Yandex connector for AI agents

Tools your analytics agent reaches for on Yandex, scoped per user.

CALL ANY TOOL

62 tools for files and analytics in Yandex: browse, upload, copy, move, publish, and restore files on Yandex Disk, read Yandex Metrica reports and raw logs, and manage counters, goals, filters, segments, and chart notes.

yandex_disk_copy_resource

Disk copy resource

Copy a file or folder to another location on Yandex Disk. Returns a link to the new item (201), or an operation link (202) when a large folder is processed in the background. Use Get Operation Status to follow a 202. Use Create Folder first if the destination folder does not exist. Requires cloud_api:disk.write.

Parameters

Name

Type

Required

Description

from

string

Required

Path of the file or folder to copy, starting at the Disk root. Example: /Documents/report.pdf.

path

string

Required

Destination path including the new name, starting at the Disk root. Example: /Archive/report.pdf.

fields

string

Optional

Comma-separated list of response properties to keep; embedded keys use dots. Omit to return the full response. Example: name,_embedded.items.path.

overwrite

boolean

Optional

When true, replaces an existing item at the destination. Yandex Disk fails the request when omitted (false) and the destination exists. Example: false. Default: `false`.

yandex_disk_create_folder

Disk create folder

yandex_disk_delete_from_trash

Disk delete from trash

yandex_disk_get_download_link

Disk get download link

yandex_disk_get_operation_status

Disk get operation status

yandex_disk_get_public_resource

Disk get public resource

yandex_disk_get_upload_link

Disk get upload link

yandex_disk_list_all_files

Disk list all files

yandex_disk_list_recent_uploads

Disk list recent uploads

yandex_disk_publish_resource

Disk publish resource

yandex_disk_restore_from_trash

Disk restore from trash

yandex_disk_unpublish_resource

Disk unpublish resource

yandex_disk_update_resource_properties

Disk update resource properties

yandex_disk_upload_from_url

Disk upload from url

yandex_metrika_cancel_log_request

Metrika cancel log request

yandex_metrika_create_counter

Metrika create counter

yandex_metrika_create_goal

Metrika create goal

yandex_metrika_create_log_request

Metrika create log request

yandex_metrika_delete_annotation

Metrika delete annotation

yandex_metrika_delete_filter

Metrika delete filter

yandex_metrika_delete_label

Metrika delete label

yandex_metrika_get_counter

Metrika get counter

yandex_metrika_get_log_request

Metrika get log request

yandex_metrika_get_report_by_time

Metrika get report by time

Get Yandex Metrica statistics over time, with metric values per day, week, month, quarter, or year. Returns time intervals and, for each dimension value, a series of metric values. Use for trends and charts. Use Get Report Table for a single total per row. Requires metrika:read.

Parameters

Name

Type

Required

Description

ids

string

Required

Comma-separated IDs of the Metrica counters to report on. Example: 44147844 or 44147844,12345678.

metrics

string

Required

Comma-separated metrics, up to 20, such as ym:s:visits, ym:s:users, ym:s:pageviews, ym:s:bounceRate. Example: ym:s:visits,ym:s:users.

accuracy

string

Optional

Sampling accuracy: a fraction from 0 to 1, or full for no sampling. Example: full.

date1

string

Optional

Start of the period as YYYY-MM-DD, today, yesterday, or NdaysAgo. Metrica uses 6daysAgo when omitted. Example: 30daysAgo.

date2

string

Optional

End of the period as YYYY-MM-DD, today, yesterday, or NdaysAgo. Metrica uses today when omitted. Example: yesterday.

dimensions

string

Optional

Comma-separated dimensions to group by, up to 10, such as ym:s:date, ym:s:trafficSourceName, ym:s:regionCountry. Example: ym:s:trafficSourceName.

filters

string

Optional

Segmentation filter in Metrica filter syntax. Example: ym:s:regionCountry=='225'.

group

string

Optional

Size of each time interval. Allowed: day, week, month, quarter, year. Metrica uses week when omitted. Example: day. One of: `day`, `week`, `month`, `quarter`, `year`.

include_undefined

boolean

Optional

When true, includes rows whose first dimension is undefined. Metrica excludes them when omitted. Example: false.

lang

string

Optional

Language of dimension names in the response, such as en or ru. Example: en.

preset

string

Optional

Name of a Metrica report preset to use instead of choosing metrics and dimensions yourself. Example: sources_summary.

timezone

string

Optional

Time zone for the period in ±hh:mm format. The counter's own time zone is used when omitted. Example: +03:00.

top_keys

integer

Optional

Number of top dimension values to chart, up to 30. Metrica uses 7 when omitted. Example: 10.

yandex_metrika_list_counters

Metrika list counters

List the Yandex Metrica counters the connected user can access. Returns each counter's id, name, site, status, permission level, and create time. Use to find a counter ID for any other Metrica tool. Use Get Counter for the full settings of one counter. Requires metrika:read.

