检测知识库中近似重复的文档（基于文档级 embedding 余弦相似度 + 标题 bigram Jaccard）。用于 wiki concepts/entities 去重。
AI agents call lint_duplicates to retrieve information from Personal Knowledge MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is fundamentally a detection and analysis tool that retrieves and examines document similarity metadata. It has no capacity to modify, delete, or execute operations—it only reads documents and computes duplicate similarity metrics.
From the tool's definition Tool detects and identifies near-duplicate documents in knowledge base using embedding cosine similarity and title bigram Jaccard analysis. It performs analysis ('检测') and comparison without modifying, deleting, or executing operations.
Documented attack patterns abuse exactly the kind of access lint_duplicates gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Personal Knowledge MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for lint_duplicates:
{
"version": "1",
"default": "deny",
"tools": {
"lint_duplicates": {}
}
}lint_duplicates is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
检测知识库中近似重复的文档（基于文档级 embedding 余弦相似度 + 标题 bigram Jaccard）。用于 wiki concepts/entities 去重。. It is categorised as a Read tool in the Personal Knowledge MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Personal Knowledge MCP Server MCP server in PolicyLayer and add a rule for lint_duplicates: 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 Personal Knowledge MCP Server. Nothing to install.
lint_duplicates is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the lint_duplicates 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 lint_duplicates. 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.
lint_duplicates is provided by the Personal Knowledge MCP Server MCP server (kyodule/personal-knowledge-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Personal Knowledge MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
29 Personal Knowledge MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.