AI agents invoke backfill_embeddings to trigger actions in Mnemex. 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.
The name 'backfill_embeddings' suggests a batch operation that computes and writes vector embeddings for existing memories, likely modifying stored data. With no description available, confidence is low. Given the context of a memory management server with temporal decay algorithms, this likely triggers a computation/write process over existing records.
From the tool's definition Tool name 'backfill_embeddings' and empty description.
Documented attack patterns abuse exactly the kind of access backfill_embeddings gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mnemex, and nothing reaches the server without passing your rules. This is the rule we recommend for backfill_embeddings:
{
"version": "1",
"default": "deny",
"tools": {
"backfill_embeddings": {
"limits": [
{
"counter": "backfill_embeddings_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}backfill_embeddings 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.
backfill_embeddings. It is categorised as a Execute tool in the Mnemex MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mnemex MCP server in PolicyLayer and add a rule for backfill_embeddings: 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 Mnemex. Nothing to install.
backfill_embeddings 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 backfill_embeddings 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 backfill_embeddings. 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.
backfill_embeddings is provided by the Mnemex MCP server (prefrontal-systems/cortexgraph). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 13 Mnemex tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
13 Mnemex tools catalogued and risk-classified — across an index of 42,500+ MCP servers.