Skip to content

Sampling Quota Guard

by textforagents.com · remote · no sign-in to list tools · v1.0.0 · published by com.textforagents

Per-server MCP sampling allowance, scope clamp and pre-connect verdict.

Changes · 4
CompareRegistry entry

4 tools: 4 change things.

Scanned Oct 22, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http sampling-quota-guard https://textforagents.com/products/sampling-quota-guard/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

4 tools

Changes things 4Claude Code: ask
  • guard_ledgerYour per-server sampling ledger rows (your operator only).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Your per-server sampling ledger rows (your operator only).
  • guard_meterMeter one sampling/createMessage request against your per-server ledger + fail-closed allowance + scope clamp.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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.
  • guard_policyYour allowance + tunable threshold policy.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Your allowance + tunable threshold policy.
  • guard_verdictPre-connect verdict (ALLOW / CAUTION / DENY / INSUFFICIENT_DATA) for one server from your own measured profile.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http sampling-quota-guard https://textforagents.com/products/sampling-quota-guard/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__sampling-quota-guard__guard_meter",
      "mcp__sampling-quota-guard__guard_verdict",
      "mcp__sampling-quota-guard__guard_ledger",
      "mcp__sampling-quota-guard__guard_policy"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as sampling-quota-guard. Review it before you use it.