MCP MeasureMCP Measure

index observed

Concurrent-client isolation probe

Concurrent two-client overlap probe proving MCP servers do not cross-deliver tool results.

Should I use this

Quality & Safety

A
Description quality
93%
Schema completeness
80%
Naming quality
93%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~153Tokens (tool definitions)
~299 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": {
    "concurrent-client-isolation-probe": {
      "url": "https://textforagents.com/products/concurrent-client-isolation-probe/mcp"
    }
  }
}

Remote endpoints

https://textforagents.com/products/concurrent-client-isolation-probe/mcpstreamable-http

What it can do

Tool inventory

Tools (3)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
⚪probe_isolation(target, authorisation)

Run a full concurrent-client isolation probe against an operator-authorised MCP server; returns a signed per-surface verdict.

Input Schema

{
  "type": "object",
  "properties": {
    "target": {
      "type": "string"
    },
    "authorisation": {
      "type": "string"
    }
  },
  "required": [
    "target",
    "authorisation"
  ]
}
🟢get_verdict(endpoint)

Latest signed verdict on file for an endpoint.

Input Schema

{
  "type": "object",
  "properties": {
    "endpoint": {
      "type": "string"
    }
  },
  "required": [
    "endpoint"
  ]
}
⚪verify_receipt(receipt)

Verify a signed verdict receipt.

Input Schema

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

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded3 tools