// SCAN REPORT

Tenth Man

3 tools. 2 can modify or destroy data without limits.

2 write tools that can modify data. Rate limits recommended.

Last updated: 2 Jul 2026

2 can modify or destroy data

1 read-only

3 tools total

Community server · catalogue entry verified 02/07/2026

How to control Tenth Man ↓

TOOL MAP

What Tenth Man exposes to your agents

Read (1) Write / Execute (2) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Tenth Man tools

Execute · Medium tenth_man_review The tool executes external agent operations (spawning and running multiple AI agents in parallel) rather than passively reading or writing data. Write · Medium tenth_man_configure This tool creates or modifies configuration data (preferences, timeouts, trigger patterns) without irreversibly deleting data or executing arbitrary external code.

2 of Tenth Man's 3 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Tenth Man

PolicyLayer is an MCP gateway — it sits between your AI agents and Tenth Man, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "tenth_man_configure": {
    "limits": [
      {
        "counter": "tenth_man_configure_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "tenth_man_history": {
    "limits": [
      {
        "counter": "tenth_man_history_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Tenth Man — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON TENTH MAN →

Instant setup, no code required.

FULL CATALOGUE

All 3 Tenth Man tools

EXECUTE 1 tools

Execute tenth_man_review Triggers the 10th Man Protocol — spawns 3 contrarian agents to independently challenge proposed code changes b

WRITE 1 tools

Write tenth_man_configure Configure agent preferences, timeouts, and trigger patterns for the 10th Man Protocol. Auto-detects available

READ 1 tools

Read tenth_man_history Query past 10th Man audit reports from this repository. Returns recent reviews with verdicts, issues found, an

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Tenth Man

How do I prevent bulk modifications through Tenth Man? +

The Tenth Man server has 1 write tools including tenth_man_configure. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Tenth Man.

How many tools does the Tenth Man MCP server expose? +

3 tools across 3 categories: Execute, Read, Write. 1 are read-only. 2 can modify, create, or delete data.

How do I enforce a policy on Tenth Man? +

Register the Tenth Man MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Tenth Man tool call.

Deterministic rules across all 3 Tenth Man tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON TENTH MAN →

Instant setup, no code required.

3 Tenth Man tools catalogued and risk-classified — across an index of 43,000+ MCP servers.