AI agents use rag_index to create or update resources in Ragi — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ragi environment.
Indexing is a Write operation: it processes source files and creates or updates stored embeddings/index structures. It does not delete existing data (so not Destructive), does not execute code, and has no financial impact. Misuse could cause unwanted indexing of sensitive files or corruption of an existing index, warranting medium severity.
From the tool's definition 'Index files/directories for the specified project' — this tool reads files from disk and writes/creates index entries (embeddings, metadata) in a local RAG store.
Attacks that exploit this kind of access
Index files/directories for the specified project. It is categorised as a Write tool in the Ragi MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ragi MCP server in PolicyLayer and add a rule for rag_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 Ragi. Nothing to install.
rag_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 rag_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 rag_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.
rag_index is provided by the Ragi MCP server (susutawar/ragi). 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 →