AI agents use project_index to create or update resources in Ensemble — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ensemble environment.
The tool builds or refreshes an index, which is a write operation that creates or modifies stored index data. It is reversible (the index can be rebuilt), so it does not qualify as Destructive. Misuse could cause incorrect indexing of the codebase, but the blast radius is moderate since it affects search/discovery rather than source data directly.
From the tool's definition Build or refresh the codebase index for faster Scope exploration
Attacks that exploit this kind of access
Build or refresh the codebase index for faster Scope exploration. It is categorised as a Write tool in the Ensemble MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ensemble MCP server in PolicyLayer and add a rule for project_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 Ensemble. Nothing to install.
project_index 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 project_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 project_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.
project_index is provided by the Ensemble MCP server (lynkbyte/ensemble). 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 →