Create a new Request For Information (RFI) in an ACC project via the APS Construction RFIs API. RFI is created in 'draft' status — the project workflow owner typically transitions it to 'submitted'. When to use: The user needs a formal question-of-record to the design or GC team — e.g. 'raise an ...
Part of the ACC MCP server.
Free to start. No card required.
AI agents use acc_create_rfi to create or modify resources in ACC MCP. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call acc_create_rfi repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach ACC MCP.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"acc_create_rfi": {
"limits": [
{
"counter": "acc_create_rfi_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full ACC MCP policy for all 9 tools.
These attack patterns abuse exactly the kind of access acc_create_rfi gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Create a new Request For Information (RFI) in an ACC project via the APS Construction RFIs API. RFI is created in 'draft' status — the project workflow owner typically transitions it to 'submitted'. When to use: The user needs a formal question-of-record to the design or GC team — e.g. 'raise an RFI asking for clarification on the Level 2 beam schedule'. RFIs are the auditable channel for clarifications; issues are for field observations. When NOT to use: Do not use for informal observations (use acc_create_issue) or to answer an existing RFI (not supported here). APS scopes: data:read data:write account:read. Rate limits: APS default ~50 req/min per endpoint per app. RFIs share the Construction API umbrella with issues (~100 req/min combined). Errors: 401 (APS token expired — refresh); 403 (user lacks RFI create permission on project); 404 (project_id not found — verify 'b.' prefix and hub membership); 422 (validation — subject/question missing or priority enum invalid); 429 (rate limit — back off 60s); 5xx (ACC upstream — retry with jitter, check for duplicate before retrying). Side effects: Creates a persistent RFI record. NOT idempotent — retry on 5xx risks duplicates; dedupe by subject before retrying.. It is categorised as a Write tool in the ACC MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ACC MCP server in PolicyLayer and add a rule for acc_create_rfi: 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 ACC MCP. Nothing to install.
acc_create_rfi is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the acc_create_rfi 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 acc_create_rfi. 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.
acc_create_rfi is provided by the ACC MCP server (https://acc-mcp.itmartin24.workers.dev/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 9 ACC MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.