Search for knowledge items by keywords, tags, or categories
AI agents call search_knowledge to retrieve information from Trello Knowledge 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 the Trello knowledge base without creating, modifying, deleting, or executing any operations. Search operations are inherently non-destructive and return results only. The low severity reflects minimal blast radius—misuse would only expose existing data the user/agent can already access through other read tools.
From the tool's definition Tool name 'search_knowledge' and description 'Search for knowledge items by keywords, tags, or categories' indicate a query/retrieval operation with no modification of data.
Attacks that exploit this kind of access
Search for knowledge items by keywords, tags, or categories. It is categorised as a Read tool in the Trello Knowledge MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Trello Knowledge MCP Server MCP server in PolicyLayer and add a rule for search_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 Trello Knowledge MCP Server. Nothing to install.
search_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 search_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 search_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.
search_knowledge is provided by the Trello Knowledge MCP Server MCP server (pscheit/trello-knowledge-mcp-server). 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 →