compute_kerb_run
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. Linear precast concrete kerb run on concrete bed and haunch over Type 1 (Class 1A) granular su...
This record as markdown: /tools/com-civilquants-civilquants/compute-kerb-run.md
What compute_kerb_run does on Civilquants
AI agents call compute_kerb_run to retrieve information from Civilquants without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
params | object | Yes | Input parameters for a kerb run assembly. Geometric defaults match a standard UK HB2 road kerb on 150mm concrete bed over 150mm Type 1 sub-base, with triangula |
standard | string | — | |
output_mode | string | — | |
deliverables | object | — |
Parameters from the server's own tool schema.
Why compute_kerb_run is rated Low
This is a parametric estimating/computation tool that calculates and emits bill-of-quantities line items for a kerb run assembly. It reads inputs and outputs cost/quantity data — it does not write to a database, execute code, delete data, or move money. The 'paid tier' gate is an authentication concern, not a financial transaction made by the tool itself.
From the tool's definition Paid tier only... Emits excavation, sub-base... concrete bed, kerb units... disposal. Supports HB2/HB1/SP/BN/EF/ER kerb profiles
Risk signalsHigh parameter count (16 properties)
Attacks that exploit this kind of access
The rule that runs compute_kerb_run safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Civilquants, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For compute_kerb_run, this is the rule to start with:
compute_kerb_run 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 Civilquants, apply this rule, and every compute_kerb_run call is checked against it from then on.
Questions about compute_kerb_run
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. Linear precast concrete kerb run on concrete bed and haunch over Type 1 (Class 1A) granular sub-base. Emits excavation, sub-base (v8 SHW-class-aware), concrete bed, kerb units to BS EN 1340 / SHW Cl. 1101, concrete haunch to back face, optional channel block, and disposal. Supports HB2/HB1/SP/BN/EF/ER kerb profiles and CS1/CS2/dish channels. All four standards render with type designators (CESMM4 R.7, NRM2 34.10, MMHW 1100, SMM7 Q10). Example params: kerb_length=25 m (1–1000), bed_thickness_mm=150 mm (75–300), bed_extra_each_side_mm=100 mm (0–300). Example call: {"params": {"kerb_length": 25, "bed_thickness_mm": 150, "bed_extra_each_side_mm": 100}, "standard": "MMHW"}. Omitted parameters use sensible engineering defaults. Pass deliverables=["xlsx","dxf","pdf"] (any subset) to also receive one-shot download URLs in the same call: Excel BoQ (both tiers, watermarked free) plus the dimensioned DXF (CAD) and PDF drawing sheets (paid tier). It is categorised as a Read tool in the Civilquants MCP Server, which means it retrieves data without modifying state.
compute_kerb_run accepts 4 parameters: params, standard, output_mode, deliverables. Required: params. The full parameter table on this page comes from the server's own tool schema.
Register the Civilquants MCP server in PolicyLayer and add a rule for compute_kerb_run: 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_kerb_run 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 compute_kerb_run 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_kerb_run. 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_kerb_run 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.
More on Civilquants, and thousands of servers like it.
This server
Across the catalogue