# get_filters

A read tool on the 999md MCP server.

Agent View of the PolicyLayer registry record for `get_filters`. HTML page: https://policylayer.com/tools/999md-mcp/get-filters

## Facts

- Tool: `get_filters`
- Server: 999md (`ilodezis/999md-mcp`) — https://policylayer.com/tools/999md-mcp.md
- Homepage: https://github.com/ilodezis/999md-mcp
- Risk category: Read (Low risk)
- Registry record: grade A, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

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

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_filters",
    "arguments": {}
  }
}
```

## Why get_filters is rated Low

The 'get_' prefix uniformly appears on sibling tools that retrieve CRM data (deals, persons, organizations, activities). 'get_filters' almost certainly retrieves filter definitions or saved filters from Pipedrive, a read-only operation. Confidence is slightly reduced due to empty description, but the naming pattern and server context provide strong evidence of a Read classification.

From the tool's own definition: "Tool name 'get_filters' indicates a retrieval operation with the 'get_' prefix, consistent with sibling read-only tools (get_activities, get_deal, get_person, etc.)."

## Use case

AI agents call get_filters to retrieve information from 999md 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 999md:

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

## Other tools on 999md (7)

- `categories` — Read — https://policylayer.com/tools/999md-mcp/categories.md
- `get_ad` — Read — https://policylayer.com/tools/999md-mcp/get-ad.md
- `get_options` — Read — https://policylayer.com/tools/999md-mcp/get-options.md
- `photos` — Read — https://policylayer.com/tools/999md-mcp/photos.md
- `price_stats` — Read — https://policylayer.com/tools/999md-mcp/price-stats.md
- `search` — Read — https://policylayer.com/tools/999md-mcp/search.md
- `seller_ads` — Read — https://policylayer.com/tools/999md-mcp/seller-ads.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=999md-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/999md-mcp