Git pull all OCA repos in the working directory (recursive).
AI agents invoke oca_update 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 git pull operation across all OCA repositories recursively. It triggers an external operation (network fetch + merge) that modifies the working directory contents.
From the tool's definition Git pull all OCA repos in the working directory (recursive)
Documented attack patterns abuse exactly the kind of access oca_update 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_update:
{
"version": "1",
"default": "deny",
"tools": {
"oca_update": {
"limits": [
{
"counter": "oca_update_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} oca_update 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.
Git pull all OCA repos in the working directory (recursive). 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_update: 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_update 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_update 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_update. 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_update 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.