Skip to main content
Glama
shaffe-fr

kiro-usage-mcp

by shaffe-fr
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

kiro-usage-mcp

An MCP server that reports your Kiro credit usage: plan, credits used and remaining, and the reset date.

It reads the output of kiro-cli chat --no-interactive "/usage", so it works with any account the Kiro CLI is logged into and needs no token of its own.

Requirements

  • Node.js 22.13 or later

  • Kiro CLI, installed and logged in (kiro-cli login)

  • pnpm, to build from source

Related MCP server: agent-usage

Install

git clone https://github.com/shaffe-fr/kiro-usage-mcp.git
cd kiro-usage-mcp
pnpm install
pnpm build

Configure

Add the server to your MCP client. For Kiro, edit ~/.kiro/settings/mcp.json (global) or .kiro/settings/mcp.json (workspace):

{
  "mcpServers": {
    "kiro-usage": {
      "command": "node",
      "args": ["/absolute/path/to/kiro-usage-mcp/dist/index.js"],
      "autoApprove": ["get_kiro_usage"]
    }
  }
}

The tool is read-only, so auto-approving it is safe. Any other MCP client that launches stdio servers works the same way.

If kiro-cli is not on the PATH of the process that starts the server, set KIRO_CLI_PATH to the executable:

"env": { "KIRO_CLI_PATH": "C:\\Users\\you\\AppData\\Local\\Kiro-Cli\\kiro-cli.exe" }

Tool

get_kiro_usage

Argument

Type

Description

refresh

boolean

Optional. Bypass the 30 second cache.

Returns a text summary:

KIRO POWER: 7483.87 of 10000 credits used (74.8%), 2516.13 remaining, resets 2026-11-01.

and the same data as structuredContent:

{
  "plan": "KIRO POWER",
  "resetsOn": "2026-11-01",
  "creditsUsed": 7483.87,
  "creditsTotal": 10000,
  "creditsRemaining": 2516.13,
  "percentUsed": 74.8,
  "addOnCreditsAvailableForPurchase": true
}

Limitations

  • Each probe starts a Kiro CLI chat session, which may leave an empty session in the CLI history. Results are cached for 30 seconds and concurrent calls share a single probe.

  • The server parses the CLI's human-readable output. If a Kiro release changes that format, the tool returns an error quoting the unexpected output rather than wrong numbers.

  • Overage and organisation-level allowances are not reported, because /usage does not show them.

Development

pnpm build   # compile to dist/
pnpm test    # compile and run the parser tests

License

MIT

Available Tools

1 tool
get_kiro_usageKiro credit usageA
Read-only

Returns the Kiro plan credits used, remaining and the reset date, read from kiro-cli /usage.

NameRequiredDescriptionDefault
refreshNoBypass the 30 second cache

Output Schema

NameRequiredDescription
planYes
resetsOnYes
creditsUsedYes
percentUsedYes
creditsTotalYes
creditsRemainingYes
addOnCreditsAvailableForPurchaseYes

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false. The description adds genuine value by disclosing the data source ('read from kiro-cli /usage'), which hints at latency and local dependency, but it does not mention the 30-second cache behavior that the schema parameter reveals.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One sentence, front-loaded with the verb and the returned data, with the data source appended. No filler.

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 explained, and the sole parameter is fully covered by the schema. The description is nearly complete for this simple read tool; only cache/staleness behavior is left implicit.

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

Parameters3/5

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

Schema description coverage is 100% and the single optional 'refresh' parameter is fully documented in the schema ('Bypass the 30 second cache'). The description adds nothing about it, so the baseline of 3 applies.

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 specific verb+resource ('Returns the Kiro plan credits') and even enumerates the returned fields (used, remaining, reset date). No siblings exist, so no differentiation is required, but the purpose is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied by the read-only 'Returns...' framing; there is no statement of when to call it, prerequisites, or alternatives. With no sibling tools the omission is minor, but no explicit guidance is given.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev0.1.0
    • First observedget_kiro_usage
Deploy Server
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

TDQS

A3.9/5.0

Scored across 1 tool

Disambiguation5/5

There is only one tool, so there is no possibility of confusion or misselection. Its purpose (fetch Kiro plan credit usage) is unambiguous.

Naming Consistency5/5

The single name get_kiro_usage follows a clear verb_noun convention with a domain-specific prefix. With only one tool there are no conflicting conventions to reconcile.

Tool Count4/5

The server's scope is narrow — reporting credit usage from kiro-cli — so a single tool is reasonable rather than thin. Slightly under-scoped only in that no optional parameters (e.g. history or date range) are offered.

Completeness4/5

The tool covers the core read operation fully: used, remaining, and reset date. There are no write or history operations, but those are arguably outside the stated reporting purpose.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers