
Flag mid-project scope changes and draft a priced change-order reply. Not legal advice.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Flag whether a client request is in scope, out of scope, or unclear, estimate a price, and draft a polite change-order reply. Not legal advice. Reuses ChangeOrder's deterministic keyword classifier (not an LLM).
Hourly rate in USD.
The signed scope of work, one item per line or semicolon-separated.
The client's new request.
If true, apply a 50% rush surcharge.
Estimated hours for the extra work. Defaults to 4.
Client name for the greeting. Optional.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http changeorder https://changeorder.dailydrop-jc.workers.dev/mcp
Flag whether a client request is in scope, out of scope, or unclear, estimate a price, and draft a polite change-order reply. Not legal advice. Reuses ChangeOrder's deterministic keyword classifier (not an LLM).
| Argument | Type | Description |
|---|
| rate* | number | Hourly rate in USD. |
| rush | boolean | If true, apply a 50% rush surcharge. |
| hours | number | Estimated hours for the extra work. Defaults to 4. |
| scope* | string | The signed scope of work, one item per line or semicolon-separated. |
| client | string | Client name for the greeting. Optional. |
| request* | string | The client's new request. |
{
"type": "object",
"required": [
"scope",
"request",
"rate"
],
"properties": {
"rate": {
"type": "number",
"description": "Hourly rate in USD."
},
"rush": {
"type": "boolean",
"description": "If true, apply a 50% rush surcharge."
},
"hours": {
"type": "number",
"description": "Estimated hours for the extra work. Defaults to 4."
},
"scope": {
"type": "string",
"description": "The signed scope of work, one item per line or semicolon-separated."
},
"client": {
"type": "string",
"description": "Client name for the greeting. Optional."
},
"request": {
"type": "string",
"description": "The client's new request."
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 10, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.