Kiro MCP Server

Kiro cloud source providers

kiro_cloud_sources

Read-onlyIdempotent

Lists connected cloud source providers or a provider's repositories, helping you select owner/name repos for cloud sessions.

Instructions

Connected source providers for cloud sessions (_kiro/sourceProviders/list), or, with provider (for example GITHUB), that provider's repositories (_kiro/sourceProviders/listResources). Use the owner/name values as repos for kiro_session_new with execution_target cloud.

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_cloud_sources"
  }
}

Input Schema

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

Output Schema

Name	Required	Description	Default
`providers`	Yes
`resources`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.1Nov 5, 2026

TDQS

A3.8/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds the meaningful behavioral fact that results depend on which providers are *connected* and that the output feeds kiro_session_new, but it does not state permissions needed, whether credential connection must be done elsewhere, or any failure behavior for an unconnected provider.

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?

One dense sentence that front-loads the primary mode and then the parameterized variant, closing with the actionable downstream tip. Parenthetical RPC paths are slightly noisy but compact and do add precision.

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?

With an output schema present, return values need not be described, and the description covers the mode switch, parameter intent, and next step. What remains thin is prerequisites (must a provider already be connected?) and the exact shape of owner/name values, which is only implied by the kiro_session_new pointer.

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 only 50% — session_id is documented, but 'provider' carries just a regex. The description compensates by explaining that 'provider' switches the tool into a repo-listing mode and giving GITHUB as an example, which also conveys the uppercase enumeration format the pattern demands.

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 concrete verb+resource pair and distinguishes its two modes: without 'provider' it lists source providers, with 'provider' (e.g. GITHUB) it lists that provider's repositories. The internal RPC names (_kiro/sourceProviders/list vs listResources) reinforce which branch does what, but it does not contrast itself against siblings that also enumerate session-adjacent data.

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?

Explicitly tells the agent when to pass 'provider' versus omit it, and frames the downstream step: use the returned owner/name values as repos for kiro_session_new with execution_target cloud. It gives no when-not guidance or alternative listing tool, so it stops 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.