AI agents use d_ann_config to create or update resources in Heuristic — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Heuristic environment.
An AI agent can call d_ann_config faster than any human can review — one bad instruction and it creates or modifies resources in Heuristic by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Configure and monitor the ANN (Approximate Nearest Neighbor) search index. Actions:. It is categorised as a Write tool in the Heuristic MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Heuristic MCP server in PolicyLayer and add a rule for d_ann_config: 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 Heuristic. Nothing to install.
d_ann_config 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 d_ann_config 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 d_ann_config. 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.
d_ann_config is provided by the Heuristic MCP server (softerist/heuristic-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.