知识库语义搜索：在指定知识库范围内进行语义召回。适用场景：「在我的 XX 知识库搜一下 XX」。返回结果按相关度从高到低排序。需要 note.topic.recall.read scope。
AI agents call recall_knowledge to retrieve information from GetNote MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data from a knowledge base without side effects. It matches the Read category definition: no data is created, modified, deleted, or executed—it only searches and returns existing knowledge base entries sorted by relevance. The read-only scope requirement reinforces this classification.
From the tool's definition Tool performs "semantic search" (语义搜索) and "semantic recall" (语义召回) within a specified knowledge base, returning results sorted by relevance. The description explicitly indicates it retrieves information ("搜", search) without modifying data.
Documented attack patterns abuse exactly the kind of access recall_knowledge gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and GetNote MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for recall_knowledge:
{
"version": "1",
"default": "deny",
"tools": {
"recall_knowledge": {}
}
}recall_knowledge 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.
知识库语义搜索：在指定知识库范围内进行语义召回。适用场景：「在我的 XX 知识库搜一下 XX」。返回结果按相关度从高到低排序。需要 note.topic.recall.read scope。. It is categorised as a Read tool in the GetNote MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GetNote MCP Server MCP server in PolicyLayer and add a rule for recall_knowledge: 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 GetNote MCP Server. Nothing to install.
recall_knowledge 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 recall_knowledge 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 recall_knowledge. 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.
recall_knowledge is provided by the GetNote MCP Server MCP server (iswalle/getnote-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from GetNote 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.
26 GetNote MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.