search function and parameters that can be used to solve the user's tasks or questions
AI agents call retrieve_knowledge to retrieve information from decoupler-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves knowledge or search results to help answer questions, with no indication of data modification, deletion, code execution, or financial impact. It is a purely informational lookup function consistent with Read category operations like 'search' or 'fetch'.
From the tool's definition Tool name 'retrieve_knowledge' combined with description 'search function' indicates data retrieval without modification. The phrase 'can be used to solve the user's tasks or questions' suggests query/lookup capabilities typical of Read operations.
Attacks that exploit this kind of access
search function and parameters that can be used to solve the user's tasks or questions. It is categorised as a Read tool in the decoupler-MCP MCP Server, which means it retrieves data without modifying state.
Register the decoupler- MCP server in PolicyLayer and add a rule for retrieve_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 decoupler-MCP. Nothing to install.
retrieve_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 retrieve_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 retrieve_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.
retrieve_knowledge is provided by the decoupler- MCP server (scmcphub/decoupler-mcp). 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 →