Paid tier only. Calling this without an authenticated CivilQuants account returns TIER_INSUFFICIENT — sign up at https://civilquants.com/pricing or use the free-tier alternative compute_cantilever_wall. In-situ reinforced concrete counterfort retaining wall. Discrete RC counterforts on the retain...
Risk signalsHigh parameter count (34 properties)
Part of the Civilquants server.
Free to start. No card required.
AI agents use compute_counterfort_wall to create or modify resources in Civilquants. 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 compute_counterfort_wall 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 Civilquants.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"compute_counterfort_wall": {
"limits": [
{
"counter": "compute_counterfort_wall_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Civilquants policy for all 52 tools.
These attack patterns abuse exactly the kind of access compute_counterfort_wall 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.
Paid tier only. Calling this without an authenticated CivilQuants account returns TIER_INSUFFICIENT — sign up at https://civilquants.com/pricing or use the free-tier alternative compute_cantilever_wall. In-situ reinforced concrete counterfort retaining wall. Discrete RC counterforts on the retained face enhance moment capacity, making the wall economic for 4-10m retained heights (above cantilever-economic range, below anchored-wall range). Includes base slab, thin curtain wall, counterforts at configurable centres, drainage, and backfill. Eight VARIANT_PRESETS exercise the 'one parameter form, eight variants, four standards' moat #1 claim. Routes via wall_type='counterfort' attribute discrimination: CESMM4 F.6.3, NRM2 11.3.3, MMHW 1700.4.2 (SHW Cl. 1704), SMM7 E10.3.2. Example params: stem_height=5 m (3–12), curtain_thickness=0.35 m (0.2–0.6), toe_length=0.6 m (0–3). Example call: {"params": {"stem_height": 5, "curtain_thickness": 0.35, "toe_length": 0.6}, "standard": "MMHW"}. Omitted parameters use sensible engineering defaults. Pass deliverables=["xlsx"] to also receive a one-shot Excel BoQ download URL in the same call. Pass freeboard (clearance below the wall top, m) instead of the retained-height field to set the retained fill by clearance — the engine back-calculates it as stem − freeboard. Supplying both is rejected.. It is categorised as a Write tool in the Civilquants MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Civilquants MCP server in PolicyLayer and add a rule for compute_counterfort_wall: 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 Civilquants. Nothing to install.
compute_counterfort_wall 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 compute_counterfort_wall 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 compute_counterfort_wall. 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.
compute_counterfort_wall is provided by the Civilquants MCP server (https://api.civilquants.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 52 Civilquants 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.