ati-hh-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ati-hh-mcp search for remote Python developer jobs in Moscow"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ati-hh-mcp
Public MCP (Model Context Protocol) server for the hh.ru API: every operation of the public hh.ru OpenAPI specification – all 135 of them – exposed as grouped, switchable toolsets for LLM agents. stdio for personal use, streamable HTTP with API keys and OAuth for teams.
Complete and verified: 135/135 public OpenAPI operations are implemented and locked by a contract metatest (operations and required parameters); responses are checked against the vendored specification with live-recorded fixtures.
Safe by design: mutations require an explicit
confirm=trueargument; GET requests are throttled and retried on 429, mutations never repeat automatically; tokens never appear in logs.Built for LLMs: domain-prefixed snake_case tool names, concise English descriptions, structured errors with hh.ru codes and Russian descriptions.
Contents
Related MCP server: HeadHunter API MCP Server
Requirements
Python 3.10 – 3.14 (CI matrix covers every minor version), or Docker.
uv for the uvx/stdio path.
An hh.ru API token or a registered OAuth application for authorized calls; public dictionaries, suggestions and vacancy search work without a token.
Quick start
uvx from git (stdio)
No clone, no install – the server runs straight from the repository:
uvx --from git+https://github.com/timur-ai/ati-hh-mcp ati-hh-mcp serve --transport stdioThe command starts the server on stdio with the default toolsets. Point an
MCP client at it (see client configuration) and set
HH_TOKEN in the server environment for authorized tools.
Docker Compose (HTTP)
git clone https://github.com/timur-ai/ati-hh-mcp
cd ati-hh-mcp
MCP_API_KEYS="$(openssl rand -hex 32)" docker compose up --buildClients connect to http://localhost:8080/mcp with
Authorization: Bearer <your-api-key>. The container is non-root, has a
/health endpoint for the Compose healthcheck, and keeps OAuth tokens in a
SQLite volume. See the deployment guide
for multi-user setup.
TLS is mandatory for network exposure: the server speaks plain HTTP, so
put a TLS-terminating reverse proxy (Caddy/nginx) in front of it, bind the
container to 127.0.0.1 and run a single worker process – see the
deployment guide for
ready-made proxy snippets.
Client configuration
ZCode (stdio)
.zcode/settings.json in the project (or the user config):
{
"mcpServers": {
"hh": {
"command": "uvx",
"args": [
"--from", "git+https://github.com/timur-ai/ati-hh-mcp",
"ati-hh-mcp", "serve", "--transport", "stdio"
],
"env": {
"HH_TOKEN": "YOUR_HH_TOKEN",
"HH_UA_EMAIL": "you@example.com"
}
}
}
}Claude Desktop (stdio)
claude_desktop_config.json
(macOS: ~/Library/Application Support/Claude/claude_desktop_config.json,
Windows: %APPDATA%\Claude\claude_desktop_config.json):
{
"mcpServers": {
"hh": {
"command": "uvx",
"args": [
"--from", "git+https://github.com/timur-ai/ati-hh-mcp",
"ati-hh-mcp", "serve", "--transport", "stdio"
],
"env": {
"HH_TOKEN": "YOUR_HH_TOKEN",
"HH_UA_EMAIL": "you@example.com"
}
}
}
}Cursor (stdio and HTTP)
.cursor/mcp.json. stdio launch:
{
"mcpServers": {
"hh": {
"command": "uvx",
"args": [
"--from", "git+https://github.com/timur-ai/ati-hh-mcp",
"ati-hh-mcp", "serve", "--transport", "stdio"
],
"env": {
"HH_TOKEN": "YOUR_HH_TOKEN",
"HH_UA_EMAIL": "you@example.com"
}
}
}
}Connection to the Docker/HTTP deployment:
{
"mcpServers": {
"hh": {
"url": "http://localhost:8080/mcp",
"headers": {
"Authorization": "Bearer YOUR_MCP_API_KEY"
}
}
}
}Toolsets
62 tools are enabled by default; six employer toolsets and the undocumented
extended set are opt-in via HH_TOOLSETS. HH_TOOLSETS fully replaces the
default list; the auth toolset is always included regardless.
