claims-coverage-assessment-assistant
by ayushgupta94
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MONGO_URI | No | Atlas / local / Cosmos DB vCore connection string | mongodb://localhost:27017 |
| RAG_TOP_K | No | Clauses retrieved per query | 3 |
| LLM_PROVIDER | No | openai | azure_openai | openai |
| OPENAI_MODEL | No | Model for the agent loop | gpt-4o-mini |
| MONGO_DB_NAME | No | Database name | claims_assistant |
| OPENAI_API_KEY | Yes | Required always (RAG embeddings; also default LLM provider) | |
| AZURE_OPENAI_API_KEY | No | Required if LLM_PROVIDER=azure_openai | |
| AZURE_OPENAI_ENDPOINT | No | Required if LLM_PROVIDER=azure_openai | |
| AZURE_OPENAI_DEPLOYMENT | No | Required if LLM_PROVIDER=azure_openai | |
| FRAUD_HIGH_AMOUNT_THRESHOLD | No | Fraud signal: high claim amount | 500000 |
| FRAUD_FREQUENCY_LOOKBACK_DAYS | No | Fraud signal: frequency window | 365 |
| FRAUD_EARLY_CLAIM_DAYS_THRESHOLD | No | Fraud signal: claim shortly after inception | 30 |
| FRAUD_FREQUENCY_CLAIM_COUNT_THRESHOLD | No | Fraud signal: claim count trigger | 3 |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues