Skip to main content
Glama

search_readwise_highlights

Search and retrieve saved highlights from Readwise using vector and full-text queries. Enables AI assistants to access and analyze your reading content based on specific criteria like author, title, tags, notes, or text.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
full_text_queriesYes
vector_search_termYes

Implementation Reference

  • The handler function for the 'search_readwise_highlights' tool. It sends the input payload to the backend API endpoint '/api/mcp/highlights' via axios and returns the results as a JSON-stringified text block.
    async (payload) => { const response = await this.axios.post("/api/mcp/highlights", payload); return {content: [{type: "text", text: JSON.stringify(response.data.results)}]}; }
  • Zod input schema defining 'vector_search_term' as string and 'full_text_queries' as an array (max 8) of objects with 'field_name' (enum of highlight fields) and 'search_term'.
    { vector_search_term: z.string(), full_text_queries: z.array( z.object({ field_name: z.enum([ "document_author", "document_title", "highlight_note", "highlight_plaintext", "highlight_tags", ]), search_term: z.string(), }), ).max(8), },
  • src/index.ts:58-79 (registration)
    Registration of the 'search_readwise_highlights' tool on the McpServer instance, including name, input schema, and inline handler function.
    this.server.tool( "search_readwise_highlights", { vector_search_term: z.string(), full_text_queries: z.array( z.object({ field_name: z.enum([ "document_author", "document_title", "highlight_note", "highlight_plaintext", "highlight_tags", ]), search_term: z.string(), }), ).max(8), }, async (payload) => { const response = await this.axios.post("/api/mcp/highlights", payload); return {content: [{type: "text", text: JSON.stringify(response.data.results)}]}; } );

Other Tools

Related Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/readwiseio/readwise-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server