List recent index runs for a vault — what was scanned, when, how long, errors.
AI agents call index_runs to retrieve information from Vault Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure read operation that queries audit/status information about the vault's indexing process. It has no side effects, makes no modifications, executes no code, and poses minimal risk. The information returned is metadata about past operations, not the operations themselves.
From the tool's definition The tool 'index_runs' lists metadata about past index operations: 'what was scanned, when, how long, errors.' It retrieves historical indexing information without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
List recent index runs for a vault — what was scanned, when, how long, errors. It is categorised as a Read tool in the Vault Memory MCP Server, which means it retrieves data without modifying state.
Register the Vault Memory MCP server in PolicyLayer and add a rule for index_runs: 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 Vault Memory. Nothing to install.
index_runs is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the index_runs 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 index_runs. 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.
index_runs is provided by the Vault Memory MCP server (owrede/vault-memory). 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 →