Skip to main content
Glama
kimi-search-mcp
by Wildare-98

Kimi Web Search Basic

kimi_search

Search the web for titles, URLs, snippets, dates, and source authority, with optional full page text for deeper research.

Instructions

Search the web with Kimi Search Basic. Returns titles, URLs, snippets, dates, and source authority. Keep include_content=false for an overview, then use kimi_fetch on selected URLs, or set it to true when full page text is needed.

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": {
      "text_query": "<text_query>"
    },
    "name": "kimi_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum number of results, 1-20. Default 5.
text_queryYesSearch query. Include specific entities, dates, and source constraints when relevant.
include_contentNoInclude full page text in each result. Prefer false for initial searches.
timeout_secondsNoKimi API search timeout in seconds, 1-60. Default 30.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.8/5.0
Behavior3/5

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

No annotations exist, so the description carries the full disclosure burden. It does add real value by describing the result shape (including 'source authority' and dates) and the cost/volume tradeoff implicit in include_content. It says nothing about rate limits, authentication, result ordering, or what happens on timeout, which matter for an unannotated network tool.

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?

Three sentences, front-loaded with purpose, then return shape, then the parameter decision. Every sentence carries content; the only minor waste is restating the tool's own name in the opening clause.

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

Completeness4/5

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

For a four-parameter search tool with no output schema, the definition covers purpose, return fields, and the key parameter tradeoff adequately. The remaining gap is sibling positioning against kimi_search_pro rather than any missing invocation detail.

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%, so the baseline is 3. The description goes beyond the schema for include_content by framing it as an overview-vs-full-text workflow decision tied to kimi_fetch, adding operational meaning the boolean alone does not convey.

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 and resource ('Search the web with Kimi Search Basic') and enumerates what comes back: titles, URLs, snippets, dates, source authority. It distinguishes itself from kimi_fetch via the workflow hint, but gives no signal about how it differs from the sibling kimi_search_pro, so an agent choosing between the two search tools gets no help here.

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

Usage Guidelines4/5

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

Gives a clear conditional workflow: keep include_content=false for an overview, follow up with kimi_fetch on selected URLs, or set true when full page text is needed. That is usable when-to-use guidance with a named alternative, but it omits any guidance on when to prefer kimi_search_pro over this basic search.

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

Deploy Server

Other Tools