Enables interaction with Kakao Channel business chats via MCP tools for checking login status, unread counts, listing chats, reading messages, marking as read, and optionally sending messages when enabled.
Enables AI agents to use Kakao's Local, Search, and Vision APIs for address conversion, place search, web/blog/search, and OCR, requiring only a REST API key.
Enables AI agents to manage Kakao Moment advertisements (Kakao's advertising platform) through natural language queries, supporting campaign, ad group, creative listing, and performance reporting.
Read-only MCP server for querying, analyzing, and reporting Kakao Moment ad data. Supports OAuth login and session-based authentication for multi-user hosting.
Enables reading messages from explicitly permitted macOS KakaoTalk chat rooms and sending replies through a two-step prepare/commit approval flow via the accessibility API. Designed fail-closed, with sending and automation disabled by default.
Enables searching the Kakao Daum Book Search API by title, author, publisher, or ISBN, retrieving detailed bibliographic and pricing metadata, and exporting results to xlsx, csv, json, or sqlite through MCP or CLI.
Provides location-based place recommendations in South Korea using the Kakao Map API, optimized for Korean language queries. Supports recommending various places like restaurants, shops, public facilities, and tourist attractions based on user queries.
Enables querying and analysis of Kakao Keyword Ads data, including campaigns, ad groups, keywords, and performance reports. Supports 21 read-only tools and 2 resources for accessing ad account information and metrics.
A server that enables AI models to access Kakao Map features (place search, address lookup, route finding) and Daum search services (web, image, blog, cafe) through Model Context Protocol.
An implementation of the Model Context Protocol that connects AI agents to Kakao Official Accounts, allowing users to send various message templates through the Kakao Developers API.
An MCP front-end for AnB. The tool surface is "use-don't-reveal": no tool returns a plaintext secret.
Reveal paths require a TTY the server doesn't have, so the no-reveal guarantee is structural, not
prompt-based — it holds even against a prompt-injected agent. Runs as a dedicated, narrowly-scoped AnB
identity; exec is default-deny (only allowlist rules tagged scope=mcp run); command output
A read-only kubectl MCP server for AI assistants. The kubectl verb is hardcoded in each tool
(get/describe/logs/events) and user input only fills argument values — no mutation path even with
malicious input, and Secret/ConfigMap values are never returned (metadata only). Returns structured
JSON, plus one-shot k8s_triage (health scan) and k8s_inventory (cluster snapshot).