KiroStats
Real-time credit usage and session tracking for Kiro IDE, reading from local state without auth or network.
README
KiroStats
Real-time credit usage and session tracking for Kiro IDE — as an MCP server.
No auth. No network. No cloud dependency. Reads directly from Kiro's local execution files.
What You Get
Three metrics, live from the same source that powers Kiro's "Est. Credits Used" display:
- Credits Used — exact per-turn credits from execution files
- Agent Time — cumulative time Kiro spent processing
- Session Time — total time since the chat started
Usage
Type /stats in any Kiro chat.
How It Works
Kiro persists every agent execution to disk as JSON files containing usageSummary[] arrays with exact per-turn credit values. KiroStats reads these files directly.
Data source:
%APPDATA%/Kiro/User/globalStorage/kiro.kiroagent/{workspace-hash}/{session-hash}/{execution-hash}
The single tool (get_session_stats) finds the running execution, groups all executions by chatSessionId, and returns aggregated credits and timing.
Install
git clone https://github.com/BrennanWebb/KiroStats.git
cd KiroStats
.\install.ps1
The installer:
- Pip-installs the MCP server package
- Registers it in
~/.kiro/settings/mcp.json - Creates a
/statssteering file for manual invocation
Restart Kiro after install.
Manual Install
pip install -e .
Add to ~/.kiro/settings/mcp.json:
{
"mcpServers": {
"kiro-stats": {
"command": "kiro-stats-mcp",
"autoApprove": ["get_session_stats"]
}
}
}
Copy .kiro/steering/stats.md from this repo to ~/.kiro/steering/.
Tool
| Tool | Returns |
|---|---|
get_session_stats |
credits_used, agent_time, session_time |
Supported Platforms
| OS | Kiro Data Path |
|---|---|
| Windows | %APPDATA%\Kiro\User\globalStorage\kiro.kiroagent\ |
| macOS | ~/Library/Application Support/Kiro/User/globalStorage/kiro.kiroagent/ |
| Linux | ~/.config/Kiro/User/globalStorage/kiro.kiroagent/ |
Requirements
- Python 3.10+
- Kiro IDE installed and opened at least once
Uninstall
pip uninstall kiro-stats-mcp
# Remove "kiro-stats" from ~/.kiro/settings/mcp.json
# Delete ~/.kiro/steering/stats.md
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.