Kiro MCP Server

Kiro knowledge bases

kiro_knowledge

Manage Kiro knowledge bases by adding, searching, updating, removing, or clearing indexed paths and checking job status, so coding sessions can reuse project context.

Instructions

Kiro knowledge bases (_kiro/knowledge), like /knowledge: show, add (a path inside KIRO_MCP_ROOTS), remove, search, update, clear, status, cancel. Returns Kiro's success, message, and data; success false is KIRO_REFUSED.

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": {
      "session_id": "<session_id>",
      "subcommand": "<subcommand>"
    },
    "name": "kiro_knowledge"
  }
}

Input Schema

Name	Required	Description
`name`	No
`path`	No	For add and update: a file or directory inside KIRO_MCP_ROOTS.
`query`	No
`exclude`	No
`include`	No
`context_id`	No
`session_id`	Yes	Kiro session id (sess_<uuid>).
`subcommand`	Yes

Output Schema

Name	Required	Description	Default
`data`	Yes
`message`	Yes
`success`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.1Nov 5, 2026

TDQS

C2.4/5.0

Behavior2/5

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

The description usefully discloses the return envelope (success, message, data) and the error sentinel (success false = KIRO_REFUSED), plus the KIRO_MCP_ROOTS sandbox for add/update. But it lists 'remove' and 'clear' as capabilities while annotations declare destructiveHint=false, which understates the blast radius of those subcommands. It also never says which subcommands are irreversible or whether removal is undoable.

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?

Two tight sentences with the resource front-loaded and the return contract at the end; nothing is padded. The compression is slightly over-aggressive — cramming eight subcommands into a comma list with a '/knowledge:' analogy costs clarity — but the size and ordering are appropriate.

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?

An output schema exists, so return values need not be detailed, and the description is fine on that front. But an eight-subcommand dispatcher with eight parameters needs at minimum a mapping of required parameters per subcommand; without it an agent cannot reliably invoke 'add' vs 'update' vs 'search'. This is the dominant gap in an otherwise reasonably scoped definition.

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

Parameters2/5

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

Schema description coverage is only 25% — only 'path' and 'session_id' are documented in the schema. The description reinforces the path constraint but says nothing about name, query, include, exclude, or context_id, and critically never maps parameters to subcommands (e.g., that 'query' belongs to search, that 'name' identifies the base for remove/update/clear). With six of eight parameters undocumented anywhere, the description fails to compensate.

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 identifies the resource (Kiro knowledge bases at _kiro/knowledge) and enumerates eight subcommands, which differentiates it from siblings like kiro_memory or kiro_specs. However, the subcommands are listed as bare verbs with no objects — an agent learns that 'show', 'add', and 'clear' exist but not what any of them operate on or return. That makes the purpose recognizable but not well-defined.

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?

There is no guidance on when to use this tool versus kiro_memory or kiro_specs, and no indication of which subcommand suits which intent. The only usage rule given is a constraint ('add a path inside KIRO_MCP_ROOTS'), not a when-to-use rule. The agent must infer the entire selection logic from subcommand names.

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