← sipi.bot
INDIVIDUAL MCP TOOL
evaluate_spend
Check whether an autonomous agent is allowed to make a purchase BEFORE spending.
Input schema
{}Risk classification
Potential side effects detected · medium confidence · heuristic, not a guarantee.
- A tool name or description suggests a financial action.
Parent endpoint
CONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.sipibot-mcp]
url = "https://sipi.bot/api/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"sipibot-mcp": {
"type": "http",
"url": "https://sipi.bot/api/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: sipibot-mcp
Remote MCP URL: https://sipi.bot/api/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"sipibot-mcp": {
"url": "https://sipi.bot/api/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"sipibot-mcp": {
"type": "http",
"url": "https://sipi.bot/api/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "sipibot-mcp",
"transport": "streamable-http",
"url": "https://sipi.bot/api/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
Related tools
add_spend_rule— Add a spend policy rule.firewall_status— Get current firewall stats: spend approved/blocked today, pending approvals, active agents.