Schema | agent-trace-intelligence

agent-trace-intelligence

Describes the environment variables required to run the server.

Name	Required	Description	Default
`JUDGE_MODEL`	No	Model to use for judging. Options include 'azure_ai/claude-opus-4-6', 'azure_ai/gpt-4.1', 'gpt-4o-mini', 'claude-haiku-4-5-20251001'	azure_ai/claude-opus-4-6
`OPENAI_API_KEY`	No	Your OpenAI API key (required for OpenAI-based judge model)
`AZURE_AI_API_KEY`	No	Your Azure AI Foundry API key (required for Azure-based judge model)
`AZURE_AI_API_BASE`	No	Your Azure AI Foundry API base URL (required for Azure-based judge model)

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{ "listChanged": false }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
judge_traceB	Diagnoses an agent trace — identifies root causes of failure, scores performance across four dimensions, and suggests a concrete fix. Returns verdict, grade, and plain-English explanation.
trace_breakdownB	Step-by-step scoring of every agent decision. Flags issues like redundant tool calls, reasoning gaps, and goal drift.
efficiency_scoreA	Deterministic efficiency analysis of token usage, tool redundancy, and latency. No API key required — runs instantly.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/harinarayn/agent-trace-intelligence'

If you have feedback or need assistance with the MCP directory API, please join our Discord server