A generated catalog with every tool, its OpenAPI operation and description
lives in the tool reference.
Toolset | Tools | Default | Domain |
| 5 | always on |
|
| 16 | on | areas, industries, professional roles, languages, locales, metro, skills, universities, vacancy conditions |
| 11 | on | search suggestions: areas, companies, positions, skills, keywords |
| 4 | on | vacancy search, similar and related vacancies |
| 10 | on | responses/invitations: lists, states, messages, tests, invitations |
| 14 | on | chats: messages, participants, files, read counters |
| 2 | on | resume viewing, call-tracking phone numbers |
| 23 | off | employer vacancy CRUD, drafts, publication, statistics |
| 5 | off | employer responses/invitations, mail templates, statistics |
| 11 | off | resume search (52 parameters), saved searches, applicant comments |
| 11 | off | managers, settings, access and limits |
| 25 | off | employers info, addresses, departments, calls, webhooks, salary statistics |
| 4 | off | undocumented: apply to a vacancy, own resumes, artifacts |
Enable extra toolsets with a comma-separated list, for example
HH_TOOLSETS=employer_vacancies,employer_resumes.
Authorization
The server separates access to the MCP server from access to hh.ru:
Authorization: Bearer <key>(HTTP mode) – the MCP API key fromMCP_API_KEYS; protects the server itself in multi-user deployments.X-HH-Token: <hh-token>– the hh.ru token for a single request (HTTP mode).OAuth profile – token pairs stored in SQLite per MCP API key.
An hh.ru token can be provided in three ways.
1. Static token
Set HH_TOKEN in the server environment (the usual stdio path). Applies to
every call of the deployment; in HTTP mode with MCP_API_KEYS set, HH_TOKEN
is deliberately ignored to avoid mixing user profiles.
2. Per-request token header
Send X-HH-Token: <token> with an MCP call (HTTP mode). The token is used
statelessly for that request only and is never stored.
3. OAuth login
With HH_CLIENT_ID, HH_CLIENT_SECRET and HH_REDIRECT_URI configured:
stdio: call
auth_get_login_url, open the URL in a browser, log in on hh.ru, copy thecodeparameter from the redirect address, then callauth_exchange_code(code). Token pairs land in the local SQLite store and refresh automatically.HTTP: same flow, but the redirect goes to
GET /oauth/callbackon the server and the exchange completes automatically. The OAuthstateparameter is bound to the caller's profile, so tokens land in the right SQLite profile.
auth_status shows the current profile state, auth_logout calls
DELETE /token on hh.ru and drops the stored pair.
Registering an hh.ru application
Sign in at dev.hh.ru and open the application admin.
Create an application; you will get
HH_CLIENT_IDandHH_CLIENT_SECRET.Register the redirect URI:
HTTP deployment:
http://<your-host>:8080/oauth/callback(for local testinghttp://localhost:8080/oauth/callback);stdio: any previously registered URI works – you copy the code manually.
Set
HH_CLIENT_ID,HH_CLIENT_SECRET,HH_REDIRECT_URIin the server environment and restart.
Two-level search schema
Heavy search operations (search_vacancies with 45 parameters,
employer_search_resumes with 52) would bury an LLM in flat arguments. Such tools use
a two-level schema: frequent filters are top-level tool parameters, the long
tail lives in a nested advanced object:
{
"text": "python developer",
"area": "1",
"salary": 200000,
"advanced": { "work_format": "remote", "date_from": "2026-01-01" }
}Unset fields – top-level or nested – are simply not sent to hh.ru. The allowed subset is locked in the tool registry and verified by the contract metatest, so no parameter outside the OpenAPI operation can sneak in.
