run_knockout_search
Run an examiner-style knockout search with scoring via the unified knockout engine — the same engine the GleanMark product uses. This is a PURE USPTO conflict search over 14M trademark records (exact, phonetic, trigram, component words, coordinated class expansion, doctrine of foreign equivalents...
This record as markdown: /tools/com-gleanmark-trademark-search/run-knockout-search.md
What run_knockout_search does on GleanMark Trademark Search
AI agents invoke run_knockout_search 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
mark_name | string | Yes | The proposed mark name to search for (e.g., "BARLYTICS", "WAR MUSCLE") |
owner_name | string | — | Optional: the applicant/owner company name (e.g., "APPLE INC."). Adds portfolio context showing their existing marks in the searched classes and flags same-owne |
max_results | integer | — | Maximum scored results to return (default: 200) |
design_codes | array | — | USPTO design codes to include in the search (optional) |
include_dead | boolean | — | Include dead/abandoned marks in results (default: false, live only) |
nice_classes | array | — | Nice classes to search (e.g., ["042", "035"]). The search automatically expands to coordinated classes. Optional — omit to search all classes. |
goods_description | string | — | The goods/services the applicant plans to sell (e.g., "hair extensions; synthetic hair pieces and wigs"). STRONGLY RECOMMENDED whenever known: it drives goods-r |
Parameters from the server's own tool schema.
Why run_knockout_search is rated High
run_knockout_search triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Attacks that exploit this kind of access
The rule that runs run_knockout_search safely
PolicyLayer is an MCP gateway: it sits between your AI agents and GleanMark Trademark Search, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For run_knockout_search, this is the rule to start with:
run_knockout_search stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect GleanMark Trademark Search, apply this rule, and every run_knockout_search call is checked against it from then on.
Questions about run_knockout_search
Run an examiner-style knockout search with scoring via the unified knockout engine — the same engine the GleanMark product uses. This is a PURE USPTO conflict search over 14M trademark records (exact, phonetic, trigram, component words, coordinated class expansion, doctrine of foreign equivalents, design codes) with mark-similarity and commercial-overlap scoring. Returns 4-tier risk-grouped results (very_high/high/medium/low) with confusion scores, plus a dead-mark "naming territory" sample. The top-line verdict is calibrated four-tier — CRITICAL CONFLICTS / ELEVATED RISK / MODERATE RISK / LOW RISK — with a one-line reason, so multi-name shortlists rank meaningfully. ALWAYS pass goods_description when the user has told you what they sell — the risk bands score goods/services relatedness, so an identical mark in a related-goods class reads VERY_HIGH only when the goods are supplied (class-only scoring understates it). It does NOT check domain availability and does NOT run a brand/web availability check — for that, use check_brand_availability instead. Most searches finish in under a minute; before calling, give the user a one-line heads-up that it may take up to a minute. Optional owner_name adds portfolio context — shows the applicant's existing marks in searched classes. It is categorised as a Execute tool in the GleanMark Trademark Search MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
run_knockout_search accepts 7 parameters: mark_name, owner_name, max_results, design_codes, include_dead, nice_classes, goods_description. Required: mark_name. The full parameter table on this page comes from the server's own tool schema.
Register the GleanMark Trademark Search MCP server in PolicyLayer and add a rule for run_knockout_search: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches GleanMark Trademark Search. Nothing to install.
run_knockout_search is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_knockout_search rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for run_knockout_search. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
run_knockout_search is provided by the GleanMark Trademark Search MCP server (https://gleanmark.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on GleanMark Trademark Search, and thousands of servers like it.
Across the catalogue