Bocha Search
Bocha Search MCP provides integration with Bocha, a Chinese search engine for AI, enabling AI assistants to perform web searches and retrieve enhanced search details from billions of documents. Developed by kunkun, this Python-based server implementation offers two primary tools: bocha_web_search for retrieving standard search results including titles, URLs, summaries, and publication dates; and bocha_ai_search for semantic search with additional structured modal cards from vertical domains like weather, news, wikis, healthcare, and more. The server requires a Bocha API key and handles authentication, request formatting, and error handling, making it particularly useful for applications needing multilingual search capabilities with rich structured data.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- security
- Source
- PulseMCP
- Repository
- github.com/bochaai/bocha-search-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Bocha Search from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp --scope user for --scope project to commit it to .mcp.json.