Clear all knowledge from the graph
AI agents call clear_knowledge to permanently remove resources in Sourcesage — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs a wholesale, irreversible erasure of all accumulated codebase knowledge (entities, patterns, relationships, style conventions) that the server has indexed and memorized. There is no undo, no partial recovery, and no way to restore the deleted information without re-processing the codebase from scratch.
From the tool's definition Tool name 'clear_knowledge' combined with description 'Clear all knowledge from the graph' indicates irreversible deletion of all stored data in the knowledge graph.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Clear all knowledge from the graph. It is categorised as a Destructive tool in the Sourcesage MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Sourcesage MCP server in PolicyLayer and add a rule for clear_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 Sourcesage. Nothing to install.
clear_knowledge is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the clear_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 clear_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.
clear_knowledge is provided by the Sourcesage MCP server (mcpflow/sourcesage). 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 →