// SCAN REPORT

Warrant

10 tools. 5 can modify or destroy data without limits.

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

Last updated: 3 Jul 2026

5 can modify or destroy data

5 read-only

10 tools total

Community server · catalogue entry verified 03/07/2026

How to control Warrant ↓

TOOL MAP

What Warrant exposes to your agents

Read (5) Write / Execute (5) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Warrant tools

Execute · Medium build_argument build_argument Write · Low create_dialogue The tool initializes a new dialogue session for argumentation analysis. Write · Low create_framework This tool creates argumentation frameworks (data structures), which is a reversible write operation. Write · Medium dialogue_move This tool writes a new speech act move into an ongoing dialogue, modifying the state of the dialogue.

5 of Warrant's 10 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Warrant

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

Rate limit write operations

{
  "compute_extensions": {
    "limits": [
      {
        "counter": "compute_extensions_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "classify_defeater": {
    "limits": [
      {
        "counter": "classify_defeater_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 Warrant — 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 WARRANT →

Instant setup, no code required.

FULL CATALOGUE

All 10 Warrant tools

EXECUTE 1 tools

Execute build_argument build_argument

WRITE 4 tools

Write compute_extensions Compute acceptable arguments using Dung's semantics. Write create_dialogue Start a new argumentation dialogue session. Write create_framework Create a Dung Argumentation Framework or Bipolar AF. Write dialogue_move Make a speech act move in a dialogue.

READ 5 tools

Read classify_defeater Classify a counterargument as rebutting or undercutting. Read diagnose_disagreement Diagnose WHY two agents disagree. Read identify_scheme Identify which Walton argumentation scheme matches a claim. Read list_schemes List all available Walton argumentation schemes. Read score_arguments Score arguments using gradual semantics.

EXPLORE

Related servers

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

FAQ

Questions about Warrant

How do I prevent bulk modifications through Warrant? +

The Warrant server has 4 write tools including compute_extensions, create_dialogue, create_framework. 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 Warrant.

How many tools does the Warrant MCP server expose? +

10 tools across 3 categories: Execute, Read, Write. 5 are read-only. 5 can modify, create, or delete data.

How do I enforce a policy on Warrant? +

Register the Warrant 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 Warrant tool call.

Deterministic rules across all 10 Warrant tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON WARRANT →

Instant setup, no code required.

10 Warrant tools catalogued and risk-classified — across an index of 43,000+ MCP servers.