Skip to content

Ban Bulkheads — Reputation Firebreaks for Agent Fleets

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

Partition an agent fleet into reputation compartments with automatic firebreaks.

Changes · 8
CompareRegistry entry

9 tools: 8 change things and 1 only read.

Scanned Oct 21, 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 ban-bulkheads-reputation-firebreaks https://textforagents.com/products/ban-bulkheads-reputation-firebreaks/mcp

Tools

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

9 tools

Changes things 8Claude Code: ask
  • add_jobRegister an in-flight job {compartment, job_id, clean}No findings

    Why it is in this group

    • The name "add_job" says "add": a word for a change.
    Description, as the server wrote it
    Register an in-flight job {compartment, job_id, clean}
  • assign_agentAssign an agent to a compartment {agent, compartment}No findings

    Why it is in this group

    • The name "assign_agent" says "assign": a word for a change.
    Description, as the server wrote it
    Assign an agent to a compartment {agent, compartment}
  • create_compartmentCreate a reputation compartment {task_class} (plan slot required)No findings

    Why it is in this group

    • The name "create_compartment" says "create": a word for a change.
    Description, as the server wrote it
    Create a reputation compartment {task_class} (plan slot required)
  • freeze_compartmentFreeze a compartment {compartment}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
    Freeze a compartment {compartment}
  • penalty_signalIntake an account-level penalty signal {kind}; attribution comes from baselines onlyNo 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
    Intake an account-level penalty signal {kind}; attribution comes from baselines only
  • readmitRe-admission probes {compartment, probes}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
    Re-admission probes {compartment, probes}
  • receiptsIncident receipt chain + validityNo 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
    Incident receipt chain + validity
  • record_outcomeRecord an outcome {compartment, outcome, job_id?, job_clean?}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
    Record an outcome {compartment, outcome, job_id?, job_clean?}
Only reads 1Claude Code: allow
  • status_queryCompartment status for an agent {agent} — $0.01 x402 or included on an active plan (same billing as HTTP)No findings

    Why it is in this group

    • The name "status_query" says "status": a word for reading.
    Description, as the server wrote it
    Compartment status for an agent {agent} — $0.01 x402 or included on an active plan (same billing as HTTP)

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 ban-bulkheads-reputation-firebreaks https://textforagents.com/products/ban-bulkheads-reputation-firebreaks/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": [
      "mcp__ban-bulkheads-reputation-firebreaks__status_query"
    ],
    "ask": [
      "mcp__ban-bulkheads-reputation-firebreaks__create_compartment",
      "mcp__ban-bulkheads-reputation-firebreaks__assign_agent",
      "mcp__ban-bulkheads-reputation-firebreaks__record_outcome",
      "mcp__ban-bulkheads-reputation-firebreaks__add_job",
      "mcp__ban-bulkheads-reputation-firebreaks__penalty_signal",
      "mcp__ban-bulkheads-reputation-firebreaks__freeze_compartment",
      "mcp__ban-bulkheads-reputation-firebreaks__readmit",
      "mcp__ban-bulkheads-reputation-firebreaks__receipts"
    ],
    "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 ban-bulkheads-reputation-firebreaks. Review it before you use it.