One-time repair: rebuild vector index from SQLite memories.
AI agents invoke rebuild_vectors to trigger actions in Robust Long-Term Memory MCP. 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.
Rebuilding a vector index is an Execute-class operation: it runs a repair/reconstruction process that modifies the ChromaDB vector index state. While it reads from SQLite as the source of truth, the primary effect is recomputing and overwriting the existing vector index. It is not purely destructive (source data in SQLite is preserved), but it does overwrite the current vector index contents.
From the tool's definition 'rebuild vector index from SQLite memories' — triggers a rebuild/repair operation on the vector index (ChromaDB), which is an external operation that modifies the vector store's state
Documented attack patterns abuse exactly the kind of access rebuild_vectors gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Robust Long-Term Memory MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for rebuild_vectors:
{
"version": "1",
"default": "deny",
"tools": {
"rebuild_vectors": {
"limits": [
{
"counter": "rebuild_vectors_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}rebuild_vectors 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.
One-time repair: rebuild vector index from SQLite memories. It is categorised as a Execute tool in the Robust Long-Term Memory MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Robust Long-Term Memory MCP server in PolicyLayer and add a rule for rebuild_vectors: 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 Robust Long-Term Memory MCP. Nothing to install.
rebuild_vectors 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 rebuild_vectors 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 rebuild_vectors. 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.
rebuild_vectors is provided by the Robust Long-Term Memory MCP server (rotoslider/long-term-memory-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 11 Robust Long-Term Memory MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
11 Robust Long-Term Memory MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.