yandex-metrica-mcp
Yandex Metrica MCP server for interactive sign-in, data discovery, read-only reporting, and raw log export.
Sign in to Yandex interactively with
login, or finish a copy-paste flow withsubmit_code.Discover available counters and valid Metrica dimensions, metrics, attribution options, and Logs API fields with
get_metadata.Read a counter’s configuration: settings, goals, segments, filters, operations, access grants, and chart annotations via
describe_counter.Run flexible table reports (
run_report), A/B period/segment comparisons (run_comparison), hierarchical drilldowns (run_drilldown), and time-series/trend reports (run_timeseries).Request, poll, download, and clean raw Logs API exports for visits or hits, returning bounded samples or streaming full exports to files.
The provided schema does not expose the opt-in write tools; these tools are read-only except that log request/clean operations consume or free quota.
yandex-metrica-mcp
Ask your Yandex Metrica analytics in plain language — from Claude, Cursor, or any MCP client.
A Model Context Protocol (MCP) server for Yandex Metrica. It lets an AI agent query your web-analytics data — traffic, sources, landing pages, conversions, geography, devices and trends — through a small set of flexible, read-only tools — plus opt-in write tools that you confirm one change at a time.
Read-only by default, no secrets stored in the package: interactive login uses a built-in public OAuth client with PKCE, and the server talks only to Yandex.
General-purpose: marketing, product analytics, e-commerce and SEO are all fair game — the server is not tied to any one use case.
Demo
Point an AI agent at your counter and ask about your traffic — the server queries
Yandex Metrica and hands back real, read-only data, no dashboards. Here the
run_report tool answers a “traffic sources, last 7 days” question against a live
counter:

Related MCP server: metabase-mcp
Quickstart
1. Add the server to your MCP client (e.g. Claude Desktop) — no token required up front; you log in interactively in step 2:
{
"mcpServers": {
"yandex-metrica": {
"command": "npx",
"args": ["-y", "yandex-metrica-mcp"],
"env": { "YANDEX_METRIKA_COUNTER_ID": "12345678" }
}
}
}2. Log in once — one command, no app registration, no secret stored:
npx yandex-metrica-mcp authApprove access in the browser and you're done — the code is handed back automatically over a local redirect, no copy-paste. The login uses authorization-code + PKCE, so no client secret ever touches your machine; the token is cached (mode 0600) and valid for ~1 year.
3. Ask your agent about traffic, sources, conversions, geography, devices, or trends — see Examples for prompts.
Prefer a static token (CI / non-interactive) or your own OAuth app? See Authentication.
Or install as a Claude Code plugin
The repo doubles as the plugin marketplace for BoxLab's Yandex MCP family, so you can install the server through Claude Code's plugin system instead of the config above:
/plugin marketplace add BoxLab-Ltd/yandex-metrica-mcp
/plugin install yandex-metrica-mcp@boxlabThen sign in from the chat with the login tool (or run
npx yandex-metrica-mcp auth). The same marketplace also carries
yandex-webmaster-mcp.
To turn on the write tools in the plugin, start Claude Code with
YANDEX_METRIKA_ENABLE_WRITE=1 in the environment.
Or install as a Claude Desktop extension (.mcpb)
For a one-click install with no JSON, download the .mcpb from the
latest release
and open it with Claude Desktop (or drag it into Settings → Extensions). It asks
for an optional default counter id; then sign in from the chat with the login
tool (or run npx yandex-metrica-mcp auth).
Why
There is no official Yandex Metrica MCP server, and existing community ones are mostly thin, unmaintained, or dump raw data straight into the model's context. This server aims to be the well-engineered, well-maintained, open option: flexible report tools, strict token/context discipline, read-only by default.
