Skip to main content
Glama
Karakeep MCP server

Karakeep MCP server

by karakeep-app

search-bookmarks

Search bookmarks using full-text, semantic, or hybrid queries with qualifiers to filter by tags, lists, dates, type, or favorites, and sort by relevance or creation date.

Instructions

Search for bookmarks matching a specific query using full-text, semantic, or hybrid search.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search-bookmarks"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoThe number of results to return in a single query.
queryYes By default, this will do a full-text search, but you can also use qualifiers to filter the results. You can search bookmarks using specific qualifiers. is:fav finds favorited bookmarks, is:archived searches archived bookmarks, is:tagged finds those with tags, is:inlist finds those in lists, and is:link, is:text, and is:media filter by bookmark type. url:<value> searches for URL substrings, #<tag> searches for bookmarks with a specific tag, list:<name> searches for bookmarks in a specific list given its name (without the icon), after:<date> finds bookmarks created on or after a date (YYYY-MM-DD), and before:<date> finds bookmarks created on or before a date (YYYY-MM-DD). If you need to pass names with spaces, you can quote them with double quotes. If you want to negate a qualifier, prefix it with a minus sign. ## Examples: ### Find favorited bookmarks from 2023 that are tagged "important" is:fav after:2023-01-01 before:2023-12-31 #important ### Find archived bookmarks that are either in "reading" list or tagged "work" is:archived and (list:reading or #work) ### Combine text search with qualifiers machine learning is:fav
sortOrderNoSort by relevance or creation date. Defaults to relevance.
nextCursorNoThe next cursor to use for pagination. The value for this is returned from a previous call to this tool.
searchModeNoSearch strategy. 'fts' uses full-text search, 'semantic' uses embeddings, and 'hybrid' combines both. Semantic and hybrid modes only support relevance sorting. Defaults to 'fts'.fts

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.35.0
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. Changed2 schema fields changedv0.33.1
    • addedInput schema / properties / searchMode
      Added value: +{
      +  "default": "fts",
      +  "description": "Search strategy. 'fts' uses full-text search, 'semantic' uses embeddings, and 'hybrid' combines both. Semantic and hybrid modes only support relevance sorting. Defaults to 'fts'.",
      +  "enum": [
      +    "fts",
      +    "semantic",
      +    "hybrid"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / sortOrder
      Added value: +{
      +  "description": "Sort by relevance or creation date. Defaults to relevance.",
      +  "enum": [
      +    "asc",
      +    "desc",
      +    "relevance"
      +  ],
      +  "type": "string"
      +}
  3. Changed4 schema fields changedv1.0.1
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / limit
      Added value: +{
      +  "default": 10,
      +  "description": "The number of results to return in a single query.",
      +  "type": "number"
      +}
    • addedInput schema / properties / nextCursor
      Added value: +{
      +  "description": "The next cursor to use for pagination. The value for this is returned from a previous call to this tool.",
      +  "type": "string"
      +}
    • changedInput schema / properties / query / description
      Previous value: -"\n    By default, this will do a full-text search, but you can also use qualifiers to filter the results.\nYou can search bookmarks using specific qualifiers. is:fav finds favorited bookmarks,\nis:archived searches archived bookmarks, is:tagged finds those with tags,\nis:inlist finds those in lists, and is:link, is:text, and is:media filter by bookmark type.\nurl:<value> searches for URL substrings, #<tag> searches for bookmarks with a specific tag,\nlist:<name> searches for bookmarks in a specific list,\nafter:<date> finds bookmarks created on or after a date (YYYY-MM-DD), and before:<date> finds bookmarks created on or before a date (YYYY-MM-DD).\nIf you need to pass names with spaces, you can quote them with double quotes. If you want to negate a qualifier, prefix it with a minus sign.\n## Examples:\n\n### Find favorited bookmarks from 2023 that are tagged \"important\"\nis:fav after:2023-01-01 before:2023-12-31 #important\n\n### Find archived bookmarks that are either in \"reading\" list or tagged \"work\"\nis:archived and (list:reading or #work)\n\n### Combine text search with qualifiers\nmachine learning is:fav"New value: +"\n    By default, this will do a full-text search, but you can also use qualifiers to filter the results.\nYou can search bookmarks using specific qualifiers. is:fav finds favorited bookmarks,\nis:archived searches archived bookmarks, is:tagged finds those with tags,\nis:inlist finds those in lists, and is:link, is:text, and is:media filter by bookmark type.\nurl:<value> searches for URL substrings, #<tag> searches for bookmarks with a specific tag,\nlist:<name> searches for bookmarks in a specific list given its name (without the icon),\nafter:<date> finds bookmarks created on or after a date (YYYY-MM-DD), and before:<date> finds bookmarks created on or before a date (YYYY-MM-DD).\nIf you need to pass names with spaces, you can quote them with double quotes. If you want to negate a qualifier, prefix it with a minus sign.\n## Examples:\n\n### Find favorited bookmarks from 2023 that are tagged \"important\"\nis:fav after:2023-01-01 before:2023-12-31 #important\n\n### Find archived bookmarks that are either in \"reading\" list or tagged \"work\"\nis:archived and (list:reading or #work)\n\n### Combine text search with qualifiers\nmachine learning is:fav"
  4. First observed

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full behavioral burden and adds essentially nothing beyond the title. It does not disclose whether archived bookmarks are included by default, whether results are paginated, how relevance ranking works, or what fields are returned.

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?

A single front-loaded sentence with no wasted words, but its brevity is closer to under-specification than to tight editing given the tool's complexity.

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

Completeness3/5

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

With five parameters, no output schema, and no annotations, an agent still lacks any sense of the return shape or default filtering behavior. The rich schema compensates for parameter detail, keeping this at minimum viable rather than inadequate.

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% and the query parameter documents the qualifier syntax with worked examples, so the schema does the heavy lifting. The description's only parameter-adjacent content restates the searchMode enum values, adding no meaning beyond the structured field.

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

Purpose4/5

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

States a specific verb (search) and resource (bookmarks), plus the three available strategies (full-text, semantic, hybrid). It is clearly distinct from retrieval siblings like get-bookmark or get-list-bookmarks, though it never explicitly says so.

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?

No guidance on when to use this versus get-bookmark, get-list-bookmarks, or get-tag-bookmarks, nor when to prefer one search mode over another. The mention of fts/semantic/hybrid is a capability list rather than usage direction, and mode-selection guidance lives only in the schema.

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