# Microgram: narrative-site-filter

`station__algovigilance__microgram-narrative-site-filter` · native (always callable) · domain `algovigilance` · pv-relevance `pv-core`

Gate 2 of narrative safe-extract: detect clinical trial site identifiers, institution names, and investigator details that could compromise trial blinding or reveal proprietary relationships

## Agent metadata

- `idempotent`: true
- `read_only`: true
- `expected_latency_ms`: unknown (not yet contract-tested)
- `cost_tokens_estimate`: unknown

## Input schema

- `has_site_number` *boolean* — Input variable has_site_number
- `has_institution_name` *boolean* — Input variable has_institution_name
- `has_investigator_name` *boolean* — Input variable has_investigator_name
- `has_irb_identifier` *boolean* — Input variable has_irb_identifier
- `has_protocol_number` *boolean* — Input variable has_protocol_number
- `is_blinded_study` *boolean* — Input variable is_blinded_study

## Example call

```json
POST /api/mcp
Content-Type: application/json

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "station__algovigilance__microgram-narrative-site-filter",
    "arguments": {}
  }
}
```

## Related

- [/tools](/tools) — all 7718 tools
- [/tools/algovigilance__microgram-narrative-site-filter](/tools/algovigilance__microgram-narrative-site-filter) — HTML page
- [/tools/algovigilance__microgram-narrative-site-filter/json](/tools/algovigilance__microgram-narrative-site-filter/json) — JSON form (agent-friendly)
- [/api/mcp](/api/mcp) — endpoint
- [/AGENTS.md](/AGENTS.md) — agent guide