Architecture
flowchart LR
A["MCP client<br/>(ZCode, Claude, Cursor)"] -- "stdio" --> S
A -- "HTTP + Bearer MCP API key" --> S
S["FastMCP server<br/>transports - auth middleware - /health - /oauth/callback"]
S --> R["Registry<br/>tool = operation (135/135)"]
S --> T["13 toolsets / 141 tools<br/>mutating tools require confirm"]
T --> K["toolkit make_tool<br/>path/query/body packing"]
K --> C["HHClient<br/>User-Agent - token bucket - 429 retries (GET only)"]
C -- "HTTPS + Bearer hh.ru token" --> HH["api.hh.ru"]
S -.-> DB[("TokenStore SQLite<br/>OAuth profiles per API key")]
B["browser OAuth"] -.-> STransports: stdio for personal launch (
uvx git+...), streamable HTTP withMCP_API_KEYSfor teams;/healthfor Docker healthchecks.Registry: the single source of truth mapping every tool to its OpenAPI operation; a contract metatest enforces
required params of the operation subset of tool params subset of operation params.HHClient: token-bucket throttling (default 25 req/min), the User-Agent contact policy of hh.ru, automatic 429 retries for GET only – mutations fail loudly instead of repeating.
TokenStore: SQLite, one OAuth profile per MCP API key (keyed by the sha256 hash – raw keys are never stored); automatic refresh on expiry.
Configuration
Environment variable | Default | Purpose |
| – | hh.ru token for all calls (stdio path; ignored in HTTP mode with |
| – | OAuth application client id (dev.hh.ru) |
| – | OAuth application client secret |
| – | OAuth redirect URI registered at dev.hh.ru |
| default set | Comma-separated toolsets to enable; fully replaces the default list ( |
|
| API base URL (tests and experiments) |
| placeholder | Contact email in the User-Agent (hh.ru requirement) |
|
| Requests per minute (token bucket) |
| platform dir | SQLite path for OAuth token pairs (Docker: |
| – | Comma-separated API keys guarding the HTTP endpoint (case-sensitive) |
Limitations
Stated honestly:
No resume CRUD. The public hh.ru OpenAPI has no operations to create or edit resumes; the
resumestoolset is read-only by design.The extended toolset is undocumented API.
apply_to_vacancy,my_resumes,artifacts_list,artifact_deleterely on endpoints outside the public specification; they are disabled by default, marked[UNDOCUMENTED hh.ru API]and may break without notice.Authorization header semantics.
Authorizationcarries the MCP server API key, not the hh.ru token; the hh.ru token travels inX-HH-TokenorHH_TOKEN. This mirrors the two-tenant reality (server access vs hh.ru access) and is an intentional deviation from the hh.ru API convention.Retries are GET-only. A timed-out mutation is reported as an error with a "may have been applied" hint; it is never retried automatically.
The live API drifts from the specification. Responses are validated against the vendored OpenAPI with live-recorded fixtures; the single confirmed deviation (
GET /suggests/companiesreturnsnullin non-nullableurl,area.name,logo_urls) is pinned inKNOWN_DEVIATIONSoftests/contract/test_schemas.py.Search endpoints are geo-blocked for datacenter IPs by hh.ru; the fixture recorder skips them (403
forbidden) when run from such networks. The server itself is unaffected when run from an allowed network.
Documented deviations
From the original design decisions, recorded with reasons:
FastMCP 4.1 instead of "FastMCP 2": the plan fixed the family, the concrete major was chosen in the M1 spike by stability and Python 3.10–3.14 support criteria; pinned in
uv.lock. Details: ADR Z1.__main__coverage floor is 90 %, below the project-wide 95 % – the CLI entrypoint is a thin argument parser around tested components.Distribution is sources-only (git + Docker): no PyPI, no GHCR, per the project decision.
