
Rudow is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Query your app's logs, metrics and incidents from your AI assistant.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'RUDOW_MCP_KEY=${RUDOW_MCP_KEY}' --transport stdio rudow-mcp '--' npx -y rudow-mcp-server
# 2 — ask your agent for something these tools do
# list_projects, list_sdks, list_incidents and 14 more
It needs RUDOW_MCP_KEY: this reads it from your environment, so export it first.
Rudow costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one can run either way — at an address its publisher runs, or as a process under your own user, with your files and your network — and this marketplace is in the path of neither.
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads RUDOW_MCP_KEY (Your Rudow MCP key (create one in the Rudow dashboard under Settings → Account → MCP keys)) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx RUDOW_MCP_KEY … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'RUDOW_MCP_KEY=${RUDOW_MCP_KEY}' --transport stdio rudow-mcp '--' npx -y rudow-mcp-serverReconnect, or start a new session, and the tools appear in the model’s tool list.
Its publisher also runs it at https://mcp.rudow.ai/mcp: nothing to start on your machine, and this marketplace is not in the path.
claude mcp add --scope user --transport http rudow-mcp https://mcp.rudow.ai/mcpIt reaches a system of yours, so it needs your own credential rather than the publisher’s: RUDOW_MCP_KEY — Your Rudow MCP key (create one in the Rudow dashboard under Settings → Account → MCP keys).. You set it in your own client’s config, on your machine — this marketplace never holds it.
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
17 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
List the projects you have access to. Call this first to get a project_id to pass to the other tools.
No parameter schema on file.
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…
No parameter schema on file.
List incidents Rudow detected for this project (newest first). Use to answer what's broken now or recently.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | string | no | — |
| project_id | string | yes | The project to query. Call list_projects first to see which ids you can use. |
Full detail of one incident: why it fired (signals with observed vs usual), top error groups, timeline.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| incident_id | string | yes | — |
| project_id | string | yes | The project to query. Call list_projects first to see which ids you can use. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| level | string | no | Filter by severity level. |
| source | string | no | Filter by source, e.g. 'backend' or 'browser'. |
| text | string | no | Case-insensitive substring match on the message. |
| minutes | integer | no | Only entries from the last N minutes. |
| before_iso | string | no | Only entries before this ISO timestamp (cursor pagination). |
| limit | integer | no | Max rows to return (default 50, max 200). |
| project_id | string | yes | The project to query. Call list_projects first to see which ids you can use. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | no | Optional substring filter across message and attributes. |
| minutes | integer | no | Window size in minutes (default 60). |
| bucket_minutes | integer | no | Bucket width in minutes (default 5). |
| per_bucket | integer | no | Max rows per bucket (default 20). |
| limit | integer | no | Total max rows returned (default 400). |
| project_id | string | yes | The project to query. Call list_projects first to see which ids you can use. |
Count log entries grouped by a dimension over a recent window. Call this to spot trends, e.g. error rate or status-code distribution.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| group_by | string | no | Dimension to group counts by. |
| minutes | integer | no | Window size in minutes (default 60). |
| project_id | string | yes | The project to query. Call list_projects first to see which ids you can use. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| minutes | integer | no | Window size in minutes (default 60). |
| project_id | string | yes | The project to query. Call list_projects first to see which ids you can use. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| minutes | integer | no | Window size in minutes (default 60). |
| project_id | string | yes | The project to query. Call list_projects first to see which ids you can use. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| minutes | integer | no | Window size in minutes (default 60). |
| project_id | string | yes | The project to query. Call list_projects first to see which ids you can use. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| minutes | integer | no | Window size in minutes (default 60). |
| project_id | string | yes | The project to query. Call list_projects first to see which ids you can use. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| minutes | integer | no | Window size in minutes (default 60). |
| project_id | string | yes | The project to query. Call list_projects first to see which ids you can use. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| minutes | integer | no | Window size in minutes (default 60). |
| project_id | string | yes | The project to query. Call list_projects first to see which ids you can use. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| route | string | yes | The route path to drill down into, e.g. '/api/v1/chat'. |
| minutes | integer | no | Window size in minutes (default 60). |
| project_id | string | yes | The project to query. Call list_projects first to see which ids you can use. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| minutes | integer | no | Window size in minutes (default 60). |
| project_id | string | yes | The project to query. Call list_projects first to see which ids you can use. |
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…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Natural-language description of what to find. |
| limit | integer | no | Max results to return (default 20, max 50). |
| project_id | string | yes | The project to query. Call list_projects first to see which ids you can use. |
Fetch the log entries immediately before and after a timestamp, to see the context around a specific event.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| around_iso | string | yes | ISO-8601 timestamp to center the window on. |
| n | integer | no | Entries on each side (default 10, max 50). |
| project_id | string | yes | The project to query. Call list_projects first to see which ids you can use. |
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Rudow or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.0. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish Rudow can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.