Hydrate JSONL telemetry from a Claude Code project sessions directory into the brain. Non-blocking: queues processing via setImmediate and returns immediately. Idempotent — already-hydrated files are skipped.
AI agents use atelier_hydrate to create or update resources in Mybrain — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mybrain environment.
This tool ingests/imports telemetry data into the knowledge base (PostgreSQL with pgvector). It creates new records from JSONL files, making it a Write operation. The idempotency and skipping of already-hydrated files reduce risk somewhat, but bulk ingestion of external telemetry data into a personal knowledge base carries medium severity — an agent could flood the brain with unwanted or malicious data.
From the tool's definition Hydrate JSONL telemetry from a Claude Code project sessions directory into the brain... queues processing via setImmediate and returns immediately. Idempotent — already-hydrated files are skipped.
Documented attack patterns abuse exactly the kind of access atelier_hydrate gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mybrain, and nothing reaches the server without passing your rules. This is the rule we recommend for atelier_hydrate:
{
"version": "1",
"default": "deny",
"tools": {
"atelier_hydrate": {
"limits": [
{
"counter": "atelier_hydrate_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}atelier_hydrate 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.
Hydrate JSONL telemetry from a Claude Code project sessions directory into the brain. Non-blocking: queues processing via setImmediate and returns immediately. Idempotent — already-hydrated files are skipped. It is categorised as a Write tool in the Mybrain MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mybrain MCP server in PolicyLayer and add a rule for atelier_hydrate: 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 Mybrain. Nothing to install.
atelier_hydrate 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 atelier_hydrate 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 atelier_hydrate. 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.
atelier_hydrate is provided by the Mybrain MCP server (robertsfeir/mybrain). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mybrain, 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.
8 Mybrain tools catalogued and risk-classified — across an index of 43,000+ MCP servers.