get_intake_schema
Return the field spec for spreadsheet-driven site creation: the shared brand-profile + FAQ fields a project needs (create_project), and the per-site copy fields YOU (the assistant) must generate (create_sites). Call this FIRST when the user gives you an intake spreadsheet (.xlsx) so you know exac...
This record as markdown: /tools/a3plus-mcp/get-intake-schema.md
What get_intake_schema does on A3plus
AI agents call get_intake_schema to retrieve information from A3plus without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why get_intake_schema is rated Low
Even though get_intake_schema only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs get_intake_schema safely
PolicyLayer is an MCP gateway: it sits between your AI agents and A3plus, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_intake_schema, this is the rule to start with:
get_intake_schema is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect A3plus, apply this rule, and every get_intake_schema call is checked against it from then on.
Questions about get_intake_schema
Return the field spec for spreadsheet-driven site creation: the shared brand-profile + FAQ fields a project needs (create_project), and the per-site copy fields YOU (the assistant) must generate (create_sites). Call this FIRST when the user gives you an intake spreadsheet (.xlsx) so you know exactly which fields to extract and which to write. WORKFLOW: read the sheet → for each FAQ row, the customer-confirmed column wins over the draft column, BUT a short confirmation like "OK"/"Good" means "use the draft", and a correction note means "merge draft + note into the final answer" (use judgement). Then YOU generate each site's ~13 copy fields (hero/about/features/…) and pick a pack per site from list_packs — the A3Plus backend does NOT run any copy-generation AI; that work is yours. It is categorised as a Read tool in the A3plus MCP Server, which means it retrieves data without modifying state.
Register the A3plus MCP server in PolicyLayer and add a rule for get_intake_schema: 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 A3plus. Nothing to install.
get_intake_schema 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 get_intake_schema 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 get_intake_schema. 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.
get_intake_schema is provided by the A3plus MCP server (a3plus-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on A3plus, and thousands of servers like it.
This server
Across the catalogue