proxy_call
Forward a tool call to an internal MCP sub-service.
This record as markdown: /tools/rosenvladimirov-odoo-claude-mcp/proxy-call.md
What proxy_call does on Odoo Claude MCP
AI agents invoke proxy_call 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.
Why proxy_call is rated High
A proxy/forwarding tool that dispatches calls to internal sub-services has an unbounded blast radius. It can effectively execute any operation available on those sub-services, including destructive or financial ones, depending on what arguments are passed.
From the tool's definition "Forward a tool call to an internal MCP sub-service" — acts as a proxy/dispatcher that can invoke arbitrary internal tools
Attacks that exploit this kind of access
The rule that runs proxy_call safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Odoo Claude MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For proxy_call, this is the rule to start with:
proxy_call 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Odoo Claude MCP, apply this rule, and every proxy_call call is checked against it from then on.
Questions about proxy_call
Forward a tool call to an internal MCP sub-service. 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 proxy_call: 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.
proxy_call 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 proxy_call 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 proxy_call. 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.
proxy_call 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.
More on Odoo Claude, and thousands of servers like it.
Across the catalogue