Sampling Quota Guard
Per-server MCP sampling allowance, scope clamp and pre-connect verdict.
Should I use this
Quality & Safety
Findings (1)
- LOWTool 'guard_ledger' description lacks action verbin guard_ledger
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"sampling-quota-guard": {
"url": "https://textforagents.com/products/sampling-quota-guard/mcp"
}
}
}Remote endpoints
https://textforagents.com/products/sampling-quota-guard/mcpstreamable-httpWhat it can do
Tool inventory
Tools (4)
⚪guard_meter(server, request)
Meter one sampling/createMessage request against your per-server ledger + fail-closed allowance + scope clamp. Billed per the pricing sheet (flat coverage, then $0.002 x402). Denied requests never consume allowance.
Input Schema
{
"type": "object",
"properties": {
"server": {
"type": "string"
},
"request": {
"type": "object"
}
},
"required": [
"server",
"request"
]
}⚪guard_verdict(server)
Pre-connect verdict (ALLOW / CAUTION / DENY / INSUFFICIENT_DATA) for one server from your own measured profile. First 100 verdicts free one time per operator; then $0.005 x402; flat tier covers verdicts.
Input Schema
{
"type": "object",
"properties": {
"server": {
"type": "string"
}
},
"required": [
"server"
]
}⚪guard_ledger(server)
Your per-server sampling ledger rows (your operator only).
Input Schema
{
"type": "object",
"properties": {
"server": {
"type": "string"
}
}
}⚪guard_policy
Your allowance + tunable threshold policy.
Input Schema
{
"type": "object",
"properties": {}
}Community
Evidence