Maintainer of this skill?
by DevCrabs-Inc
Read-only MCP server for Yandex Metrika (Яндекс Метрика): verifiable reports, period comparisons, time series and exports for Claude, Cursor, VS Code and Codex.
# Add to your Claude Code skills
git clone https://github.com/DevCrabs-Inc/yandex-metrika-mcpGuides for using ai agents skills like yandex-metrika-mcp.
See how yandex-metrika-mcp compares with popular alternatives.
yandex-metrika-mcp is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by DevCrabs-Inc. Read-only MCP server for Yandex Metrika (Яндекс Метрика): verifiable reports, period comparisons, time series and exports for Claude, Cursor, VS Code and Codex. It has 126 GitHub stars.
yandex-metrika-mcp's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/DevCrabs-Inc/yandex-metrika-mcp" and add it to your Claude Code skills directory (see the Installation section above).
yandex-metrika-mcp is primarily written in TypeScript. It is open-source under DevCrabs-Inc on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh yandex-metrika-mcp against similar tools.
No comments yet. Be the first to share your thoughts!
Available after the catalog security scan passes.
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
Read-only MCP server for Yandex Metrika (Yandex Metrica, Яндекс Метрика). Connect it to Claude, Cursor, VS Code, Codex or any MCP client and ask about traffic, sources, landing pages and goals. Every answer comes with exact dates, the counter time zone, sampling status, filters and provenance, so the numbers can be checked.
Документация на русском: README.ru.md и docs/ru.
Status: 1.0.0, the first stable release; tool names, arguments and outputs follow semantic versioning. Covered by tests against synthetic data and a simulated API, and checked with a live Yandex sign-in and reports on macOS. Other clients and platforms are tracked in docs/release-checklist.md.
Requires Node.js 22.13 or later. No API key and no OAuth app of your own: after installing, ask the assistant to connect Yandex Metrika and sign in through the browser.
One command (writes the client config and keeps a backup):
npx -y @dev-crabs/yandex-metrika-mcp setup --client claude-desktop # or claude-code, cursor, vscode, windsurf, codex
One click:
Claude Code:
claude mcp add --scope user yandex-metrika -- npx -y @dev-crabs/yandex-metrika-mcp
Any MCP client (mcpServers format; VS Code uses servers with "type": "stdio"):
{
"mcpServers": {
"yandex-metrika": { "command": "npx", "args": ["-y", "@dev-crabs/yandex-metrika-mcp"] }
}
}
On Windows some clients cannot start npx directly; use "command": "cmd", "args": ["/c", "npx", "-y", "@dev-crabs/yandex-metrika-mcp"], which is what setup writes there. Claude Desktop users can also install the .mcpb bundle from the GitHub release. AI agents installing the server should follow llms-install.md.
Restart the client and ask: "Connect Yandex Metrika and compare the last two weeks by traffic source." The assistant calls metrika_connect and gives you a local sign-in link. Try it without an account: the synthetic conn_demo connection is always available.
| Tool | Purpose |
|---|---|
metrika_status |
Connections, exports and the next step. Works before sign-in. |
metrika_connect / metrika_disconnect |
Browser sign-in; local removal of a connection and its token. |
metrika_list_counters / metrika_describe_counter |
Sites, time zones and goals with IDs. |
metrika_catalog |
Presets, metrics (with aggregation rules), dimensions, period presets. |
metrika_run_report |
One period: presets or explicit fields, filters, sorting, paging. |
metrika_compare_periods |
Two periods under identical conditions: absolute, % and p.p. changes. |
metrika_run_timeseries |
Day, week or month buckets with exact calendar boundaries. |
metrika_export_report / metrika_get_job / metrika_cancel_job / metrika_read_artifact |
Full CSV/JSON exports as resumable background jobs. |
Prompts: weekly_review, traffic_drop, landing_conversion.
Report data you request is sent to your AI client and its model provider; tokens never are. Tokens live in the OS credential store (macOS Keychain, Windows Credential Manager, Linux Secret Service). Without one, the server refuses to store tokens unless you explicitly choose an unencrypted user-only file. URL query strings are removed from labels by default. No telemetry. Details: docs/ru/privacy-security.md.
pnpm install
pnpm check # Biome, tsc, vitest
pnpm build # dist/cli.js
pnpm mcpb # build/yandex-metrika-mcp-<version>.mcpb
See CONTRIBUTING.md and AGENTS.md. Security reports: SECURITY.md.
MIT © DevCrabs