Deploy OCA repos from buffer to target (rsync). Only in buffered mode.
AI agents invoke oca_deploy to trigger actions in Odoo Claude MCP. 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.
This tool executes a deployment operation (rsync) that modifies filesystem state on a target system. While not immediately destructive (rsync by default doesn't delete), it irreversibly propagates code/configuration changes to target infrastructure. An AI agent could misuse this to push malicious code to production systems, corrupt deployments, or create denial-of-service conditions.
From the tool's definition Tool description states 'Deploy OCA repos from buffer to target (rsync)' — rsync is a file synchronization command that executes on remote systems to copy/update files.
Documented attack patterns abuse exactly the kind of access oca_deploy 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 oca_deploy:
{
"version": "1",
"default": "deny",
"tools": {
"oca_deploy": {
"limits": [
{
"counter": "oca_deploy_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} oca_deploy 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.
Deploy OCA repos from buffer to target (rsync). Only in buffered mode. It is categorised as a Execute tool in the Odoo Claude MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Odoo Claude MCP server in PolicyLayer and add a rule for oca_deploy: 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.
oca_deploy 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 oca_deploy 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 oca_deploy. 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.
oca_deploy 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.