Yandex Wordstat MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| YANDEX_WORDSTAT_API_KEY | No | API key with the yc.search-api.execute scope. Set exactly one of YANDEX_WORDSTAT_API_KEY or YANDEX_WORDSTAT_IAM_TOKEN. | |
| YANDEX_WORDSTAT_MAX_RPH | No | Maximum requests per hour. Allowed range: 0–1000000; 0 disables the limit. | 100 |
| YANDEX_WORDSTAT_MAX_RPS | No | Maximum requests per second. Allowed range: 1–10000. | 8 |
| YANDEX_WORDSTAT_FOLDER_ID | No | Yandex Cloud folder ID on which the search-api.webSearch.user role is granted. Required with a Yandex-account or federated-account IAM token; can normally be omitted for an API key or a service-account IAM token. Up to 50 characters. | |
| YANDEX_WORDSTAT_IAM_TOKEN | No | IAM token. Set exactly one of YANDEX_WORDSTAT_API_KEY or YANDEX_WORDSTAT_IAM_TOKEN. | |
| YANDEX_WORDSTAT_LOG_LEVEL | No | Log level. Allowed values: silent, error, warn, info, debug. | error |
| YANDEX_WORDSTAT_TIMEOUT_MS | No | Request timeout in milliseconds. Allowed range: 1–300000. | 30000 |
| YANDEX_WORDSTAT_MAX_RETRIES | No | Maximum number of retries. Allowed range: 0–10. | 2 |
| YANDEX_WORDSTAT_MAX_CONCURRENCY | No | Maximum concurrency. Allowed range: 1–100. | 4 |
| YANDEX_WORDSTAT_REGIONS_CACHE_TTL_MS | No | Regions cache TTL in milliseconds. Allowed range: 0–2592000000. | 86400000 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| wordstat_top_requestsC | Popular and associated Wordstat queries for the last 30 days. |
| wordstat_dynamicsC | Daily, weekly or monthly Wordstat demand dynamics. |
| wordstat_regionsC | Wordstat demand distribution by region for the last 30 days. |
| wordstat_regions_treeC | The hierarchy of regions supported by Wordstat. |
| wordstat_find_regionsB | Find Wordstat region IDs locally by exact or substring name match. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
The three data tools (top_requests, dynamics, regions) target clearly distinct dimensions of keyword research. The only mild overlap is between wordstat_regions_tree (static hierarchy) and wordstat_find_regions (name-based ID lookup), but the descriptions make the difference clear enough for an agent to pick correctly.
Every tool follows the same wordstat_<noun_phrase> convention with snake_case throughout. The verbs are implicit (all are retrieval-style), which is perfectly uniform for a read-only analysis server.
Five tools is a tight, well-scoped surface for a keyword-research service. Each tool earns its place: three analysis outputs plus two region-support tools needed to use the region-based analysis.
The surface covers the core Wordstat workflow: popular queries, demand dynamics, regional breakdown, plus region ID discovery and hierarchy browsing. Minor gaps exist around multi-query comparison or device/market segmentation, but nothing that would block typical agent workflows.