High Risk →

compute_ditch

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_manhole. Linear primary measurement of an open earthwork drainage channel — trapezoidal cross-section, four lin...

Risk signalsHigh parameter count (11 properties)

Part of the Civilquants server.

compute_ditch can trigger actions in Civilquants, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE CIVILQUANTS →

Free to start. No card required.

AI agents invoke compute_ditch to trigger processes or run actions in Civilquants. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.

compute_ditch can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.

Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "compute_ditch": {
      "limits": [
        {
          "counter": "compute_ditch_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

See the full Civilquants policy for all 52 tools.

Get this rule live on your own Civilquants server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY CIVILQUANTS →

View all 52 tools →

These attack patterns abuse exactly the kind of access compute_ditch gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so compute_ditch only ever does what you allow.

SECURE CIVILQUANTS →

Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

What does the compute_ditch tool do? +

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_manhole. Linear primary measurement of an open earthwork drainage channel — trapezoidal cross-section, four lining variants (unlined / geotextile / granular / concrete). Routes via CESMM4 Class E.4 (excavation for cuttings), NRM2 Group 34.10 (site works: open drains and ditches), MMHW Series 500.4 (SHW Cl. 514 Earthwork ditches and drains), SMM7 R13.4 (Land Drainage — ditches). Eight variant presets cover all four lining types x two characteristic size scenarios each. Unit: M. Second member of the drainage_ancillaries L2 leaf (opened at S32 with connection_to_existing). 20th use of the classed-then-legacy attribute discrimination pattern via the lining_type discriminator. The four standards genuinely diverge on which work-section heading owns ditches (Class E vs Group 34 vs Series 500 vs R13) — the platform renders all four honestly from one source WorkItem. Example params: run_length_m=100 m (1–1000), top_width_mm=1700 mm (200–10000), bottom_width_mm=500 mm (100–5000). Example call: {"params": {"run_length_m": 100, "top_width_mm": 1700, "bottom_width_mm": 500}, "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.. It is categorised as a Execute tool in the Civilquants MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on compute_ditch? +

Register the Civilquants MCP server in PolicyLayer and add a rule for compute_ditch: 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.

What risk level is compute_ditch? +

compute_ditch is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit compute_ditch? +

Yes. Add a rate_limit block to the compute_ditch 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.

How do I block compute_ditch completely? +

Set action: deny in the PolicyLayer policy for compute_ditch. 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.

What MCP server provides compute_ditch? +

compute_ditch 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.

Enforce policy on every Civilquants tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.