alibi
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TYPESAFE_API_KEY | Yes | API key for TypeSafe AI's Jev model, required to use the judge backend. | |
| ALIBI_JUDGE_BACKEND | No | Backend for the judge, typically 'typesafe'. | |
| ALIBI_MAX_TRACE_TOKENS | No | Maximum trace tokens allowed (default: 250000). | |
| ALIBI_MIN_TRACE_TOKENS | No | Minimum trace tokens for analysis (default: 50000). | |
| ALIBI_ALLOW_PAID_MODELS | No | Set to '1' to allow paid model calls; without it, the judge refuses to run. |
Instructions
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.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| diagnose_traceA | Find where a long AI-agent run went wrong. Reads the trace chapter by chapter
(never all at once), raises a CUSUM alarm, looks back, and returns the 3 steps to
read first. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility of selecting between overlapping tools. The tool's purpose is clearly distinct by virtue of being the only resource.
The single tool name follows a clean verb_noun pattern (diagnose_trace). Consistency is trivially maintained with no mixed conventions.
A one-tool server is below the typical 3-15 range, but the narrow focus on trace diagnosis justifies a minimal surface. The tool is substantial and non-trivial, so the low count feels only slightly thin rather than inadequate.
For the stated purpose of diagnosing AI traces, the tool covers the full workflow: reading gated segments, detecting anomalies, and pointing to the key steps. No obvious missing operations are apparent within the narrow domain.