Re-embed memories to fix stale embeddings (e.g. after content updates or after enabling semantic search). Optionally filter by category, id list, or re-embed all memories.
AI agents invoke crow_regenerate_embeddings to trigger actions in Crow. 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.
Regenerating embeddings is an Execute-class operation: it triggers a computational pipeline (embedding model inference) over stored memories and updates their vector representations.
From the tool's definition 'Re-embed memories' and 'fix stale embeddings' indicate running a computational process (embedding generation) over stored data, triggered as an external operation that transforms existing memory records
Documented attack patterns abuse exactly the kind of access crow_regenerate_embeddings gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Crow, and nothing reaches the server without passing your rules. This is the rule we recommend for crow_regenerate_embeddings:
{
"version": "1",
"default": "deny",
"tools": {
"crow_regenerate_embeddings": {
"limits": [
{
"counter": "crow_regenerate_embeddings_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}crow_regenerate_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.
Re-embed memories to fix stale embeddings (e.g. after content updates or after enabling semantic search). Optionally filter by category, id list, or re-embed all memories. It is categorised as a Execute tool in the Crow MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Crow MCP server in PolicyLayer and add a rule for crow_regenerate_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 Crow. Nothing to install.
crow_regenerate_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 crow_regenerate_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 crow_regenerate_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.
crow_regenerate_embeddings is provided by the Crow MCP server (kh0pper/crow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Crow, 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.
576 Crow tools catalogued and risk-classified — across an index of 43,000+ MCP servers.