通过关键词全文搜索策略和经验。仅返回已审批（approved）的策略。
AI agents call search_strategies to retrieve information from Agent-Comm-Hub without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries strategy data based on keywords through full-text search. It performs no side effects, creates no data, executes no code, and deletes nothing. The constraint to return only approved strategies further confirms it is a passive read operation with minimal risk if misused by an agent—worst case would be information disclosure of already-approved strategies.
From the tool's definition Tool name 'search_strategies' and description indicate a search operation that 'returns only approved strategies' — a read-only query with no modification, deletion, or execution of code.
Attacks that exploit this kind of access
通过关键词全文搜索策略和经验。仅返回已审批（approved）的策略。. It is categorised as a Read tool in the Agent-Comm-Hub MCP Server, which means it retrieves data without modifying state.
Register the Agent-Comm-Hub MCP server in PolicyLayer and add a rule for search_strategies: 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 Agent-Comm-Hub. Nothing to install.
search_strategies 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 search_strategies 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 search_strategies. 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.
search_strategies is provided by the Agent-Comm-Hub MCP server (liuboacean/agent-comm-hub). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →