Kiro MCP Server

Kiro session transcript

kiro_session_history

Read-onlyIdempotent

Read a Kiro session transcript page by page with cursor and limit, and list rewind points (message id, turn number, prompt preview) so you can fork the session back to a chosen user message.

Instructions

Read a session's transcript (_kiro/session/history), paged with cursor and limit, like /transcript. Falls back to this server's event feed when Kiro returns no history. rewind_points lists each user message id with its turn number and a prompt preview: pass one as message_id to kiro_session_fork to rewind.

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>"
    },
    "name": "kiro_session_history"
  }
}

Input Schema

Name	Required	Description
`limit`	No
`cursor`	No
`session_id`	Yes	Kiro session id (sess_<uuid>).

Output Schema

Name	Required	Description	Default
`source`	Yes
`entries`	Yes
`has_more`	Yes
`session_id`	Yes
`next_cursor`	Yes
`rewind_points`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.1Nov 5, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, and openWorld, so the safety profile is covered. The description adds meaningful behavior beyond that: a documented fallback path when no history exists, and the fact that the response carries rewind_points with turn numbers and prompt previews. It does not describe ordering or error behavior.

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 tight sentences with the core read action front-loaded, followed by fallback behavior and the cross-tool rewind hint. The trailing rewind_points sentence is dense but earns its place by linking to kiro_session_fork.

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?

An output schema exists, so return values needn't be spelled out, and the description usefully flags the rewind_points member that matters for follow-up actions. The main remaining gap is pagination semantics for cursor and limit against a schema that under-documents them.

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 33% - only session_id is documented in the schema, while cursor and limit carry just numeric bounds. The description says the result is 'paged with cursor and limit' but never explains what a cursor value means or what the default page size is, so it does not compensate for the coverage gap.

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?

States a specific verb (Read) and resource (a session's transcript at _kiro/session/history) and anchors it against a familiar equivalent (/transcript). This clearly separates it from siblings such as kiro_session_state, kiro_session_load, and kiro_events.

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 real routing context: it explains the fallback to the server's event feed when Kiro returns no history, and it explicitly routes the agent to kiro_session_fork when it wants to rewind from a rewind_point. It stops short of stating when to prefer kiro_events or kiro_session_state directly, so it is not fully exhaustive.

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