Pull shared memory file(s) into your personal storage.
AI agents use memory_pull to create or update resources in Odoo Claude MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Odoo Claude MCP environment.
This tool copies/moves shared memory files into personal storage, which constitutes a write operation — it creates or modifies data in the user's personal storage area. The action is likely reversible (files can be deleted), so it doesn't qualify as Destructive.
From the tool's definition Pull shared memory file(s) into your personal storage
Documented attack patterns abuse exactly the kind of access memory_pull gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Odoo Claude MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for memory_pull:
{
"version": "1",
"default": "deny",
"tools": {
"memory_pull": {
"limits": [
{
"counter": "memory_pull_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} memory_pull 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.
Pull shared memory file(s) into your personal storage. It is categorised as a Write tool in the Odoo Claude MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Odoo Claude MCP server in PolicyLayer and add a rule for memory_pull: 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 Odoo Claude MCP. Nothing to install.
memory_pull 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 memory_pull 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 memory_pull. 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.
memory_pull is provided by the Odoo Claude MCP server (rosenvladimirov/odoo-claude-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Odoo Claude MCP, 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.
180 Odoo Claude MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.