Atlas / MCP servers / altrr2 / Yandex Tools

Yandex ToolsBLOCK

mcp/altrr2/yandex-tools
Verdict
BLOCK
Grade
F
Trust score
59 /100
Exposed tools
101 92r · 8w · 1d
Transport
stdio
License
MIT
Stars
65
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

MCP servers for Yandex APIs — search, keyword research, webmaster tools, and web analytics for the Russian market.

English | Русский

English

Packages

Quick Start

Yandex Wordstat v2 (keyword research) — Yandex Cloud Search API; uses the same key as Search:

{
"mcpServers": {
"yandex-wordstat": {
"command": "npx",
"args": ["-y", "yandex-wordstat-mcp"],
"env": {
"YANDEX_SEARCH_API_KEY": "your_api_key",
"YANDEX_FOLDER_ID": "your_folder_id"
}
}
}
}
Prefer a hosted tool? Use the managed endpoint at unoapi.ru/services/wordstat — no Yandex Cloud credentials to manage.

**Yandex Se

Read from source at commit a6ad56709fd2OBSERVED · 2026-10-08
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code
claude mcp add yandex-wordstat-mcp --env YANDEX_CLIENT_SECRET=${YANDEX_CLIENT_SECRET} --env YANDEX_DIRECT_TOKEN=${YANDEX_DIRECT_TOKEN} --env YANDEX_METRIKA_TOKEN=${YANDEX_METRIKA_TOKEN} --env YANDEX_SEARCH_API_KEY=${YANDEX_SEARCH_API_KEY} -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "yandex-wordstat-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "YANDEX_CLIENT_SECRET": "${YANDEX_CLIENT_SECRET}",
        "YANDEX_DIRECT_TOKEN": "${YANDEX_DIRECT_TOKEN}",
        "YANDEX_METRIKA_TOKEN": "${YANDEX_METRIKA_TOKEN}",
        "YANDEX_SEARCH_API_KEY": "${YANDEX_SEARCH_API_KEY}"
      }
    }
  }
}
03

Exposed tools (101)

92 read · 8 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.

ToolRiskDescription
add-keywordswrite
create-adgroupwrite
create-campaignwrite
create-text-adwrite
delete-adgroupdestructive
dynamicsread
get-audience-interestsread
get-balanceread
get-bounce-by-devices-organicread
get-bounce-comparison-search-enginesread
get-bounce-device-search-engineread
get-broken-internal-linksread
get-broken-internal-links-historyread
get-campaignread
get-conversions-by-devicesread
get-conversions-by-landing-pagesread
get-conversions-by-regionsread
get-conversions-by-search-engineread
get-conversions-by-search-phrasesread
get-conversions-device-regionread
get-counterread
get-countersread
get-critical-pagesread
get-demographics-organicread
get-devicesread
get-diagnosticsread
get-entry-exit-pathsread
get-exit-pages-by-devicesread
get-exit-pages-by-sectionread
get-external-linksread
get-external-links-historyread
get-feed-regionsread
get-feed-statusread
get-feedsread
get-geographyread
get-goalsread
get-high-bounce-pages-organicread
get-hostread
get-important-url-historyread
get-important-urlsread
get-indexing-historyread
get-indexing-samplesread
get-insearch-historyread
get-insearch-samplesread
get-new-vs-returning-organicread
get-organic-activity-by-day-of-weekread
get-organic-activity-by-hourread
get-organic-browsersread
get-organic-seasonalityread
get-organic-traffic-dynamicsread
get-page-depth-by-sectionsread
get-popular-pagesread
get-popular-queriesread
get-problematic-osread
get-quality-referral-trafficread
get-query-analyticsread
get-query-historyread
get-recrawl-queueread
get-recrawl-quotaread
get-recrawl-taskread
get-referral-conversionsread
get-referral-donors-behaviorread
get-referral-full-urlsread
get-region-childrenread
get-region-idsread
get-regionsread
get-regions-treeread
get-reportread
get-screen-resolutionsread
get-search-events-historyread
get-search-events-samplesread
get-search-phrasesread
get-single-query-historyread
get-sitemapread
get-sitemapsread
get-social-landing-pagesread
get-social-networks-qualityread
get-social-networks-trafficread
get-sqi-historyread
get-summaryread
get-top-exit-pages-organicread
get-traffic-sourcesread
get-traffic-summaryread
get-userread
get-user-sitemapread
get-user-sitemapsread
get-visit-frequency-organicread
list-adgroupsread
list-adsread
list-campaignsread
list-hostsread
list-keywordsread
manage-adread
manage-campaignread
regionsread
searchread
set-bidswrite
set-negative-keywordswrite
submit-recrawlwrite
top-requestsread
update-campaignwrite
04

Trust audit

BLOCKgrade F · trust 59/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeFAIL
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfaceWARN
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (1 observation(s))
Network
declared (5 observation(s))
Shell
declared (3 observation(s))
Dependencies
not all pinned
Secrets in source
none-found

Findings (13)

HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
packages/yandex-direct-mcp/src/auth.mjs:10
exec(`${start} "${url}"`);
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
packages/yandex-metrika-mcp/src/auth.mjs:10
exec(`${start} "${url}"`);
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
packages/yandex-webmaster-mcp/src/auth.mjs:10
exec(`${start} "${url}"`);
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
MEDIUMInformation disclosure · disclose.log_secret · CWE-209, CWE-532
packages/yandex-direct-mcp/src/auth.mjs:98
console.log(token);
MEDIUMInformation disclosure · disclose.log_secret · CWE-209, CWE-532
packages/yandex-metrika-mcp/src/auth.mjs:93
console.log(token);
MEDIUMInformation disclosure · disclose.log_secret · CWE-209, CWE-532
packages/yandex-webmaster-mcp/src/auth.mjs:92
console.log(token);
MEDIUMFilesystem / path · mcp.destructive_tools · CWE-22, CWE-59
delete-adgroup
Why it matters. 1 tool(s) can delete or overwrite
Fix. prefer a read-only mode or scoped tokens; the page states the blast radius
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
packages/yandex-webmaster-mcp/test/endpoints.test.mjs:21
const baseUrl = `http://127.0.0.1:${httpServer.address().port}/v4`;
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@biomejs/biome
Why it matters. 1 dependency range(s) float
Fix. pin exact versions or ship a lockfile
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
packages/yandex-direct-mcp/package.json
@modelcontextprotocol/sdk, zod
Why it matters. 2 dependency range(s) float
Fix. pin exact versions or ship a lockfile
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
packages/yandex-metrika-mcp/package.json
@modelcontextprotocol/sdk, zod
Why it matters. 2 dependency range(s) float
Fix. pin exact versions or ship a lockfile
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
packages/yandex-search-mcp/package.json
@modelcontextprotocol/sdk, zod
Why it matters. 2 dependency range(s) float
Fix. pin exact versions or ship a lockfile
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
packages/yandex-webmaster-mcp/package.json
@modelcontextprotocol/sdk, zod
Why it matters. 2 dependency range(s) float
Fix. pin exact versions or ship a lockfile

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha a6ad56709fd2full audit observations/trust-audit/mcp-server/altrr2__yandex-tools.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-08a6ad56709fd2BLOCKF59first audit
06

Questions

What tools does Yandex Tools expose?

101 in total: 92 read-only, 8 that write, and 1 that can delete or overwrite (delete-adgroup). Every one is listed on this page with its risk.

Is Yandex Tools safe to connect to an agent?

No — not without reading the findings first. The audit graded it F (59/100) and found 3 critical or high issues in the source. Each one is listed on this page with the file and line it is on. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.

What credentials does Yandex Tools need?

It reads YANDEX_CLIENT_SECRET, YANDEX_DIRECT_TOKEN, YANDEX_METRIKA_TOKEN, YANDEX_SEARCH_API_KEY, YANDEX_WEBMASTER_TOKEN and YANDEX_WORDSTAT_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does Yandex Tools run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as yandex-wordstat-mcp at 2.0.1.

How current is this page?

The grade is for one exact copy of the source (a6ad56709fd2), read on 2026-10-08. The repository is watched and re-audited when it changes.

Advertisement