MCP MeasureMCP Measure

index observed

Unattended-surface parity probe

Pre-run parity probe for scheduled agents: signed PARITY / NO-GO verdict naming the failing gate.

Should I use this

Quality & Safety

B
Description quality
77%
Schema completeness
43%
Naming quality
80%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Findings (1)

  • LOWTool 'pre_run' description lacks action verbin pre_run

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~135Tokens (tool definitions)
~126 BTypical response size
Minimal attention impact (0.11% 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": {
    "unattended-surface-parity-probe": {
      "url": "https://textforagents.com/products/unattended-surface-parity-probe/mcp"
    }
  }
}

Remote endpoints

https://textforagents.com/products/unattended-surface-parity-probe/mcpstreamable-http

What it can do

Tool inventory

Tools (3)

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

Run the parity fixture through the unattended surface (first probe per operator free, then $4.99 x402)

Input Schema

{
  "type": "object",
  "properties": {}
}
⚪parity_verdict(task_id)

Precomputed signed verdict for a task ($0.01 x402)

Input Schema

{
  "type": "object",
  "properties": {
    "task_id": {
      "type": "string"
    }
  }
}
⚪pre_run

Scheduler gate: GO on valid PARITY else NO-GO + draft queued

Input Schema

{
  "type": "object",
  "properties": {}
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded3 tools