Features
run_report— flexible wrapper over the Reporting API (/stat/v1/data).run_comparison— compare two periods with absolute and percentage deltas.run_drilldown— drill down through a dimension tree.run_timeseries— metrics split into a time series (/bytime) for trends.get_metadata— discover the counters on your account and a catalog of common dimensions/metrics (and Logs API fields) so the model queries with real names.describe_counter— read one counter's configuration (goals, segments, filters, operations, access grants, chart annotations) via anincludeselector. The goals section gives the goal ids needed for conversion metrics inrun_report.logs_request/logs_status/logs_download/logs_clean— Logs API: export raw, un-sampled session (visits) or hit (hits) rows. Async lifecycle (request → poll → download → clean);logs_downloadreturns a bounded sample inline by default, or streams the full export to a file — never dumping raw rows into the model's context.login/submit_code— sign in to Yandex Metrica from your MCP client, no terminal needed:loginopens the browser and captures the code over a local redirect, or hands back a URL and takes the pasted code viasubmit_code.Built-in context control: field selection on by default, low default row limits, and sampling/quota surfaced back to the model.
Analysis hygiene: the server hands every client a short set of rules (exclude robots, compare complete periods, never sum users, use explicit goals, …). The Claude Code plugin adds the fuller
metrica-hygieneskill.
Write tools (opt-in)
Off unless you set YANDEX_METRIKA_ENABLE_WRITE=1. Then the server adds:
manage_annotation— create, update or delete a note pinned to a chart date (a release, a campaign start, an outage).upload_expenses— import ad costs from a non-Yandex source as CSV, so Metrica reports cost and ROI.dryRun: truevalidates the file and shows the rows, dates and totals without sending anything.
With the flag on, sign-in also asks for the metrika:write scope — run auth
(or the login tool) once more after turning it on. Without the flag the
sign-in asks for read access only, and tokens issued earlier keep working.
Every change is confirmed by you before it is sent: your client shows a
confirmation prompt if it supports MCP elicitation, otherwise the tool returns
a summary and a one-time token that the agent can use only after you agree.
The server also checks that your account has edit access to the counter.
Local HTTP mode
By default the server talks stdio, started by your MCP client. For clients that connect by URL, or to share one running server between several clients, start it over Streamable HTTP:
npx yandex-metrica-mcp --http # http://127.0.0.1:7801/mcp
npx yandex-metrica-mcp --http --port 9000Or set MCP_TRANSPORT=http (and MCP_HTTP_PORT). Every client gets its own
session; they share one sign-in and one request budget. The server listens on
127.0.0.1 only and rejects requests whose Host or Origin is not local,
so a web page cannot reach it. To listen on another interface
(--host 0.0.0.0, e.g. in Docker) you must set MCP_HTTP_TOKEN; clients then
send Authorization: Bearer <token>. This is a local mode, not hosting: one
user, one Yandex account.
Requirements
Node.js >= 18
Yandex Metrica credentials with the
metrika:readscope (see Authentication), plusmetrika:writefor the opt-in write tools. Whoever the credentials belong to must have access to the counters you query.
Authentication
Recommended: interactive login. No app registration needed — the server ships a built-in public OAuth client. Run once:
yandex-metrica-mcp auth # or, in dev: bun run authIt opens the Yandex consent page in your browser; after you approve, the code is
returned automatically over a loopback redirect (http://127.0.0.1:53682) — no
copy-paste. If that port is taken, it falls back to showing a code you paste in
(force that flow with auth --oob, or change the port with
YANDEX_OAUTH_LOOPBACK_PORT). The token is cached at
~/.config/yandex-metrica-mcp/token.json (mode 0600) and is valid for ~1 year;
re-run auth when it expires. The login uses authorization-code + PKCE, so no
client secret is stored anywhere. A cached login takes precedence over
YANDEX_METRIKA_TOKEN.
From your MCP client (no terminal). Not signed in yet? The server still
starts — ask your agent to run the login tool and it does the same browser
flow in-process (or returns a URL and takes the code via submit_code). Handy
for GUI clients like Claude Desktop, where there is no terminal to run auth.
Static token. Get a token for an app with the metrika:read scope at
https://oauth.yandex.ru and pass it as YANDEX_METRIKA_TOKEN — handy for CI
or non-interactive use.
Own OAuth app (optional). To use your own app instead of the built-in one,
set YANDEX_OAUTH_CLIENT_ID; add YANDEX_OAUTH_CLIENT_SECRET to also enable
automatic token refresh.
