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.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。