Kingfisher Streaming Inference
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KINGFISHER_API_KEY | No | API key for the real HTTP scoring provider. | |
| KINGFISHER_LOG_PATH | No | JSONL path to persist events. | |
| KINGFISHER_PROVIDER | No | Provider type: 'stub' (offline) or 'real' (HTTP). | stub |
| KINGFISHER_LOG_LEVEL | No | Logging level. | INFO |
| KINGFISHER_THRESHOLD | No | Z-score magnitude that flags an event. | 3.0 |
| KINGFISHER_AUDIT_PATH | No | JSONL path to persist the audit chain. | |
| KINGFISHER_MIN_SAMPLES | No | Per-stream samples before scoring leaves REVIEW. | 30 |
| KINGFISHER_MAX_FEATURES | No | Reject events with more features than this. | 256 |
| KINGFISHER_MAX_EVENT_BYTES | No | Reject events larger than this. | 65536 |
| KINGFISHER_SCORING_ENDPOINT | No | Endpoint for the real HTTP scoring provider. |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ingest_eventB | Score one event incrementally and append it to the audit chain. |
| verify_auditA | Recompute and verify the entire audit hash chain. |
| stream_statsC | Return running statistics for a stream. |
| export_auditA | Export audit records as a list for offline review. |
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 4 tools
Each tool has a clear, distinct role: ingest_event adds data, verify_audit validates the chain, stream_stats provides metrics, and export_audit retrieves records. There is no functional overlap between any of the four tools.
All tool names follow a consistent verb_noun pattern in snake_case (ingest_event, verify_audit, stream_stats, export_audit). The naming is predictable and immediately communicates each tool's action and target.
With 4 tools, the set is tightly scoped to the server's apparent purpose of event ingestion and audit verification. Each tool earns its place, and the number is well within the typical range for a focused toolkit.
The set covers the core lifecycle of an audit chain: ingest, verify, export, and stream-level statistics. Minor gaps exist, such as no per-record retrieval or stream configuration, but the essential workflows are complete.