Pre-spend firewall for AI agents. Approves, blocks, flags transactions against policy rules.
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.
Add a rule to the authenticated API key's isolated workspace.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Add a rule to the authenticated API key's isolated workspace.
| Argument | Type | Description |
|---|---|---|
| label | string | |
| action | string | |
| params* | object | |
| priority | integer |
| rule_type* | string |
{
"type": "object",
"required": [
"rule_type",
"params"
],
"properties": {
"label": {
"type": "string"
},
"action": {
"type": "string"
},
"params": {
"type": "object"
},
"priority": {
"type": "integer"
},
"rule_type": {
"type": "string"
}
}
}Check whether an autonomous agent is allowed to make a purchase BEFORE spending. Returns APPROVED, BLOCKED, or FLAGGED.
| Argument | Type | Description |
|---|---|---|
| amount* | number | |
| category | string | |
| merchant | string | |
| description | string |
{
"type": "object",
"required": [
"amount"
],
"properties": {
"amount": {
"type": "number"
},
"category": {
"type": "string"
},
"merchant": {
"type": "string"
},
"description": {
"type": "string"
}
}
}Get private firewall stats for the authenticated API key.
No arguments.
{
"type": "object"
}