Repair detected index issues by re-indexing missing files and removing orphaned vectors.
AI agents use repair_index to create or update resources in MCP Codebase Index — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Codebase Index environment.
The tool modifies the index by re-indexing files (write) and removing orphaned vectors (deletion of stale/invalid entries). While it does remove vectors, 'orphaned vectors' implies data that no longer corresponds to valid files, making this more of a maintenance/repair operation than a destructive one targeting intentionally kept data.
From the tool's definition re-indexing missing files and removing orphaned vectors
Documented attack patterns abuse exactly the kind of access repair_index gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Codebase Index, and nothing reaches the server without passing your rules. This is the rule we recommend for repair_index:
{
"version": "1",
"default": "deny",
"tools": {
"repair_index": {
"limits": [
{
"counter": "repair_index_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} repair_index stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Repair detected index issues by re-indexing missing files and removing orphaned vectors. It is categorised as a Write tool in the MCP Codebase Index MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Codebase Index MCP server in PolicyLayer and add a rule for repair_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 MCP Codebase Index. Nothing to install.
repair_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 repair_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 repair_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.
repair_index is provided by the MCP Codebase Index MCP server (ngotaico/mcp-codebase-index). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Codebase Index, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
9 MCP Codebase Index tools catalogued and risk-classified — across an index of 43,000+ MCP servers.