Skip to main content
Glama
real-jiakai

kagi-mcp-gpt-5.6-sol-ultra

by real-jiakai

Search Kagi

kagi_search
Read-only

Retrieve ranked organic web search results from a signed-in Kagi account using optional lenses, pagination, region, and time filters. Returns snippets for each result.

Instructions

Search the signed-in user's Kagi account and return ranked organic results with Kagi-provided search snippets. The default returns one full 20-result lightweight page. Destination pages are not opened or fetched; paginate explicitly when more results are needed.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
lensNoOptional Kagi Lens. Use a known name such as forums, programming, academic, news_360, recipes, small_web, or a numeric ID returned by kagi_list_lenses. The Lens must be active in Kagi settings.
pageNoKagi result page. Start at 1 and paginate only when needed.
sortNoResult ordering. Use recency for time-sensitive research.relevance
limitNoMaximum number of ranked organic results to return. The default returns Kagi's full lightweight HTML result page; lower it when context should be smaller.
queryYesThe web search query. Kagi operators such as site:example.com may be included.
regionNoKagi region code. Defaults to no_region (International); use a lowercase ISO country code such as us, gb, cn, or jp, or a locale variant such as ca_fr.no_region
verbatimNoMatch the query text more literally when true.
time_rangeNoOptional relative publication-time filter.any

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageYesCurrent Kagi result page, starting at 1.
queryYesThe submitted search query.
cachedYesWhether this response was served from the local memory cache.
filtersYes
hasMoreYesWhether Kagi exposed a link to another upstream result page.
resultsYesRanked organic search results.
returnedYesNumber of result objects returned to the caller.
elapsedMsNoSearch time reported by Kagi, in milliseconds.
truncatedYesTrue only when limit omitted some recognized results from this page.
contentScopeYesSignals that snippets came from Kagi's result page; destination pages were not fetched.
totalEstimateNoApproximate relevant-result count reported by Kagi.
relatedQueriesYesRelated searches displayed by Kagi.
pageResultCountYesNumber of recognized organic result cards on this Kagi lightweight page before applying limit.
Behavior5/5

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

Annotations indicate readOnlyHint=true, openWorldHint=true, destructiveHint=false. The description adds context: no page fetching, explicit pagination, and that results are snippets. No contradictions.

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

Conciseness5/5

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

The description is three sentences, front-loaded with purpose, and every sentence provides essential information without fluff.

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

Completeness5/5

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

Given the output schema exists (not shown but indicated), the description covers all needed context: search scope, result format, pagination, and that pages are not fetched. It is complete for a search tool.

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

Parameters4/5

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

Schema coverage is 100% with all parameters described. The description adds value by providing examples for the query parameter ('Kagi operators such as site:example.com may be included') and clarifying default behavior for limit and page.

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

Purpose5/5

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

The description clearly states the verb 'Search', the resource 'signed-in user's Kagi account', and what is returned ('ranked organic results with Kagi-provided search snippets'). It distinguishes from the sibling tool 'kagi_list_lenses' which lists lenses.

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

Usage Guidelines5/5

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

The description gives explicit guidance: 'Destination pages are not opened or fetched; paginate explicitly when more results are needed.' It also explains the default behavior ('one full 20-result lightweight page') and implies the tool is for searching, not other actions.

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

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/real-jiakai/kagi-mcp-gpt-5.6-sol-ultra'

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