Kiro MCP Server

Load a Kiro session

kiro_session_load

Idempotent

Resume a saved local or cloud session and attach it to this server, replaying history and returning a summary plus cursor for polling.

Instructions

Resume a saved local or cloud session (session/load) and attach it to this server, like kiro-cli chat --resume-id. Pass session_id, or latest: true with cwd for the most recently updated session in that workspace (--resume). Replayed history goes into the session's event feed marked replay; the result has a short replay summary and the cursor to poll from. Cloud sessions keep streaming, and approvals that were waiting are returned in pending_permissions.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "kiro_session_load"
  }
}

Input Schema

Name	Required	Description
`cwd`	No	Workspace directory inside KIRO_MCP_ROOTS.
`latest`	No
`session_id`	No	Kiro session id (sess_<uuid>).
`additional_directories`	No

Output Schema

Name	Required	Description	Default
`modes`	Yes
`cursor`	Yes
`source`	Yes
`commands`	Yes
`session_id`	Yes
`current_mode`	Yes
`context_usage`	Yes
`config_options`	Yes
`replay_summary`	Yes
`already_attached`	Yes
`execution_target`	Yes
`pending_permissions`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.1Nov 5, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Adds real behavior beyond the annotations: replayed history lands in the event feed marked replay, the result carries a replay summary plus a poll cursor, cloud sessions keep streaming, and waiting approvals surface in pending_permissions. It does not say what permissions or side effects attaching has, which is the remaining gap.

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?

Front-loaded with the action, then the two calling modes, then return behavior; every sentence carries information. It is dense but not padded, though the parenthetical CLI references add a little noise.

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 tool with an output schema, local/cloud branching and a streaming caveat, the description covers selection, replay semantics, the cursor, and pending permissions. Only the additional_directories parameter and the lack of any permissions note keep it from complete.

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?

With schema coverage at 50%, the description compensates by explaining the session_id path and the latest-plus-cwd pairing, which the schema leaves implicit. additional_directories is never mentioned, so one parameter still relies on the schema alone.

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 and resource ('Resume a saved local or cloud session (session/load) and attach it to this server') and anchors it to a CLI equivalent, which makes it unmistakable against siblings like kiro_session_new or kiro_session_list.

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 the two selection modes explicitly: pass session_id, or pass latest: true together with cwd for the most recently updated session in a workspace. It never names a sibling to avoid or a precondition, so it stops just short of full routing guidance.

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