Share personal memory file(s) — copies to shared storage
AI agents use memory_share 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.
The tool copies files from personal storage to shared storage, which is a write/create operation. It makes data available to other users or processes, which could expose sensitive information if misused. It is reversible in principle (files can be deleted from shared storage), so it does not qualify as Destructive.
From the tool's definition Share personal memory file(s) — copies to shared storage
Documented attack patterns abuse exactly the kind of access memory_share 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_share:
{
"version": "1",
"default": "deny",
"tools": {
"memory_share": {
"limits": [
{
"counter": "memory_share_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} memory_share 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.
Share personal memory file(s) — copies to shared 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_share: 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_share 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_share 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_share. 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_share 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.