AI agents invoke index_repair to trigger actions in Work Memory MCP Server. 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.
Index repair triggers an active repair/rebuild operation on the storage index, which is an execution of a maintenance process rather than a simple read or write. It modifies internal index structures and validates processes, making it Execute. Misuse could corrupt or destabilize the search/storage system, warranting high severity.
From the tool's definition '인덱스를 수동으로 복구하고 인덱싱 프로세스를 검증합니다' — manually repairs missing indexes and validates indexing processes
Documented attack patterns abuse exactly the kind of access index_repair gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Work Memory MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for index_repair:
{
"version": "1",
"default": "deny",
"tools": {
"index_repair": {
"limits": [
{
"counter": "index_repair_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}index_repair stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
누락된 인덱스를 수동으로 복구하고 인덱싱 프로세스를 검증합니다. It is categorised as a Execute tool in the Work Memory MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Work Memory MCP Server MCP server in PolicyLayer and add a rule for index_repair: 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 Work Memory MCP Server. Nothing to install.
index_repair 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 index_repair 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_repair. 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_repair is provided by the Work Memory MCP Server MCP server (moontmsai/work-memory-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Work Memory MCP Server, 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.
24 Work Memory MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.