collection.search — api MCP Tool
collection.search
(collection search) is one of 22 tools on the
api
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call collection.search from your client
- Claude Code api collection.search run in your project directory
- Claude Desktop api collection.search ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor api collection.search ~/.cursor/mcp.json
- VS Code api collection.search .vscode/mcp.json
- Zed api collection.search ~/.config/zed/settings.json
- Windsurf api collection.search ~/.codeium/windsurf/mcp_config.json
- Cline api collection.search ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI api collection.search ~/.gemini/settings.json
- Grok api collection.search .mcp.json (in your project root)
- ChatGPT api collection.search Settings → Connectors → Advanced → Developer mode
- Claude.ai api collection.search Settings → Connectors → Add custom connector
- LangChain api collection.search pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http api https://api.docimprint.com/mcpOther tools on this server
- document.extract_text
- document.extract_tables
- document.parse_invoice
- document.check_claims
- document.extract_structured
- document.summarize
- bundle.verify
- collection.create
- collection.ask
- url.extract
- url.summarize
- url.qa
- url.translate
- bundle.get
- bundle.notarize
- receipt.verify
- receipt.list
- job.status
- collection.list
- collection.add_document
- account.quota
This list was read from the server itself, by connecting to it and calling tools/list on 24 September 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.