AI agents invoke rebuild_index to trigger actions in Engram. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Rebuilding indexes is an Execute-category action: it triggers a potentially expensive system operation that reprocesses and reconstructs internal data structures (bloom filters, git indexes, embeddings). It is not a simple read, nor does it delete user data irreversibly, but it runs a significant background operation whose effects depend on the current state of the system.
From the tool's definition 'Rebuild Engram indexes (bloom, git, embeddings)' — rebuilding indexes is an operational/maintenance action that triggers reprocessing of all indexed data
Attacks that exploit this kind of access
Rebuild Engram indexes (bloom, git, embeddings). It is categorised as a Execute tool in the Engram MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Engram MCP server in PolicyLayer and add a rule for rebuild_index: 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 Engram. Nothing to install.
rebuild_index is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the rebuild_index 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 rebuild_index. 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.
rebuild_index is provided by the Engram MCP server (tinydarkforge/engram). 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 →