Development
uv sync --dev # environment
uv run pytest -q # 547 tests (+8 live, opt-in): unit + contract + MCP e2e
uv run ruff check src tests # lint
uv run mypy src # strict type checkUseful maintenance scripts:
uv run python scripts/record_fixtures.py # re-record live response fixtures (read-only, sanitized)
uv run python scripts/gen_tool_docs.py # regenerate docs/tools/ from the registry
bash scripts/fetch_openapi.sh # refresh the vendored OpenAPI spec
uv run mkdocs serve # documentation site locallyLive integration tests (tests/integration_live/, marker live) are opt-in
and safe: read-only calls, token from the HH_LIVE_TOKEN secret, masked in
logs. The documentation site builds strictly (mkdocs build --strict) and
deploys to GitHub Pages from main on every push.
License
Available Tools
62 toolsauth_exchange_codeAuth Exchange CodeA
Exchange an hh.ru OAuth authorization code for token pair.
Use after auth_get_login_url: pass the code parameter copied
from the redirect address. Tokens are stored in the local profile.
Inputs: code (required). Returns: object
auth_get_login_urlAuth Get Login UrlA
Get the hh.ru OAuth login URL (manual code copy flow).
Returns the authorize URL and Russian instructions: open the URL,
log in on hh.ru, copy the code query parameter from the redirect
address and pass it to auth_exchange_code.
Inputs: no named parameters. Returns: object
auth_logoutAuth LogoutA
Revoke the hh.ru OAuth token and delete the local profile.
Calls DELETE /token on hh.ru (invalidates the token pair) and removes stored tokens. Mutation: requires confirm=True.
Inputs: confirm. Returns: object
auth_statusAuth StatusA
Show OAuth configuration and stored token status.
Reports whether OAuth client credentials are configured, whether
a token pair is stored for the current profile (the request
profile in HTTP mode, default otherwise), and when it was
obtained.
Inputs: no named parameters. Returns: object
create_chat_file_upload_linkCreate Chat File Upload LinkA
Create a one-time upload link for a chat file attachment. Upload the file with a multipart POST (field 'file') to the returned URL, then send the message with the received file_upload_id (see send_chat_message). Check get_chat_file_conditions first. Mutation: requires confirm=True.
Inputs: body, confirm.
create_chat_without_vacancyCreate Chat Without VacancyA
Get an existing chat or create a new one bound to a resume without a specific vacancy (resume_hash is required, an optional first_message opens the conversation). Mutation: requires confirm=True.
Inputs: body (required), confirm.
delete_chat_messageDelete Chat MessageA
Delete your own message from a chat. Mutation: requires confirm=True.
Inputs: chat_id (required), message_id (required), confirm.
dict_areaDict AreaA
Get one hh.ru region (area) by its numeric id, including nested children. Optional additional_case=prepositional adds a Russian prepositional-case name.
Inputs: area_id (required), additional_case.
dict_area_countriesDict Area CountriesA
Get the list of countries known to hh.ru with their numeric ids (each country is also an area).
Inputs: no named parameters.
dict_areasDict AreasB
Get the full tree of hh.ru regions (areas): countries, federal subjects and cities, with their numeric ids. Optional additional_case=prepositional adds a Russian prepositional-case name.
Inputs: additional_case.
dict_dictionariesDict DictionariesA
Get hh.ru core dictionaries: currencies, genders, vacancies statuses and other enumerations used across the API.
Inputs: no named parameters.
dict_districtsDict DistrictsA
Get the administrative districts of Russian cities (district ids narrow down a vacancy search within a city).
Inputs: no named parameters.
dict_educational_institutionsDict Educational InstitutionsA
Get educational institutions by id (up to 50 values per request). Find institution ids with suggest_educational_institutions.
Inputs: id (required).
dict_facultiesDict FacultiesC
Get the faculty list of one educational institution by its id.
Inputs: id (required).
dict_industriesDict IndustriesA
Get the tree of industries (spheres of company activity) with sub-industries and their ids.
Inputs: no named parameters.
dict_languagesDict LanguagesA
Get the dictionary of foreign languages with their ids.
Inputs: no named parameters.
dict_localesDict LocalesB
Get the locales supported by hh.ru (vacancy interface).
