Google Search Console integration for Model Context Protocol (MCP)
Nothing to run from here
Yandex Direct is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
97/100
trust score
43
tools declared
local
runs on your machine
—
downloads a day
What it does
MCP server for Yandex Direct API v5 — campaigns, ads, keywords, reports
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'YANDEX_DIRECT_TOKEN=${YANDEX_DIRECT_TOKEN}' --transport stdio stufently-yandex-direct-mcp '--' npx -y @stufently/yandex-direct-mcp
# 2 — ask your agent for something these tools do
# set_keyword_bids, set_auto_keyword_bids, set_bid_modifiers and 40 more
It needs YANDEX_DIRECT_TOKEN: this reads it from your environment, so export it first.
Yandex Direct costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
STAll 19 servers
stufently19 servers
6 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Yandex Direct as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads YANDEX_DIRECT_TOKEN (OAuth token for Yandex Direct API v5) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx YANDEX_DIRECT_TOKEN … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'YANDEX_DIRECT_TOKEN=${YANDEX_DIRECT_TOKEN}' --transport stdio stufently-yandex-direct-mcp '--' npx -y @stufently/yandex-direct-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: YANDEX_DIRECT_TOKEN — OAuth token for Yandex Direct API v5. You set it in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
43 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Set keyword bids. Pass a JSON array of bid objects with KeywordId, SearchBid (in micros), and/or NetworkBid (in micros).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| bids_json | string | yes | JSON array of bid objects, e.g. [{"KeywordId":12345,"SearchBid":30000000,"NetworkBid":10000000}] |
| confirm | boolean | no | — |
Set automatic keyword bids (strategy-level). Pass a JSON array of auto-bid objects. Common fields: CampaignId, AdGroupId, KeywordId, Bid, ContextBid, and strategy parameters.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| bids_json | string | yes | — |
| confirm | boolean | no | — |
Update bid modifier values. Pass a JSON array of objects with Id and the new adjustment value.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| modifiers_json | string | yes | JSON array of bid modifier update objects, e.g. [{"Id":11111,"BidModifier":120}] |
| confirm | boolean | no | — |
Create a Yandex Direct report. Supported ReportType: ACCOUNT_PERFORMANCE_REPORT, AD_PERFORMANCE_REPORT, ADGROUP_PERFORMANCE_REPORT, CAMPAIGN_PERFORMANCE_REPORT, CRITERIA_PERFORMANCE_REPORT, CUSTOM_REPORT, REACH_AND_FREQUENCY_PERFORMANCE_REPORT, SEARCH_QUERY_PERFORMANCE_REPORT. DateRangeType:…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| report_type | string | yes | Report type |
| field_names | array | yes | — |
| date_range_type | string | yes | Date range type. Use CUSTOM_DATE with date_from/date_to. |
| date_from | string | no | Start date YYYY-MM-DD (required when date_range_type=CUSTOM_DATE) |
| date_to | string | no | End date YYYY-MM-DD (required when date_range_type=CUSTOM_DATE) |
| filter_json | string | no | — |
| include_vat | boolean | no | Include VAT in money values (default: true) |
Get Yandex Direct dictionaries (reference data). Available dictionaries: Currencies, MetroStations, GeoRegions, TimeZones, Constants, Categories, OperationSystemVersions, InterestCategories, Interests, AudienceInterests.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dictionary_names | array | yes | Array of dictionary names to retrieve |
Get client info (for agency accounts). Common FieldNames: Login, ClientId, ClientInfo, AccountQuality, Archived, CountryId, CreatedAt, Currency, Grants, Notification, OverdraftSumAvailable, Phone, Representatives, Restrictions, Settings, Type.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| field_names | array | yes | Fields to return, e.g. ["Login","ClientId","ClientInfo","Currency"] |
Get campaigns. Common FieldNames: Id, Name, Status, State, Type, StartDate, EndDate, DailyBudget, Statistics, ClientInfo, TimeTargeting, NegativeKeywords, BlockedIps, StatusPayment, StatusClarification, SourceId, Currency, Funds, RepresentedBy.
No parameter schema on file.
Get ad groups. Common FieldNames: Id, Name, CampaignId, Status, Type, RegionIds, NegativeKeywords, TrackingParams, ServingStatuses, Subtype.
No parameter schema on file.
Get ads. Common FieldNames: Id, AdGroupId, CampaignId, Status, State, Type, StatusClarification, TextAd, DynamicTextAd, MobileAppAd, CpmBannerAdBuilderAd, SmartAdBuilderAd. Use TextAd field to get ad texts.
No parameter schema on file.
Get keywords. Common FieldNames: Id, Keyword, AdGroupId, CampaignId, Status, State, Bid, ContextBid, StrategyPriority, UserParam1, UserParam2, Productivity, StatisticsSearch, StatisticsNetwork.
No parameter schema on file.
Get keyword bids. Common FieldNames: KeywordId, AdGroupId, CampaignId, Bid, ContextBid, CurrentSearchPrice, MinSearchPrice, StrategyPriority.
No parameter schema on file.
Get bid modifiers. Common FieldNames: Id, CampaignId, AdGroupId, Type, Level, MobileAdjustment, DesktopAdjustment, DemographicsAdjustment, RetargetingAdjustment, RegionalAdjustment, VideoAdjustment, SmartAdAdjustment, IncomeGradeAdjustment.
No parameter schema on file.
Get sitelink sets. Common FieldNames: Id, Sitelinks. Each Sitelinks contains an array of {Title, Href, Description}.
No parameter schema on file.
