Yandex Direct MCP

Get statistics

get_statistics

Read-only

Retrieve performance reports from Yandex Direct campaigns, including aggregated statistics, day-by-day trends, and detailed search query summaries with sorting and filtering options.

Instructions

Requests a performance report via the Yandex Direct Reports service. By default the report is AGGREGATED over the whole period (one row per object) — add "Date" to fieldNames only for day-by-day dynamics or trend questions. ALL_TIME without a campaign filter is rejected for SEARCH_QUERY/CRITERIA reports; pass campaignIds or a bounded date range. SEARCH_QUERY_PERFORMANCE_REPORT returns a COMPUTED SUMMARY (totals over ALL rows + top-N detail + tail rollup + zero-click/zero-conversion counts), not raw rows — shape it with sortBy/topN/minCost/queryContains/zeroClicksOnly/zeroConversionsOnly, and add Conversions to fieldNames for conversion-based counts. Other report types return tab-separated rows (no header).

Input Schema

TableJSON Schema

Name	Required	Description
`topN`	No	Max detail rows in the summary (server-capped at 100). Default 50.
`order`	No	Sort order for detail rows. Default desc.
`dateTo`	No	End date YYYY-MM-DD (required for CUSTOM_DATE).
`sortBy`	No	Metric to rank the detail rows by. Default Cost.
`minCost`	No	Only include rows with Cost >= this in the detail list.
`dateFrom`	No	Start date YYYY-MM-DD (required for CUSTOM_DATE).
`fieldNames`	No	Report columns (must be valid for the report type).
`includeVat`	No	Whether costs include VAT. Default true.
`reportType`	No	Report type. Default CAMPAIGN_PERFORMANCE_REPORT.
`campaignIds`	No	Limit the report to these campaign ids.
`dateRangeType`	No	Predefined date range. Inferred as CUSTOM_DATE when dateFrom/dateTo are given.
`queryContains`	No	Only include rows whose query/criterion contains this substring (case-insensitive).
`zeroClicksOnly`	No	Only include rows with 0 clicks in the detail list.
`zeroConversionsOnly`	No	Only rows with clicks>0 and 0 conversions (needs Conversions in fieldNames).

Tool Definition Quality

A5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark it as readOnly, but the description adds crucial behavioral details: default aggregation, special handling of SEARCH_QUERY reports (computed summary vs raw rows), and conditions for rejection. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Despite packing extensive detail, the description remains concise and well-organized. It front-loads the core purpose, then uses a structured breakdown of special cases and specific report types. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 14 parameters with full schema coverage and no output schema, the description adequately explains return formats (tab-separated rows or computed summary) and key behavioral constraints like ALL_TIME rejection. No gaps for typical use cases.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema description coverage, baseline is 3, but the description adds significant value by explaining how parameters like 'Date', 'ALL_TIME', 'campaignIds', 'sortBy', 'topN', etc. interact in practice. This contextualizes the schema definitions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool requests a performance report via Yandex Direct, with specific verb and resource. It distinguishes itself from sibling tools which are primarily CRUD operations on entities like campaigns, ads, and keywords.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly guides when to add 'Date' to fieldNames, warns about ALL_TIME rejection for certain reports without campaign filter, and describes how to shape the special SEARCH_QUERY performance report. Provides clear context for different parameter combinations.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Latest Blog Posts

Lightport: Open-Sourcing Glama's AI Gateway
By punkpeye on April 27, 2026.
open source
OpenAI
Tool Definition Quality Score (TDQS)
By punkpeye on April 3, 2026.
mcp
The Hackers Who Tracked My Sleep Cycle
By punkpeye on March 26, 2026.
security

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/askads/mcp-yandex-direct'

If you have feedback or need assistance with the MCP directory API, please join our Discord server