Skip to content

MCP security checks — WARDEN and HISTOR

by modelmarket.dev · remote · no sign-in to list tools · v1.0.0 · published by dev.modelmarket

Scan MCP tool definitions for poisoning, look up server history, count tool-list tokens. Free.

Changes · 3
CompareRegistry entry

4 tools: 3 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 security https://modelmarket.dev/tools/mcp/security

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 3Claude Code: ask
  • histor_checkLook up an MCP server in HISTOR, a public append-only log of MCP tool sets: when its tool set was first pinned, how often it changed, and what the pattern scan found.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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Look up an MCP server in HISTOR, a public append-only log of MCP tool sets: when its tool set was first pinned, how often it changed, and what the pattern scan found. HISTOR answers from its own observations and never contacts the server.

    Annotations the server declares

    • title: Server history (HISTOR)
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • warden_scanScan an MCP server's tools/list with WARDEN, the open-source MCP firewall: static rules and a threat list over every name, description, schema and annotation.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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Scan an MCP server's tools/list with WARDEN, the open-source MCP firewall: static rules and a threat list over every name, description, schema and annotation. Returns allow or block and each finding with its rule and severity. Quoted fragments of the scanned text are left out of the answer.

    Annotations the server declares

    • title: Scan tool definitions (WARDEN)
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • x402_checkCheck a signed x402 USDC payment before submitting it: recovers the EIP-712 signer, runs USDC's own checks and the seller's terms, and when the signature fails names the domain it …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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Check a signed x402 USDC payment before submitting it: recovers the EIP-712 signer, runs USDC's own checks and the seller's terms, and when the signature fails names the domain it was really made for (e.g. Base Sepolia's 'USDC' used on Base, where USDC is 'USD Coin').

    Annotations the server declares

    • title: x402 payment check
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 1Claude Code: allow
  • tool_list_costHow many tokens an MCP server's tool list adds to every model request, what that costs per 1,000 requests, the heaviest tools, and where it sits among 18,204 packages and 16,170 re…No findings

    Why it is in this group

    • The name "tool_list_cost" says "list": a word for reading.
    Description, as the server wrote it
    How many tokens an MCP server's tool list adds to every model request, what that costs per 1,000 requests, the heaviest tools, and where it sits among 18,204 packages and 16,170 remote servers. Send a tools/list or name a server HISTOR observes.

    Annotations the server declares

    • title: Tool list token cost
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true

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 security https://modelmarket.dev/tools/mcp/security

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__security__tool_list_cost"
    ],
    "ask": [
      "mcp__security__warden_scan",
      "mcp__security__histor_check",
      "mcp__security__x402_check"
    ],
    "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 security. Review it before you use it.