Configuration
The Quickstart covers the happy path. For all options — static
token, your own OAuth app, default counter, request tuning, language — see
.env.example. The published package runs on Node (so
npx/MCP clients work out of the box); local development uses
Bun.
Examples
Once connected, an agent can answer questions like:
“How many visits and users did counter 12345678 get last week, split by traffic source?” →
run_reportwithmetrics: ["ym:s:visits","ym:s:users"],dimensions: ["ym:s:lastsignTrafficSource"].“Compare this week's organic conversions to last week's.” →
run_comparison(server returns A, B, and the deltas).“Which operating systems do my visitors use? Let me drill into Windows versions.” →
run_drilldown, then again withparentId.“What counters do I have?” →
get_metadata.“List this counter's goals, then show how the ‘Purchase’ goal converted last week.” →
describe_counter(include: ["goals"]) for the goal id, thenrun_reportwithym:s:goal<id>conversionRate.“Export last month's raw sessions with landing pages and referrers for offline analysis.” →
logs_request(source: "visits"), polllogs_status, thenlogs_download(mode: "file"), thenlogs_cleanto free the quota.
Development
This project is Bun-first:
bun install
bun run dev # run from source with hot reload
bun run typecheck # tsc --noEmit
bun run lint # eslint
bun test # bun's test runner
bun run build # emit dist/ with tsc (Node-compatible)The skill has an eval suite in evals/ that runs against mocked
Metrica tools, so it never touches the real API:
claude plugin eval . --ablation noneLicense
MIT © boxlab
Available Tools
12 toolsdescribe_counterDescribe Metrica counterARead-only
Read a single counter's configuration — settings, goals, segments, filters, operations and access grants and chart annotations — choosing sections with include. The goals section returns the goal ids needed to build conversion metrics (ym:s:goalreaches / conversionRate) in run_report, so call this with include=["goals"] before any conversion question. To list the account's counters, use get_metadata. Read-only.
Inputs: include, counterId, fullResponse.
get_metadataGet Metrica metadataARead-only
Discovery tool. Lists the counters available to your token plus a curated catalog of common dimensions and metrics (Metrica has no enumeration API), attribution options and Logs API fields. Call this before run_report or logs_request to use real field names and to find a counterId. For a counter's own goals, segments, filters or grants, use describe_counter. Read-only.
Inputs: no named parameters.
loginSign in to YandexA
Sign in to Yandex from here. Opens your browser to approve access; the code returns automatically over a local redirect, so this usually finishes in one call. If the local port is unavailable it returns a URL to approve and you then call submit_code with the code Yandex shows. Run this once (the token lasts ~1 year); needed before the data tools if you are not signed in yet.
Inputs: oob.
logs_cleanClean or cancel a Metrica log requestADestructive
Free the counter storage quota by cleaning a finished (processed) log request, or cancel one still being prepared. Dispatches by current status. Destructive: cleaned data must be requested again to download later.
Inputs: requestId (required), counterId.
logs_downloadDownload Metrica raw logsARead-only
Download prepared log data for a request_id (must be status="processed"; check logs_status). Default mode "sample" returns up to maxRows parsed rows inline — cheap and bounded. Mode "file" streams the FULL export to a file and returns its path plus a small preview; the raw content (potentially millions of rows) is never loaded into context. Read-only.
Inputs: requestId (required), mode, maxRows, counterId, +1 more.
logs_requestRequest Metrica raw logsA
Create a Yandex Metrica Logs API request for RAW, un-sampled rows (source="visits" sessions or "hits" events) over a date range. Checks feasibility, then queues preparation (takes minutes). Returns a request_id to poll with logs_status; then logs_download, then logs_clean. Discover field ids with get_metadata. Not read-only: preparing data consumes the counter storage quota.
Inputs: date1 (required), date2 (required), fields (required), source (required), +3 more.
logs_statusCheck Metrica log requestsARead-only
Inspect a Logs API request by request_id (status, parts, size, next step), or omit request_id to list all of the counter's log requests and current storage-quota usage. Poll this after logs_request until status="processed". Read-only.