Inputs: no named parameters.
dict_metroDict MetroA
Get metro lines and stations for all hh.ru cities that have a metro map, grouped by city with station ids.
Inputs: no named parameters.
dict_metro_cityDict Metro CityB
Get metro lines and stations of a single city by area id (for example 4 = Moscow).
Inputs: city_id (required).
dict_professional_rolesDict Professional RolesA
Get the tree of professional roles (job categories) with sub-categories and their numeric ids; role ids are used in vacancy and resume search.
Inputs: no named parameters.
dict_resume_localesDict Resume LocalesA
Get the locales supported in hh.ru resumes.
Inputs: no named parameters.
dict_skillsDict SkillsA
Get key skills by id (one or several; up to 50 values per request). Find skill ids with suggest_skill_set.
Inputs: id (required).
dict_vacancy_conditionsDict Vacancy ConditionsA
Get the dictionary of paid vacancy placement conditions (branded templates, priority placement and similar options).
Inputs: no named parameters.
get_chat_file_conditionsGet Chat File ConditionsA
Get conditions for files attached to chat messages: allowed formats, size limits and other constraints.
Inputs: no named parameters.
get_chat_participantsGet Chat ParticipantsC
List participants of the chat: the applicant and employer managers involved in the conversation.
Inputs: chat_id (required).
get_meGet MeA
Get information about the current hh.ru user (GET /me).
Requires an hh.ru token (HH_TOKEN env, X-HH-Token header or OAuth profile). If the token has expired, the server refreshes the OAuth pair and retries the request once.
Inputs: no named parameters.
get_negotiationGet NegotiationA
Get full information about a single negotiation (response or invitation) by its id, including messages URL and available state actions.
Inputs: id (required).
get_negotiation_test_solutionGet Negotiation Test SolutionC
Get the results of tests completed by the applicant of a negotiation (attached to the vacancy).
Inputs: nid (required).
get_resumeGet ResumeA
Get a resume by id or hash: own resume for an applicant or an accessible resume for an employer. Optional flags add contact credentials, job search status and negotiation history.
Inputs: resume_id (required), with_creds, with_job_search_status, with_negotiations_history.
get_resume_phoneGet Resume PhoneA
Get the phone number of a resume through hh.ru call tracking (employer side; the call is logged by hh.ru).
Inputs: resume_id (required).
get_unread_countersGet Unread CountersA
Get the number of unread chats for the current user (total and with new messages).
Inputs: no named parameters.
get_vacancyGet VacancyB
Get full details of one vacancy by its numeric id, including salary, key skills, contacts and branded description.
Inputs: vacancy_id (required).
leave_chatLeave ChatC
Leave the given chat. Mutation: requires confirm=True.
Inputs: chat_id (required), confirm.
list_chat_messagesList Chat MessagesB
List messages of a chat, starting from start_message_id in the given order (next or prev) with a limit (default 10).
Inputs: chat_id (required), limit, order, start_message_id.
list_chatsList ChatsB
List chats of the current user (applicant or employer) with pagination and filters: unread only, with text messages, by vacancy status or explicit vacancy ids.
Inputs: page, per_page, filter_unread, vacancy_status, +2 more.
list_collection_negotiationsList Collection NegotiationsC
List negotiations of the unsorted responses collection ("/response") of a vacancy with resume-like filters: area, experience, education, salary range, age and others. The same URL pattern serves other collections: replace the last path segment with the collection id from the collections list.
Inputs: vacancy_id (required), area, page, age_to, +22 more.
list_negotiation_messagesList Negotiation MessagesB
List all messages of a negotiation (response or invitation) thread. Note: hh.ru considers negotiation messaging legacy and recommends chats; use with_text_only to skip service messages.
Inputs: nid (required), page, per_page, with_text_only.
list_negotiationsList NegotiationsB
List negotiations (responses and invitations) of the current user. Filter by status, vacancy or unread updates; ordered by last update (newest first) by default. The response contains collections with actions URLs used by other negotiation tools.
