# run_safe_analytics

Run a constrained business-level analytics query without exposing schema details. This is the default fallback for bespoke rankings, counts, snapshots, and timelines across owners, firms, and correspondents. Prefer this before chaining search, summary, or web research tools for aggregate business questions.

Agent View of the PolicyLayer registry record for `run_safe_analytics`. HTML page: https://policylayer.com/tools/com-gleanmark-trademark-search/run-safe-analytics

## Facts

- Tool: `run_safe_analytics`
- Server: GleanMark Trademark Search (`https://gleanmark.com/mcp`) — https://policylayer.com/tools/com-gleanmark-trademark-search.md
- Homepage: https://github.com/https://gleanmark.com/mcp
- Risk category: Execute (High risk)
- Registry record: grade D, identity unverified
- Server auth posture: open
- Server CORS policy: *
- Server rate-limited: yes
- Parameters: 6 (2 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `limit` | integer | no | Maximum number of ranked rows, preview marks, or timeline events to return. |
| `entity` | string | yes | What to analyze. Ranking currently supports owners. Count, snapshot, and timeline also support firms and correspondents. |
| `metric` | string | no | Required for count. Ranking currently supports filings only. |
| `filters` | object | no |  |
| `subject_name` | string | no | Required for count, snapshot, and timeline. Examples: "Ideaya Biosciences", "Goodwin Procter", or "Todd Schneider". |
| `analysis_type` | string | yes | Business analytics mode: ranking, count, snapshot, or timeline. |

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": "run_safe_analytics",
    "arguments": {
      "entity": "<entity>",
      "analysis_type": "<analysis_type>"
    }
  }
}
```

## Why run_safe_analytics is rated High

The tool executes analytics queries against the trademark database. While described as 'constrained' and 'safe' (suggesting read-only analytics), the term 'run' combined with 'query' places this in the Execute category rather than Read, as it triggers computation/query execution whose results depend on arguments.

From the tool's own definition: "'Run a constrained business-level analytics query' — the word 'Run' indicates execution of a query operation against the underlying data store"

Risk signals: High parameter count (14 properties)

## Use case

AI agents invoke run_safe_analytics to trigger actions in GleanMark Trademark Search. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches GleanMark Trademark Search:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_safe_analytics": {
      "limits": [
        {
          "counter": "run_safe_analytics_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on GleanMark Trademark Search (60)

- `run_knockout_search` — Execute — https://policylayer.com/tools/com-gleanmark-trademark-search/run-knockout-search.md
- `analyze_prosecution_history` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/analyze-prosecution-history.md
- `analyze_ttab_proceeding` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/analyze-ttab-proceeding.md
- `check_brand_availability` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/check-brand-availability.md
- `check_domain_availability` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/check-domain-availability.md
- `compare_marks` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/compare-marks.md
- `count_trademarks_by_attributes` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/count-trademarks-by-attributes.md
- `get_class_relationships` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/get-class-relationships.md
- `get_cohort_event_intervals` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/get-cohort-event-intervals.md
- `get_correspondent_marks` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/get-correspondent-marks.md
- `get_correspondent_specialization` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/get-correspondent-specialization.md
- `get_deadline_satisfaction_mapping` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/get-deadline-satisfaction-mapping.md
- `get_event_code_reference` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/get-event-code-reference.md
- `get_event_status_mapping` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/get-event-status-mapping.md
- `get_fame_profile` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/get-fame-profile.md
- `get_firm_correspondent_tasks` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/get-firm-correspondent-tasks.md
- `get_firm_deadlines` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/get-firm-deadlines.md
- `get_firm_oa_outcomes` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/get-firm-oa-outcomes.md
- `get_firm_top_correspondents` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/get-firm-top-correspondents.md
- `get_latest_office_action` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/get-latest-office-action.md
- `get_mark_ai_summary` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/get-mark-ai-summary.md
- `get_mark_deadlines` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/get-mark-deadlines.md
- `get_mark_international_profile` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/get-mark-international-profile.md
- `get_mark_owner_landscape` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/get-mark-owner-landscape.md
- `get_mark_prosecution_summary` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/get-mark-prosecution-summary.md
- `get_nice_classes` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/get-nice-classes.md
- `get_owner_ai_summary` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/get-owner-ai-summary.md
- `get_owner_deadlines` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/get-owner-deadlines.md
- `get_owner_filing_trends` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/get-owner-filing-trends.md
- `get_owner_goods_keywords` — Read — https://policylayer.com/tools/com-gleanmark-trademark-search/get-owner-goods-keywords.md
- …and 30 more: https://policylayer.com/tools/com-gleanmark-trademark-search.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-gleanmark-trademark-search · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/com-gleanmark-trademark-search