Inputs: counterId, requestId.
run_comparisonCompare Metrica segmentsARead-only
Compare two segments/periods (A vs B) for the same metrics and dimensions (/stat/v1/data/comparison). Returns per-metric values for A and B plus the absolute and percentage delta, computed server-side: delta = B − A (segment A is the baseline), delta_pct = (B − A) / A × 100. Defaults to last 7 days (B) vs the prior 7 days (A), so a positive delta means growth. Read-only.
Inputs: metrics (required), sort, limit, date1A, +13 more.
run_drilldownDrill down a Metrica reportARead-only
Return one level of a hierarchical (tree) report (/stat/v1/data/drilldown). Each row has an "expandable" flag; pass parentId with the path of dimension keys to expand deeper. Requires dimensions. Read-only.
Inputs: metrics (required), sort, date1, date2, +11 more.
run_reportRun Metrica reportARead-only
Query a Yandex Metrica table report (/stat/v1/data): one or more metrics grouped by dimensions over a date range, with optional filter and sort. Read-only. Use get_metadata first to discover valid metric/dimension ids and the account counters.
Inputs: metrics (required), sort, date1, date2, +10 more.
run_timeseriesMetrica metrics over timeARead-only
Return metrics split into a time series (/stat/v1/data/bytime): each metric comes back as an array of values, one per interval (day/week/month/…) over the date range. Use for trends and charts. Optionally group by dimensions (topKeys rows). Read-only.
Inputs: metrics (required), date1, date2, group, +8 more.
submit_codeSubmit the Yandex sign-in codeA
Complete a copy-paste sign-in started by login: pass the code Yandex showed you after you approved access.
Inputs: code (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 12 tools
Each tool has a distinct role: authentication, counter discovery/config, four reporting shapes, and the Logs API lifecycle. The reporting tools are clearly differentiated by output shape (flat rows, A/B comparison, tree drilldown, time series), and the metadata/counter-config split is explicitly cross-referenced.
Most names follow predictable patterns within workflow groups: run_* for reports, logs_* for log-request lifecycle, and verb_noun for get_metadata, describe_counter, and submit_code. The lone outliers are login and the noun-prefixed logs_* group, but they remain readable and conventional.
Twelve tools is well scoped for auth, discovery, reporting, and Logs API workflows. Each tool earns its place, with no obvious redundant variants or thin single-purpose surface.
The set covers the full practical lifecycle: sign-in with fallback, counter discovery and configuration, multiple report modalities, and log request/status/download/clean operations. No obvious dead ends are visible for the stated Yandex Metrica analytics purpose.
Maintenance
Related MCP Connectors
Read-only Yandex Metrika MCP. Query visits, sources, geo, devices and more in plain language.
Hosted MCP server for marketing agencies: connect Google Ads, GA4, Search Console, Meta, LinkedIn and more to Claude or ChatGPT. Pull reports and make changes via OAuth login, no setup.
MCP servers for Yandex APIs: Wordstat, Search, Webmaster, Metrika, Direct. Open source, by Seyka AI.
MCP for Yandex Direct: manage ad campaigns & analytics from Claude or ChatGPT
Related MCP Servers
- AlicenseCqualityDmaintenanceMCP server for Yandex Metrika analytics, enabling AI assistants to access traffic, content, demographics, conversion, e-commerce, and drill-down reports.312MIT
- AlicenseNot gradedqualityCmaintenanceA TypeScript/Node.js MCP server that wraps the Metabase REST API, enabling AI agents to execute queries, explore schemas, and build dashboards through structured tool calls.167 npmMIT
- AlicenseAqualityBmaintenanceMCP server for Yandex Metrica analytics: query web analytics metrics, goals, conversions, and raw API data using natural language from AI clients like Claude and Cursor.8708 npm5MIT
- AlicenseNot gradedqualityDmaintenanceRead-only MCP server for Yandex Metrika analytics, enabling report retrieval via MCP clients like Claude Code or Cursor without modifying any data.150 npmMIT