RMCP.DEV
← agentbenchmark.dev

INDIVIDUAL MCP TOOL

ami_write_findings

Write the judgement sections of a run's scorecard.

agentbenchmark.devnone authenticationAvailability not checked

LIVE ENDPOINT

https://survey.agentbenchmark.dev/mcp

No auth detected

Connect to this endpoint to inspect the live schema for ami_write_findings and invoke it with your own arguments.

Indexed input schema

{}

Risk classification

Potential side effects detected · medium confidence · heuristic, not a guarantee.

  • A tool name or description contains a write-action term.

Parent server

agentbenchmark.dev

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.ami-survey]
url = "https://survey.agentbenchmark.dev/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "ami-survey": {
      "type": "http",
      "url": "https://survey.agentbenchmark.dev/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: ami-survey
Remote MCP URL: https://survey.agentbenchmark.dev/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "ami-survey": {
      "url": "https://survey.agentbenchmark.dev/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code 
{
  "servers": {
    "ami-survey": {
      "type": "http",
      "url": "https://survey.agentbenchmark.dev/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "ami-survey",
  "transport": "streamable-http",
  "url": "https://survey.agentbenchmark.dev/mcp"
}
MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

Related tools

  • ami_register — Obtain a submission token.
  • ami_survey_begin — Open a survey run for a workflow that has finished.
  • ami_mark_stage — Record a stage of the workflow.
  • ami_record_calls — Report the API calls the workflow made, using the usage your own runtime reported for each one - values read from real responses, never estimated.
  • ami_prepare_workflow — Return the procedure for adapting an existing prompt so the run it describes can be measured.
  • ami_get_grading_scale — The grades a submission may carry and what each one means.
  • ami_get_workflow_categories — The workflow categories a run may declare itself into, and what each one covers.
  • ami_get_scorecard — The scorecard for a submitted run: the AMI Maturity Index, the Performance Score, the five pillars, and structured findings.