Naver Search Ad MCP
An MCP server for the Naver Search Ad API that enables querying campaigns, ad groups, keywords, stats, keyword research, and bid estimates through any MCP client.
README
Naver Search Ad MCP
An MCP server for the Naver Search Ad (네이버 검색광고) API — read/analytics focused. Query campaigns, ad groups, keywords, stats, keyword research, and bid estimates through any MCP client.
- Read-only by default (safe): all tools are annotated
readOnlyHint. - Multi-account: one credential per user auto-discovers every advertiser
account it can access (agency-delegated + own) via
/ad-accounts+child-ad-accounts, addressed byaccount_id(= NavercustomerId). - Two transports: local
stdiofor a single account, or hostedstreamable-http(Google Workspace OAuth) for a team — see DEPLOY.md.
Quick start (local, stdio)
Get your credentials at searchad.naver.com → 관리 → 도구 → API 사용 관리 (CUSTOMER_ID, access license, secret key).
uv venv --python 3.13
uv pip install -e .
export NAVER_API_KEY=... # access license
export NAVER_SECRET_KEY=... # secret key
export NAVER_CUSTOMER_ID=... # customer id (integer)
naver-searchad-mcp # stdio MCP server
Register with an MCP client (e.g. Claude Desktop):
{
"mcpServers": {
"naver-searchad": {
"command": "/path/to/.venv/bin/naver-searchad-mcp",
"env": {
"NAVER_API_KEY": "...",
"NAVER_SECRET_KEY": "...",
"NAVER_CUSTOMER_ID": "..."
}
}
}
}
Tools
Accounts
| Tool | Description |
|---|---|
list_accounts() |
All accessible ad accounts (/ad-accounts ∪ child-ad-accounts, deduped). Each account_id = customerId |
get_accounts_overview(...) |
Per-account campaign count + period performance summary |
whoami() |
Diagnostic: authenticated caller + linked credential (hosted mode) |
Entities
| Tool | Description |
|---|---|
list_campaigns(account_id, campaign_type?) |
Campaigns |
get_campaign(account_id, campaign_id) |
Campaign detail |
list_adgroups(account_id, campaign_id) |
Ad groups |
get_adgroup(account_id, adgroup_id) |
Ad group detail |
list_keywords(account_id, adgroup_id) |
Keywords |
list_ads(account_id, adgroup_id) |
Ads (creatives) |
list_business_channels(account_id) |
Business channels |
Performance & analytics
| Tool | Description |
|---|---|
get_stats(account_id, ids[], fields[], since/until|date_preset, ...) |
Low-level /stats (≤92-day window, single entity level) |
get_campaign_performance(account_id, dates, fields?) |
All campaigns + names |
get_keyword_performance(account_id, adgroup_id, dates) |
Keyword performance + text |
get_related_keywords(account_id, hint_keywords[]) |
Related keywords, search volume, competition (/keywordstool) |
get_performance_report(account_id, level, since, until, daily?, ...) |
Named report; auto-chunks >92 days; aggregate (ratios recomputed) or daily |
create_stat_report(account_id, report_tp, stat_dt) |
Async bulk StatReport job (1 job = 1 day) |
download_stat_report(account_id, download_url, max_rows?) |
Download StatReport TSV (raw, columns not interpreted) |
Bid estimates
| Tool | Description |
|---|---|
estimate_keyword_bid(account_id, keywords[], estimate_type, device, position) |
Target-position / min-exposure bid |
estimate_keyword_performance(account_id, keyword, bids[], device) |
Predicted impressions/clicks/cost per bid |
Metric field names are terse and sometimes misleading (salesAmt = cost,
ror = ROAS %); the server attaches clear aliases (cost, roas_pct, …)
and exposes a naver://metric-glossary resource.
Hosted deployment (team, Google OAuth)
See DEPLOY.md — Cloud Run + Secret Manager + Google Workspace
OAuth, per-email credential model, and a self-service admin console at /admin.
Development
uv pip install -e ".[dev]"
pytest
Notes
- This server covers Search Ad only. Naver GFA (성과형 디스플레이광고) is a separate API (partner-only OAuth) and is out of scope.
- Signing rule:
base64(HMAC_SHA256(secret, "{timestamp}.{METHOD}.{path}"))— path only, query excluded, timestamp in ms.
License
MIT — see LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.