Parameters

Name

Type

Required

Description

favorite

boolean

Optional

When true, return only counters marked as favorites. Metrica returns all counters when omitted. Example: true.

field

string

Optional

Comma-separated extra sections to include in each counter. Allowed: goals, mirrors, grants, filters, operations, counter_flags, measurement_tokens. Omit for the base counter fields only. Example: goals,filters.

label_id

integer

Optional

Return only counters attached to this label. Find IDs with List Labels. Example: 1234.

offset

integer

Optional

1-based position of the first counter to return, for pagination. Metrica starts at 1 when omitted. Example: 51.

per_page

integer

Optional

Number of counters to return. Metrica returns up to 1000 when omitted. Example: 50.

permission

string

Optional

Filter by the user's access level, one or several separated by commas. Allowed: own, view, edit. Example: own,edit.

reverse

boolean

Optional

When true, returns the sorted list in descending order. Metrica returns descending order when omitted (true). Example: true.

search_string

string

Optional

Return only counters whose ID, name, site, or mirror address contains this text; an ID must be given in full. Example: example.com.

sort

string

Optional

Sort order. Allowed: None, Default, Visits, Hits, Uniques, Name. Metrica uses Default when omitted. Example: Visits. One of: `None`, `Default`, `Visits`, `Hits`, `Uniques`, `Name`.

status

string

Optional

Filter by counter status. Allowed: Active, Deleted. Metrica returns Active counters when omitted. Example: Active. One of: `Active`, `Deleted`.

type

string

Optional

Filter by counter type. Allowed: simple (created in Metrica), partner (imported from the Yandex advertising network). Example: simple. One of: `simple`, `partner`.

yandex_metrika_list_goals

Metrika list goals

yandex_metrika_list_labels

Metrika list labels

yandex_metrika_list_operations

Metrika list operations

yandex_metrika_update_counter

Metrika update counter

yandex_metrika_update_goal

Metrika update goal

For more tools, view docs.

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Yandex tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["yandex"], toolNames: [
    "yandex_metrika_list_counters",
    "yandex_metrika_get_report_table",
    "yandex_disk_list_recent_uploads"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Show visits by traffic source for acme.com last month" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["yandex"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Show visits by traffic source for acme.com last month" }],
  tools,
});

// Execute the tool call with the user's vaulted Yandex OAuth token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["yandex"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Show visits by traffic source for acme.com last month" }],
  tools,
});

// Tool call runs with the user's vaulted Yandex OAuth token
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["yandex"] }, pageSize: 100,
});

const agent = new Agent({
  name: "analytics_agent",
  model: "gemini-2.5-pro",
  instruction: "Yandex tools scoped to this user",
  tools,
});

await agent.run("Show visits by traffic source for acme.com last month");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Yandex tool. Click to copy, paste into your agent, done.

Yandex Disk

Copy the prompt

Copied

How much free space is left on my Yandex Disk?

Copy the prompt

Copied

List files uploaded to my Disk this week.

Copy the prompt

Copied

Publish the Q3 report folder and give me the public link.

Metrica reports

Copy the prompt

Copied

Show visits by traffic source for acme.com last month.

Copy the prompt

Copied

Chart daily visits for the last 30 days.

Copy the prompt

Copied

Export raw session logs for September.

Metrica setup

Copy the prompt

Copied

Create a goal for visits to /thank-you.

Copy the prompt

Copied

Add a filter to exclude traffic from our office IP.

Copy the prompt

Copied

Add a chart note for the October 20 release.

SEE HOW AUTH WORKS

Each user signs in to Yandex once, and Scalekit stores and refreshes their tokens. Credentials stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Yandex

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Yandex

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Yandex

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Yandex

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other files and analytics connectors.

GTM and RevOps Teams

Competitive intelligence briefing agent

Scans Gong calls for competitor mentions, matches each one to its Notion battlecard, and DMs every affected rep a single Slack digest per cycle. Every call runs as the PMM who owns the briefing, never a shared bot.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Yandex token looks fine in a demo. In production every file move and goal change looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Yandex today. Ten connectors tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Yandex as the user or through a shared service account?

As the user. Each user signs in to Yandex once, and Scalekit stores and refreshes their tokens. File moves, published links, and Metrica changes the agent makes are attributed to that user in your audit trail, not a shared service account.

Where is the Yandex OAuth token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Yandex?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example Disk and report read tools without yandex_disk_delete_from_trash, which permanently deletes a file, and yandex_metrika_delete_counter. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Yandex access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Which Yandex services does the connector cover?

Yandex Disk, Yandex Metrica, and the Yandex ID profile. Disk tools work with the signed-in user's files and public links, Metrica tools work with the counters that user can access, and yandex_id_get_user_info returns their login and profile.