Inputs: page, order, status, order_by, +5 more.
mark_chat_message_readMark Chat Message ReadB
Mark the message as the last viewed one in the chat (updates unread counters). Mutation: requires confirm=True.
Inputs: chat_id (required), message_id (required), confirm.
mark_negotiations_readMark Negotiations ReadA
Mark negotiations as read. topic_id values in the body must belong to one vacancy (up to 50 ids). Mutation: requires confirm=True.
Inputs: body (required), confirm.
move_negotiationMove NegotiationB
Change the employer or applicant state of a negotiation by moving it to another collection (for example from response to invitation). collection_name and nid come from the actions URL of the negotiation; an optional message can be attached. Mutation: requires confirm=True.
Inputs: nid (required), collection_name (required), body, confirm.
request_phone_interviewRequest Phone InterviewA
Invite an applicant to a vacancy by resume: creates an invitation negotiation, optionally sends an email message and an SMS notification. resume_id and vacancy_id are required in the body (sent form-encoded per the vendor spec). Mutation: requires confirm=True.
Inputs: body (required), confirm.
search_vacanciesSearch VacanciesA
Search vacancies on hh.ru. Frequent filters (text, area, salary, currency, experience, employment, schedule, search_field, page, per_page, order_by and others) are top-level parameters. Rare or niche filters are grouped into the nested advanced object: pass only the fields you need, unset fields are not sent. Resolve ids first: dict_areas, dict_professional_roles, dict_industries, dict_metro. The response includes found, pages and clusters for pagination.
Inputs: area, page, text, label, +15 more.
send_chat_messageSend Chat MessageA
Send a message to a chat: either a text message ({"text": "..."}) or a file ({"file_upload_id": "..."} from create_chat_file_upload_link). Mutation: requires confirm=True.
Inputs: body (required), chat_id (required), confirm.
send_negotiation_messageSend Negotiation MessageB
Send a new message inside a negotiation thread. Sending is possible while the conversation is open (see the hh.ru rules for negotiations). Mutation: requires confirm=True.
Inputs: nid (required), body (required), confirm.
set_chat_write_possibilitySet Chat Write PossibilityA
Enable or disable the applicant's right to write messages in the chat (employer side; applicant_write_possibility is sent as a query parameter). Mutation: requires confirm=True.
Inputs: chat_id (required), applicant_write_possibility (required), body, confirm.
similar_vacanciesSimilar VacanciesC
Get vacancies similar to the given vacancy id; supports the same frequent filters as search_vacancies plus the nested advanced object for rare filters.
Inputs: vacancy_id (required), area, page, text, +16 more.
suggest_area_leavesSuggest Area LeavesA
Suggest leaf regions (cities/districts without children) inside area_id by name prefix; used to pick concrete locations.
Inputs: text (required), area_id.
suggest_areasSuggest AreasA
Suggest hh.ru regions (areas) by name prefix; returns matching areas with ids. area_id narrows the search to children of a given region, include_parent=true adds the parent region to the response.
Inputs: text (required), area_id, include_parent.
suggest_companiesSuggest CompaniesA
Suggest registered employers (companies) by name prefix with their ids and urls.
Inputs: text (required).
suggest_educational_institutionsSuggest Educational InstitutionsB
Suggest educational institutions by name prefix with their ids.
Inputs: text (required).
suggest_fields_of_studySuggest Fields Of StudyA
Suggest fields of study (specialties) by name prefix with their ids for resume and vacancy education blocks.
Inputs: text (required).
suggest_positionsSuggest PositionsA
Suggest job positions (titles) by name prefix for resumes; returns positions with professional role ids.
Inputs: text (required).
suggest_professional_rolesSuggest Professional RolesB
Suggest professional roles by name prefix with their ids for vacancy and resume search.
Inputs: text (required).
suggest_resume_search_keywordSuggest Resume Search KeywordA
Suggest full search phrases for resume search by a partial keyword (employer side).
