costwright — agent budget analysis runs on your own machine — the client starts it, so there is no endpoint to ping. 43 installs a week from npm. Last commit 30 Jun 2026.
Static worst-case token-budget analysis for LLM-agent workflows + signed budget certificates.
We read the source, 22 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
import { readdirSync, lstatSync, readFileSync } from "node:fs";
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add costwright-mcp -- npx -y costwright-mcp
{
"mcpServers": {
"costwright-mcp": {
"args": [
"-y",
"costwright-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.costwright-mcp]
command = "npx"
args = ["-y", "costwright-mcp"]
{
"mcpServers": {
"costwright-mcp": {
"args": [
"-y",
"costwright-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"costwright-mcp": {
"args": [
"-y",
"costwright-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
COSTWRIGHT_API_KEY (API key for costwright (RapidAPI key or direct Bearer). Only needed for check/certify; verify/pubkey are public.).
The author declared them in the registry entry; get the values from the project itself.
Pre-execution cost estimation for LLM agent workflows with calibration learning
Verification and memory layer for coding-agent workflows.
Go code coverage analysis tool with MCP server for AI-powered coverage workflows
Go code coverage analysis tool with MCP server for AI-powered coverage workflows
Real-time cost awareness for MCP agent workflows
Shared versioned state for multi-agent AI workflows
Workflow timing analysis, configuration audit and billing insight for GitHub Actions.
Measures the cost, tokens and duration of a completed agent workflow from its session log.
Answers built from our own checks of this server.