# get_findings

Retrieve security findings filtered by file or severity. Run scan_repository first to populate results.

Agent View of the PolicyLayer registry record for `get_findings`. HTML page: https://policylayer.com/tools/com-graneth-mcp-server/get-findings

## Facts

- Tool: `get_findings`
- Server: Mcp Server (`@graneth/mcp-server`) — https://policylayer.com/tools/com-graneth-mcp-server.md
- Install: `npx -y @graneth/mcp-server`
- Homepage: https://github.com/zubovartemiy/graneth-mcp
- Risk category: Read (Low risk)
- Registry record: grade D, identity unverified
- Server auth posture: open
- Server rate-limited: yes
- Parameters: 4 (2 required)
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `file` | string | no | Filter findings to a specific file path |
| `repo` | string | yes | GitHub repository name |
| `owner` | string | yes | GitHub repository owner |
| `severity` | string | no | Filter by severity level |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_findings",
    "arguments": {
      "repo": "<repo>",
      "owner": "<owner>"
    }
  }
}
```

## Why get_findings is rated Low

This tool retrieves and filters existing security findings without modifying, deleting, or executing anything. It is purely informational, similar to a search or get operation. The filtering parameters (file, severity) are applied to already-scanned data, not to trigger new operations or mutations.

From the tool's own definition: "Tool name 'get_findings' and description 'Retrieve security findings' indicates a query/retrieval operation with no side effects. The instruction to 'Run scan_repository first to populate results' confirms this is a read-only accessor of pre-computed data."

Risk signals: Accepts file system path (file)

## Use case

AI agents call get_findings to retrieve information from Mcp Server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Mcp Server:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_findings": {}
  }
}
```

## Other tools on Mcp Server (3)

- `scan_repository` — Execute — https://policylayer.com/tools/com-graneth-mcp-server/scan-repository.md
- `pre_flight_check` — Read — https://policylayer.com/tools/com-graneth-mcp-server/pre-flight-check.md
- `auto_remediate` — Write — https://policylayer.com/tools/com-graneth-mcp-server/auto-remediate.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=com-graneth-mcp-server · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/com-graneth-mcp-server