Inputs: text (required).
suggest_skill_setSuggest Skill SetB
Suggest key skills by name prefix with their ids; skill ids are accepted by dict_skills.
Inputs: text (required).
suggest_vacancy_positionsSuggest Vacancy PositionsA
Suggest job positions (titles) by name prefix for vacancies; returns positions with professional role ids.
Inputs: text (required).
suggest_vacancy_search_keywordSuggest Vacancy Search KeywordB
Suggest full search phrases for vacancy search by a partial keyword (applicant side).
Inputs: text (required).
update_chat_messageUpdate Chat MessageB
Edit the text of your own message in a chat. Mutation: requires confirm=True.
Inputs: body (required), chat_id (required), message_id (required), confirm.
update_chat_participantsUpdate Chat ParticipantsB
Add an employer manager to the chat (body: manager id). Mutation: requires confirm=True.
Inputs: body (required), chat_id (required), confirm.
update_negotiationUpdate NegotiationA
Apply a collection action (for example invite or decline) to one or more negotiations. The {id} path value and required body arguments (topic_id, message, send_sms and others) come from actions[].url and actions[].arguments of the negotiation list. Mutation: requires confirm=True.
Inputs: id (required), body (required), confirm.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 62 tools
Most tools target a distinct resource+action, but with 62 tools there are several near-pairs that require careful reading: dict_areas vs suggest_areas vs suggest_area_leaves, dict_metro vs dict_metro_city, suggest_positions vs suggest_vacancy_positions vs suggest_professional_roles, and list_negotiations vs list_collection_negotiations. Descriptions do clarify the boundaries (resume-side vs vacancy-side, legacy negotiations vs chats), but an agent can still misselect without close attention.
Names follow a predictable, readable pattern of domain prefix + verb/noun (dict_*, suggest_*, auth_*, chat_*, negotiation_*), with clear verb_noun forms like get_resume, list_chats, send_chat_message, delete_chat_message. Minor deviations exist (e.g. get_me, similar_vacancies, related_vacancies lack a domain prefix, and auth_get_login_url mixes prefix and verb), but the overall scheme is coherent.
62 tools far exceeds the 3-15 sweet spot and makes the surface hard for an agent to navigate; many niche dictionary/suggest endpoints could be consolidated or lazily exposed. Each tool does map to a real hh.ru endpoint, so it is not arbitrary bloat, but the count is still excessive for practical selection.
Coverage is broad across dictionaries, OAuth, negotiations, and chats (including message CRUD, file uploads, and participant management), so core workflows are reachable. However, key lifecycle operations are missing: resumes and vacancies are read-only (no create/update/publish), and applicant-side/employer-side applicant search tools are absent, leaving notable gaps.
Maintenance
Related MCP Connectors
Multi-tenant Telegram gateway for AI agents — HTTP+stdio, 8 tools, MTProto User API
87 public tools: agent workflows, audio data transfer, semantic search, queues and webhooks.
100+ pay-per-call x402 tools for AI agents (web, company, crypto, media); 22,000+ APIs to search
Russian APIs for AI agents: YooKassa, CDEK, Bitrix24 and more. Ready scenarios with code. No key.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to search job vacancies, manage resumes, and apply to jobs on HeadHunter (hh.ru), Russia's largest job search platform. Includes OAuth 2.0 integration for secure job applications and an automated vacancy hunter agent with intelligent matching.38MIT
- AlicenseNot gradedqualityFmaintenanceEnables AI assistants to access and manage HeadHunter job platform data, including vacancies, resumes, negotiations, and employer settings via 167+ tools.5MIT
- AlicenseNot gradedqualityDmaintenanceExposes iiko restaurant management system REST API as 42+ LLM-callable tools over stdio, enabling natural language interaction with products, employees, orders, payments, OLAP reports, and assembly charts.3MIT
- AlicenseAqualityBmaintenanceEnables searching and retrieving job vacancies, resumes, employers, and salary statistics from the hh.ru API (Russia/CIS) via 19 tools, with optional token access for resume search.1996 npm9MIT