AI agents use add_diagram_references to create or update resources in Claude Patent Creator — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Patent Creator environment.
The name 'add_diagram_references' semantically aligns with Write (creates or modifies data reversibly). Without a description, confidence is reduced. It does not appear to delete data (thus not Destructive), execute arbitrary code (Execute), or move money (Financial). The tool likely updates patent diagram metadata or document references, which is reversible and constitutes modification without destruction.
From the tool's definition Tool name 'add_diagram_references' indicates modification of data (adding/inserting references). Description is empty, limiting direct evidence.
Documented attack patterns abuse exactly the kind of access add_diagram_references gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Patent Creator, and nothing reaches the server without passing your rules. This is the rule we recommend for add_diagram_references:
{
"version": "1",
"default": "deny",
"tools": {
"add_diagram_references": {
"limits": [
{
"counter": "add_diagram_references_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_diagram_references stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
add_diagram_references. It is categorised as a Write tool in the Claude Patent Creator MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claude Patent Creator MCP server in PolicyLayer and add a rule for add_diagram_references: 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 Claude Patent Creator. Nothing to install.
add_diagram_references is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_diagram_references 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 add_diagram_references. 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.
add_diagram_references is provided by the Claude Patent Creator MCP server (robthepcguy/claude-patent-creator). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 30 Claude Patent Creator tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
30 Claude Patent Creator tools catalogued and risk-classified — across an index of 42,500+ MCP servers.