Register a code pattern
AI agents use register_pattern to create or update resources in Sourcesage — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Sourcesage environment.
This tool creates or adds new code pattern records to SourceSage's in-memory codebase model. While it modifies the knowledge store, the changes are reversible (patterns can be updated or cleared via sibling tools like 'clear_knowledge'), so it is Write rather than Destructive.
From the tool's definition Tool name 'register_pattern' with description 'Register a code pattern' indicates creation/modification of pattern data in the codebase knowledge store. The verb 'register' implies writing new pattern information into the system.
Attacks that exploit this kind of access
Register a code pattern. It is categorised as a Write tool in the Sourcesage MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Sourcesage MCP server in PolicyLayer and add a rule for register_pattern: 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.
register_pattern is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the register_pattern 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 register_pattern. 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.
register_pattern 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 →