List available functions grouped by server. Each entry includes the function name and its description. Use the returned name value as the property name on the codemode object when writing code for sandbox_eval_js, and as the tool_name argument when calling sandbox_get_function_schema.\n\nFunction...
AI agents call sandbox_get_functions to retrieve information from Code Mode Bridge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a discovery/introspection tool that queries metadata about available functions. It performs a read-only operation with no side effects, does not modify or delete data, and does not execute code or trigger external operations. The returned information is used to inform subsequent actions but the tool itself only retrieves schema/catalog information.
From the tool's definition Tool lists available functions grouped by server with their names and descriptions. The description explicitly states it 'List available functions' and returns metadata about available functions.
Attacks that exploit this kind of access
List available functions grouped by server. Each entry includes the function name and its description. Use the returned name value as the property name on the codemode object when writing code for sandbox_eval_js, and as the tool_name argument when calling sandbox_get_function_schema.\n\nFunction names follow the pattern serverName__functionName, where a double underscore separates the server namespace from the original function name. For example, a function called list_items on a server named inventory becomes inventory__list_items.\n\nResults are paginated. The first call returns the first page. If the response includes a nextCursor value, pass it as the cursor parameter to retrieve the next page. It is categorised as a Read tool in the Code Mode Bridge MCP Server, which means it retrieves data without modifying state.
Register the Code Mode Bridge MCP server in PolicyLayer and add a rule for sandbox_get_functions: 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 Code Mode Bridge. Nothing to install.
sandbox_get_functions is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the sandbox_get_functions 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 sandbox_get_functions. 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.
sandbox_get_functions is provided by the Code Mode Bridge MCP server (ruifung/mcp-cm-bridge). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →