For the complete documentation index, see llms.txt. This page is also available as Markdown.

kb_search

Retrieve ranked chunks from one knowledge base. query_strategy is semantic (default), keyword or hybrid. top_k defaults to 5 and caps at 20.

Effect: This call reads data and does not run or change a project.

Inputs

Name
Type
Requirement
Description

kb_id

string

Required

Knowledge base ID from kb_list.

query

string

Required

Nonempty question or search text, at most 2000 characters.

top_k

integer

Optional

Maximum chunks returned: default 5; allowed range 1–20.

query_strategy

semantic, keyword, or hybrid

Optional

Default semantic. keyword matches terms; hybrid combines both approaches.

expand

array of strings

Optional

Up to 20 returned chunk IDs whose full text to include.

Example

These are MCP tool arguments, not an HTTP request body. Replace bracketed IDs with values returned from your account.

{
  "kb_id": "<knowledge-base-id>",
  "query": "What is the approval process?",
  "top_k": 5
}

Result

Abbreviated result example; unshown fields are omitted for clarity.

Behavior

Results contain previews and document/locator metadata, not a synthesized answer.

Repeat the query with expand set to selected chunk IDs (up to 20) to obtain full text where available; check text_truncated before relying on completeness.

Troubleshooting

If an answer needs more evidence, repeat the same query with selected chunk IDs in expand. Check text_truncated; an empty or partial result does not establish that the source contains no relevant information.

Connections, knowledge and discovery

Connection, permissions, pagination, and recovery

Was this helpful?