# Sentinel Signal MCP for Healthcare Claims Scoring

Hosted MCP server for denial risk, prior authorization, reimbursement scoring, usage, and feedback. Includes no-signup trial keys and Smithery support.

## Quick Start

```bash
# Connect this server (installs CLI if needed)
npx -y @smithery/cli@latest mcp add sentinelsignal/scoring

# Browse available tools
npx -y @smithery/cli@latest tool list sentinelsignal/scoring

# Get full schema for a tool
npx -y @smithery/cli@latest tool get sentinelsignal/scoring list_workflows

# Call a tool
npx -y @smithery/cli@latest tool call sentinelsignal/scoring list_workflows '{}'
```

## Direct MCP Connection

Endpoint: `https://scoring--sentinelsignal.run.tools`

**Optional config:**
- `sentinelApiKey` (header) — Optional. Use your own Sentinel API key for account-bound quota and usage.
- `sentinelApiBaseUrl` (query) — Optional override for private or self-hosted Sentinel API environments.
- `sentinelTokenBaseUrl` (query) — Optional override for minting trial keys outside the default hosted environment.

## Tools (8)

- `list_workflows` — List supported workflows and current model versions via GET /v1/workflows
- `get_workflow_schema` — Fetch required fields, optional fields, enums, and an example payload for a workflow via GET /v1/workflows/{workflow}/s…
- `validate_workflow_payload` — Validate and normalize a workflow payload without consuming a scoring call via POST /v1/workflows/{workflow}/validate
- `score_workflow` — Score denial risk, prior auth, and reimbursement workflows via POST /v1/score
- `score_batch` — Score up to 25 workflow items sequentially in one request via POST /v1/score/batch
- `get_limits` — Retrieve plan limits, trial quota, and upgrade state via GET /v1/limits
- `get_usage` — Retrieve monthly scoring call usage via GET /v1/usage
- `submit_feedback` — Submit structured claims outcome feedback via POST /v1/feedback

```bash
# Get full input/output schema for a tool
npx -y @smithery/cli@latest tool get sentinelsignal/scoring <tool-name>
```

## Prompts (2)

- `claims_triage_prompt` — Help an agent choose the right healthcare claims workflow and required payload fields before scoring.
- `explain_score_prompt` — Help an agent interpret a Sentinel score and decide what operational action to take next.