Get VCards (business cards). Common FieldNames: Id, CampaignId, CompanyName, WorkTime, Phone, Street, Building, City, Country, Ogrn, InstantMessenger, ExtraMessage, ContactEmail, ContactPerson.
No parameter schema on file.
Archive campaigns by IDs.
No parameter schema on file.
Unarchive campaigns by IDs.
No parameter schema on file.
Suspend (pause) campaigns by IDs.
No parameter schema on file.
Resume campaigns by IDs.
No parameter schema on file.
Archive ad groups by IDs.
No parameter schema on file.
Unarchive ad groups by IDs.
No parameter schema on file.
Archive ads by IDs.
No parameter schema on file.
Unarchive ads by IDs.
No parameter schema on file.
Send ads for moderation by IDs.
No parameter schema on file.
Suspend keywords by IDs.
No parameter schema on file.
Resume keywords by IDs.
No parameter schema on file.
Delete campaigns by IDs.
No parameter schema on file.
Delete ad groups by IDs.
No parameter schema on file.
Delete ads by IDs.
No parameter schema on file.
Delete keywords by IDs.
No parameter schema on file.
Delete bid modifiers by IDs.
No parameter schema on file.
Delete sitelink sets by IDs.
No parameter schema on file.
Delete VCards by IDs.
No parameter schema on file.
Add new campaigns. Pass a JSON array of campaign objects. Each must include Name and a campaign-type-specific settings object (e.g. TextCampaign, DynamicTextCampaign).
No parameter schema on file.
Add new ad groups. Each must include Name, CampaignId, RegionIds, and optionally type-specific settings.
No parameter schema on file.
Add new ads. Each must include AdGroupId and an ad-type-specific object (TextAd, DynamicTextAd, etc.).
No parameter schema on file.
Add new keywords. Each must include Keyword text and AdGroupId.
No parameter schema on file.
Add bid modifiers. Each must include CampaignId or AdGroupId and an adjustment object.
No parameter schema on file.
Add sitelink sets. Each set contains a Sitelinks array of {Title, Href, Description} objects (2-8 sitelinks per set).
No parameter schema on file.
Add VCards. Each must include CampaignId, Country, City, CompanyName, WorkTime, and Phone.
No parameter schema on file.
Update existing campaigns. Pass a JSON array of campaign objects with Id and fields to update.
No parameter schema on file.
Update existing ad groups. Pass a JSON array with Id and fields to update.
No parameter schema on file.
Update existing ads. Pass a JSON array with Id and fields to update.
No parameter schema on file.
Update existing keywords. Pass a JSON array with Id and fields to update.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Yandex Direct or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 97 / 100
Release 2.2.1 · scanned 16 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score97
Findings0 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationsource
Surface digest41337eaa7c4a2df3d2c416229349ec0b40ade87c912ee645092d9b1a691da0d9
Score vectorthreat 100 → client 97
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (43 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| set_keyword_bids | no tags | |
| set_auto_keyword_bids | no tags | |
| set_bid_modifiers | no tags | |
| create_report | no tags | |
| get_dictionaries | external-sink | external-sink: handler sends an HTTP POST (fetch(url) at src/index.mjs:134 |
| get_clients | external-sink | external-sink: handler sends an HTTP POST (fetch(url) at src/index.mjs:134 |
| get_campaigns | no tags | |
| get_adgroups | no tags | |
| get_ads | no tags | |
| get_keywords | no tags | |
| get_keyword_bids | no tags | |
| get_bid_modifiers | no tags | |
| get_sitelinks | no tags | |
| get_vcards | no tags | |
| archive_campaigns | external-sink | external-sink: handler sends an HTTP POST (fetch(url) at src/index.mjs:134 |
| unarchive_campaigns | external-sink | external-sink: handler sends an HTTP POST (fetch(url) at src/index.mjs:134 |
| suspend_campaigns | external-sink | external-sink: handler sends an HTTP POST (fetch(url) at src/index.mjs:134 |
| resume_campaigns | external-sink | external-sink: handler sends an HTTP POST (fetch(url) at src/index.mjs:134 |
| archive_adgroups | external-sink | external-sink: handler sends an HTTP POST (fetch(url) at src/index.mjs:134 |
| unarchive_adgroups | external-sink | external-sink: handler sends an HTTP POST (fetch(url) at src/index.mjs:134 |
| archive_ads | external-sink | external-sink: handler sends an HTTP POST (fetch(url) at src/index.mjs:134 |
| unarchive_ads | external-sink | external-sink: handler sends an HTTP POST (fetch(url) at src/index.mjs:134 |
| moderate_ads | external-sink | external-sink: handler sends an HTTP POST (fetch(url) at src/index.mjs:134 |
| suspend_keywords | external-sink | external-sink: handler sends an HTTP POST (fetch(url) at src/index.mjs:134 |
| resume_keywords | external-sink | external-sink: handler sends an HTTP POST (fetch(url) at src/index.mjs:134 |
| delete_campaigns | no tags | |
| delete_adgroups | no tags | |
| delete_ads | no tags | |
| delete_keywords | no tags | |
| delete_bid_modifiers | no tags | |
| delete_sitelinks | no tags | |
| delete_vcards | no tags | |
| add_campaigns | no tags | |
| add_adgroups | no tags | |
| add_ads | no tags | |
| add_keywords | no tags | |
| add_bid_modifiers | no tags | |
| add_sitelinks | no tags | |
| add_vcards | no tags | |
| update_campaigns | no tags | |
| update_adgroups | no tags | |
| update_ads | no tags | |
| update_keywords | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest41337eaa7c4a2df3
Scanned2026-10-16
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 2.2.1. Pin a release below and the command asks for exactly that one.
2.2.1
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Yandex Direct can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.