---
title: "The check your coding agent can call | Skene"
description: "Skene runs as a hosted MCP server: eleven tools your agent calls in the same session it is already in, scoped by the API key you issue."
url: https://www.skene.ai/developers/mcp
doc_version: "f353917c3682"
last_updated: 2026-08-29
---

MCP server

# The check your coding agent can call, before the pull request opens.

Skene runs as a hosted MCP server: eleven tools your agent calls in the same session it is already in, scoped by the API key you issue.

[Start free](https://www.skene.ai/signup) [See it against a coding agent](https://www.skene.ai/vs/coding-agents)

MCP is the protocol your agent uses to call outside tools. The hosted endpoint is www.skene.ai/api/mcp; auth is a workspace API key.

acme/webapp #4815

Agent

Complete. The feature works and the tests pass.

Check

`signup_completed` is no longer recorded on this path.

- **Runs in the same session**
  Not a separate tool to open or a second dashboard to check. One more thing the agent can call mid-turn.

- **The gate is deterministic**
  Returns the events your journey says should exist and do not. Call it over HTTP or as an MCP tool.

- **Scoped by the API key you issue**
  Hosted by Skene. The key belongs to the workspace, and you issue it.

Supabase PostHog Mixpanel BigQuery Resend

The check

## A check the agent did not write.

**Skene**/MCP

Agent config

```plaintext
endpoint www.skene.ai/api/mcp auth workspace API key
```

Tools the server answers with 11 tools

**skene_workspace_info** Returns the authenticated workspace and granted scopes for the MCP credential.

**skene_journey_analyse** Starts a Lifecycle rebuild and returns which schema, events, and routes to collect.

**skene_journey_build** Builds and saves the Lifecycle definition from the collected schema, events, and routes.

**skene_get_journey** Returns Lifecycle canvas data with stages, steps, levers, triggers, connectors, and usage overlays.

**skene_view_journey** Opens an interactive Lifecycle map for exploring stages and steps.

**skene_get_tracking_events** Lists tracked events in the same order as the Events page, with status, files, and mapped steps.

**skene_check** Starts an analytics scan and returns the scan steps for the agent to run locally.

**skene_gap** Compares scanned events and providers against the Lifecycle baseline and returns coverage gaps.

**skene_ack** Records whether flagged events are wired, deferred, or rejected, so later scans skip handled gaps.

**skene_analytics_review** Reviews a pull request diff for tracking regressions. It does not post to GitHub.

**skene_feature_check** Checks every active tracking plan for success metric movement, goal status, and Check learning.

- An event the journey plans for that no longer fires

- A database event whose table is not there

- A tracking call for an event nobody planned

- A planned property the call stopped sending

Baseline comparison 4 finding classes

- **`Missing event`**: fails gate

- **`Missing table`**: fails gate

- **`Unplanned tracking call`**: reported

- **`Dropped property`**: reported

An agent checking its own tracking is checking its own work.

The MCP check compares your diff against a baseline the agent never touches: the planned event baseline from your workspace journey artifacts.

## Two paths that can disagree.

The MCP check and the pull request review are separate: one is a deterministic comparison against your journey baseline, the other a model reading the diff against a written policy. They share no code.

- Either can be used alone; neither replaces your test suite

- Both are about tracking specifically, which most CI suites do not check at all

Eleven tools Hosted by Skene

For coding agents: Cursor, Claude Code and any other MCP-capable agent. Add the hosted endpoint to the agent’s config; the check is callable the same turn.

## Put the check in your agent's reach.

[Start free](https://www.skene.ai/signup) [See Skene Cloud](https://www.skene.ai/developers/cloud)

No card needed, minutes to connect.

## Sitemap

- [Markdown sitemap](https://www.skene.ai/sitemap.md): every page on this site, with its markdown counterpart.
- [Index for language models](https://www.skene.ai/llms.txt): the same set as a link-dense index.
- [Full corpus](https://www.skene.ai/llms-full.txt): reference content concatenated as plain text.