Get details of a specific control (formula cell, button, date picker...) in a Coda document. Args: - doc_id (string): The document ID - control_id (string): The control ID or name - response_format:
AI agents call coda_get_control to retrieve information from Coda MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about a control element in a Coda document. It is a read-only query operation with no side effects. The most severe action on the sibling tool list is destructive (coda_delete_doc, coda_delete_page, coda_delete_row), but this specific tool only reads. Blast radius if misused is minimal—an agent could learn document structure but cannot alter or destroy data.
From the tool's definition Tool description: 'Get details of a specific control (formula cell, button, date picker...)' — uses 'Get' which retrieves data. The arguments accept identifiers (doc_id, control_id) to fetch control metadata.
Attacks that exploit this kind of access
Get details of a specific control (formula cell, button, date picker...) in a Coda document. Args: - doc_id (string): The document ID - control_id (string): The control ID or name - response_format:. It is categorised as a Read tool in the Coda MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Coda MCP Server MCP server in PolicyLayer and add a rule for coda_get_control: 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 Coda MCP Server. Nothing to install.
coda_get_control 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 coda_get_control 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 coda_get_control. 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.
coda_get_control is provided by the Coda MCP Server MCP server (thierryvm/coda-mcp-server). 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 →