Yandex Metrika MCP
MCP server for Yandex.Metrica API providing 15 tools for managing counters, goals, reports, logs, traffic sources, and top pages with OAuth Bearer token authentication.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
theYahia
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
list_countersList all Yandex.Metrica counters available to the authenticated user. Returns counter ID, name, site URL, and status. Supports search filtering.
get_counterGet full details of a single Yandex.Metrica counter by ID, including configuration, code snippet status, and goals count.
create_counterCreate a new Yandex.Metrica counter for a website. Returns the new counter ID and tracking code. You need to install the tracking code on the site afterwards.
update_counterUpdate an existing Yandex.Metrica counter — change its name or site URL.
delete_counterPermanently delete a Yandex.Metrica counter. This action is irreversible — all historical data for this counter will be lost.
list_goalsList all goals configured for a Yandex.Metrica counter. Goals track conversions like page visits, button clicks, or multi-step funnels.
create_goalCreate a new conversion goal for a counter. Supports types: 'url' (page visit), 'number' (page count threshold), 'step' (multi-step funnel), 'action' (JavaScript event).
delete_goalDelete a conversion goal from a counter. Historical goal data in reports is preserved.
export_logsExport raw visit or hit logs via the Logs API. Creates a log request and evaluates feasibility. Use source='visits' for session data, source='hits' for pageview data.
get_reportFlexible Yandex.Metrica reporting endpoint. Query any combination of metrics (ym:s:visits, ym:s:pageviews, ym:s:bounceRate, ym:s:avgVisitDurationSeconds, ym:s:users, ym:s:newUsers, etc.) with dimensions (ym:s:trafficSource, ym:s:searchEngine, ym:s:country, ym:s:browser, ym:s:deviceCategory, ym:s:dat…
get_report_comparisonCompare metrics between two date periods (A vs B). Useful for week-over-week, month-over-month, or campaign before/after analysis.
get_report_drilldownDrill down into report data hierarchically. Start at top level, then pass parent_id to explore sub-dimensions (e.g., country -> city, traffic source -> campaign).
get_traffic_summaryQuick traffic overview for a counter over a date range. Returns visits, pageviews, unique users, bounce rate, and average visit duration in one call.
get_traffic_sourcesTraffic sources breakdown — visits and users by source channel (organic search, direct, social, referral, ad). Quick way to see where traffic comes from.
get_top_pagesTop pages by pageviews for a counter. Returns URL, visits, pageviews, bounce rate, and avg duration for each page. Useful for content performance analysis.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
When Vitest UI server is listening, arbitrary file can be read and executed
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
YANDEX_METRIKA_TOKEN"": "your_token"Tool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
15/15 tools missing one or more hints — list_counters (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_counter (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); create_counter (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +12 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool inputs are validated
Only 0/15 tool handlers declare input schemas (0%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
Only 0/15 tool handlers wrap calls in try/catch (0%)
Wrap each tool handler body in try/catch and return a structured error response.
Tool test coverage
10/15 tools referenced in tests (67%)
Write tests that reference each tool by name so every tool has at least one test.
Production dependencies are patched
0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.12.0 (high), @modelcontextprotocol/sdk@1.12.0 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dev dependencies
1 critical/high in dev-only deps (does not ship to users)
Upgrade dev dependencies when convenient.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/theyahia/yandex-metrika-mcp)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check