MCP MeasureMCP Measure

index observed

Refusal-dialect & meter-truth probe

Refusal-dialect probe: signed cards naming what a server's 429 means and whether its meter lies.

Should I use this

Quality & Safety

B
Description quality
87%
Schema completeness
63%
Naming quality
93%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~148Tokens (tool definitions)
~239 BTypical response size
Minimal attention impact (0.12% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "refusal-dialect-meter-truth-probe": {
      "url": "https://textforagents.com/products/refusal-dialect-meter-truth-probe/mcp"
    }
  }
}

Remote endpoints

https://textforagents.com/products/refusal-dialect-meter-truth-probe/mcpstreamable-http

What it can do

Tool inventory

Tools (3)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢list_servers

List admitted dialect servers

Input Schema

{
  "type": "object",
  "properties": {}
}
🟢cached_card_query(api_token, server_id)

Cached signed dialect card query ($0.05; first free once per account and per wallet). Requires api_token and server_id.

Input Schema

{
  "type": "object",
  "properties": {
    "api_token": {
      "type": "string"
    },
    "server_id": {
      "type": "string"
    }
  },
  "required": [
    "api_token",
    "server_id"
  ]
}
⚪verify_card(card)

Verify a dialect card Ed25519 signature

Input Schema

{
  "type": "object",
  "properties": {
    "card": {
      "type": "object"
    }
  },
  "required": [
    "card"
  ]
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded3 tools