Connects AI clients to Yandex AppMetrica for reports, funnels, segments, dashboards, event audits, and log exports.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.
We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag — we're steadily working through the catalog.
~/Library/Application Support/Claude/claude_desktop_config.json💡 Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.
Inspect callable tools, capabilities, and parameters exposed to AI agents by Appmetrica MCP.
list_applicationsList all AppMetrica applications in your account
get_applicationGet details for a specific application by ID
list_eventsList client event names of an application (use them as funnel steps)
list_conversionsList configured conversions (attributed events)
get_logs_api_statusCheck whether the Logs API is enabled for the account
get_reportAggregated metrics for a date range, with `filters`, `sort`, `segment_id`, `currency`, `accuracy`, `include_undefined`, `lang`, `offset
The appmetrica-mcp MCP server exposes Yandex AppMetrica data and selected management operations as MCP tools. It can enumerate applications, retrieve application details, inspect client event names and configured conversions, and check whether the Logs API is available for the account.
Reporting tools cover aggregated metrics over a date range, time-series grouping by hour, day, week, or month, and dimension drilldowns. Reports accept options such as filters, sorting, segments, currency, accuracy, undefined-value handling, language, and pagination. A metric and dimension catalogue supports compact listing and filtered searches across the available definitions.
The server also includes tools for saved segments and funnels, ad-hoc funnel steps, funnel conversion results, dashboard presets, locally stored workspaces, and event instrumentation audits. The audit compares registered events with observed activity and can identify zero-volume or missing events for a selected period.
An MCP client starts the server, which calls AppMetrica APIs using a Yandex OAuth token. Read operations are available for account and application analytics. Write actions are protected by a setting that must be enabled explicitly; the README identifies push campaign creation and funnel or segment changes as write operations.
Local workspaces are represented as JSON data on the server’s filesystem. These differ from AppMetrica’s web workspaces. The web_* tools use an experimental logged-in Chrome session to inspect or modify AppMetrica workspaces, including their groups, headers, and widgets. This browser path is separate from the API-based reporting and management functions.
The appmetrica-mcp MCP server requires Node.js 22 or newer, an AppMetrica account with at least one application, and Yandex authorization. The recommended authentication command is npx appmetrica-mcp auth; it stores credentials locally for later server runs. An OAuth token can instead be supplied directly with APPMETRICA_OAUTH_TOKEN.
The standard installation pattern runs the package with npx -y appmetrica-mcp, including from Claude Code or Claude Desktop. APPMETRICA_ALLOW_WRITE=true enables supported write tools; its default is false. APPMETRICA_WORKSPACES_FILE changes the location of locally saved workspaces.
The experimental web tools additionally need Google Chrome or another configured Chromium-compatible browser and a one-time npx appmetrica-mcp login. Browser profile and executable settings can be controlled with APPMETRICA_BROWSER_PROFILE, APPMETRICA_BROWSER_PATH, and APPMETRICA_BROWSER_CHANNEL.
Available capabilities include:
The server depends on AppMetrica account access and a valid Yandex OAuth authorization. Logs-related operations require the account’s Logs API availability. Browser workspace features are experimental and require a separate logged-in browser session. Write operations remain disabled unless explicitly enabled, so read-only behavior is the default.
Factual signals from GitHub, npm, and our automated checks — not a rating.
No reviews yet — be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/appmetrica-mcp)<a href="https://allmcps.com/mcp/appmetrica-mcp"><img src="https://allmcps.com/api/badge/appmetrica-mcp?style=directory" alt="Appmetrica MCP on AllMCPs" /></a>