Skip to main content
Glama

getBookmarks

Retrieve your saved bookmarks from Raindrop.io with customizable filters like tags, search, sorting, and pagination for efficient organization and access.

Instructions

Get bookmarks with optional filtering

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
collectionNoCollection ID
pageNoPage number
perPageNoItems per page (max 50)
searchNoSearch query
sortNoSort order
tagsNoFilter by tags

Implementation Reference

  • Core implementation of the getBookmarks method in RaindropService class. This is the function that executes the logic to fetch bookmarks from the Raindrop.io API using openapi-fetch client, supporting various query parameters like search, collection, tags, pagination, sorting, and filters.
    async getBookmarks(params: {
      search?: string;
      collection?: number;
      tags?: string[];
      important?: boolean;
      page?: number;
      perPage?: number;
      sort?: string;
      tag?: string;
      duplicates?: boolean;
      broken?: boolean;
      highlight?: boolean;
      domain?: string;
    } = {}): Promise<{ items: Bookmark[]; count: number }> {
      const query: any = {};
      if (params.search) query.search = params.search;
      if (params.tags) query.tag = params.tags.join(',');
      if (params.tag) query.tag = params.tag;
      if (params.important !== undefined) query.important = params.important;
      if (params.page) query.page = params.page;
      if (params.perPage) query.perpage = params.perPage;
      if (params.sort) query.sort = params.sort;
      if (params.duplicates !== undefined) query.duplicates = params.duplicates;
      if (params.broken !== undefined) query.broken = params.broken;
      if (params.highlight !== undefined) query.highlight = params.highlight;
      if (params.domain) query.domain = params.domain;
      const endpoint = params.collection ? '/raindrops/{id}' : '/raindrops/0';
      const options = params.collection
        ? { params: { path: { id: params.collection }, query } }
        : { params: { query } };
      const { data } = await (this.client as any).GET(endpoint, options);
      return {
        items: data?.items || [],
        count: data?.count || 0
      };
    }
  • MCP tool handler 'handleBookmarkSearch' (tool name: 'bookmark_search') that uses RaindropService.getBookmarks to perform bookmark search and returns MCP content links.
    async function handleBookmarkSearch(args: z.infer<typeof BookmarkSearchInputSchema>, { raindropService }: ToolHandlerContext) {
        const query: Record<string, unknown> = {};
        setIfDefined(query, 'search', args.search);
        setIfDefined(query, 'collection', args.collection);
        setIfDefined(query, 'tags', args.tags);
        setIfDefined(query, 'important', args.important);
        setIfDefined(query, 'page', args.page);
        setIfDefined(query, 'perPage', args.perPage);
        setIfDefined(query, 'sort', args.sort);
        setIfDefined(query, 'tag', args.tag);
        setIfDefined(query, 'duplicates', args.duplicates);
        setIfDefined(query, 'broken', args.broken);
        setIfDefined(query, 'highlight', args.highlight);
        setIfDefined(query, 'domain', args.domain);
    
        const result = await raindropService.getBookmarks(query as any);
    
        const content: McpContent[] = [textContent(`Found ${result.count} bookmarks`)];
        result.items.forEach((bookmark: any) => {
            content.push(makeBookmarkLink(bookmark));
        });
    
        return { content };
    }
  • MCP tool handler 'handleListRaindrops' (tool name: 'listRaindrops') that uses RaindropService.getBookmarks to list bookmarks in a specific collection.
    async function handleListRaindrops(args: z.infer<typeof ListRaindropsInputSchema>, { raindropService }: ToolHandlerContext) {
        const result = await raindropService.getBookmarks({
            collection: parseInt(args.collectionId),
            perPage: args.limit || 50,
        });
    
        const content: McpContent[] = [textContent(`Found ${result.count} bookmarks in collection`)];
        result.items.forEach((bookmark: any) => content.push(makeBookmarkLink(bookmark)));
    
        return { content };
    }
  • Input schema (BookmarkSearchInputSchema) for the bookmark_search MCP tool, matching the parameters accepted by getBookmarks.
    const BookmarkSearchInputSchema = z.object({
        search: z.string().optional().describe('Full-text search query'),
        collection: z.number().optional().describe('Collection ID to search within'),
        tags: z.array(z.string()).optional().describe('Tags to filter by'),
        important: z.boolean().optional().describe('Filter by important bookmarks'),
        page: z.number().optional().describe('Page number for pagination'),
        perPage: z.number().optional().describe('Items per page (max 50)'),
        sort: z.string().optional().describe('Sort order (score, title, -created, created)'),
        tag: z.string().optional().describe('Single tag to filter by'),
        duplicates: z.boolean().optional().describe('Include duplicate bookmarks'),
        broken: z.boolean().optional().describe('Include broken links'),
        highlight: z.boolean().optional().describe('Only bookmarks with highlights'),
        domain: z.string().optional().describe('Filter by domain'),
    });
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'optional filtering' but doesn't explain key behaviors like pagination (implied by 'page' and 'perPage' parameters), rate limits, authentication needs, or what happens when no filters are applied. For a read operation with multiple parameters, this leaves significant gaps in understanding how the tool behaves.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that front-loads the core purpose ('Get bookmarks') and adds a qualifier ('with optional filtering'). There's no wasted text, making it appropriately concise. However, it could be more structured by explicitly stating it's for listing or retrieving multiple bookmarks.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations, no output schema, and 6 parameters, the description is incomplete. It doesn't explain the tool's behavior (e.g., pagination, filtering logic), return values, or how it differs from siblings like 'searchBookmarks'. For a tool with this complexity and lack of structured data, the description should provide more context to guide effective use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 6 parameters with descriptions and enums for 'sort'. The description adds no additional meaning beyond implying filtering capabilities, which the schema already covers via parameters like 'search', 'tags', and 'collection'. Baseline 3 is appropriate as the schema does the heavy lifting, but the description doesn't compensate or enhance parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Get bookmarks with optional filtering' clearly states the verb ('Get') and resource ('bookmarks'), and mentions optional filtering. However, it doesn't distinguish this tool from sibling tools like 'searchBookmarks' or 'getBookmark', leaving ambiguity about when to use each. The purpose is understandable but lacks sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. With siblings like 'searchBookmarks' and 'getBookmark' available, there's no indication of whether this tool is for listing all bookmarks, filtered searches, or other use cases. The mention of 'optional filtering' is vague and doesn't clarify context or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

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/adeze/raindrop-mcp'

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