Low Risk

tool_patent_detail

Get detailed information for a specific patent. Args: publication_number: Patent publication number (e.g., "JP-2020123456-A"). JP granted patents use kind code B1: "JP-7637366-B1". JP applications use kind code A: "JP-2020-123456-A". Returns: Full patent record including CPC codes, assignees, inv...

Part of the Patent Space server.

tool_patent_detail is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE PATENT SPACE →

Free to start. No card required.

AI agents call tool_patent_detail to retrieve information from Patent Space without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though tool_patent_detail only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "tool_patent_detail": {}
  }
}

See the full Patent Space policy for all 29 tools.

Get this rule live on your own Patent Space server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY PATENT SPACE →

View all 29 tools →

These attack patterns abuse exactly the kind of access tool_patent_detail gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so tool_patent_detail only ever does what you allow.

SECURE PATENT SPACE →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the tool_patent_detail tool do? +

Get detailed information for a specific patent. Args: publication_number: Patent publication number (e.g., "JP-2020123456-A"). JP granted patents use kind code B1: "JP-7637366-B1". JP applications use kind code A: "JP-2020-123456-A". Returns: Full patent record including CPC codes, assignees, inventors, and citations.. It is categorised as a Read tool in the Patent Space MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on tool_patent_detail? +

Register the Patent Space MCP server in PolicyLayer and add a rule for tool_patent_detail: 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 Patent Space. Nothing to install.

What risk level is tool_patent_detail? +

tool_patent_detail is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit tool_patent_detail? +

Yes. Add a rate_limit block to the tool_patent_detail 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.

How do I block tool_patent_detail completely? +

Set action: deny in the PolicyLayer policy for tool_patent_detail. 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.

What MCP server provides tool_patent_detail? +

tool_patent_detail is provided by the Patent Space MCP server (Rei02061986/patent-space-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Patent Space tool call.

Deterministic rules across all 29 Patent Space tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.