evaluate_pipeline

THE RISK

High Risk

Why evaluate_pipeline needs a policy

This tool executes mathematical operations in a pipeline where outputs feed into subsequent operations. While the operations are mathematical rather than shell commands, the ability to execute sequences of expressions that depend on prior results and involve variable substitution constitutes Execute-category risk.

From the tool's definition Tool description states 'Execute a sequence of mathematical operations' and processes expressions with variable substitution ($LAST). The word 'Execute' directly indicates code/operation execution.

Documented attack patterns abuse exactly the kind of access evaluate_pipeline gives an agent:

POLICY

How to control evaluate_pipeline

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Calc Tools, and nothing reaches the server without passing your rules. This is the rule we recommend for evaluate_pipeline:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "evaluate_pipeline": {
      "limits": [
        {
          "counter": "evaluate_pipeline_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

evaluate_pipeline stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register MCP Calc Tools — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More MCP Calc Tools tools

Execute fourier_transform Numerical approximation of the Fourier transform F(ω) = ∫ f(t)·e^(-iωt) dt. Provide expres Execute find_root Find root of f(x)=0 using Newton-Raphson method. Provide the expression, variable, and ini Execute riemann_sum Numerical definite integration using Riemann sums. Methods: left, right, midpoint (default Read laplace_transform Numerical approximation of the Laplace transform F(s) = ∫₀^∞ f(t)·e^(-st) dt. Provide expr Read binomial_distribution Calculate binomial probability P(X=k) for exactly k successes in n trials with success pro Read black_scholes Price a European option using Black-Scholes formula. Returns the option premium as a numbe Read derivative Calculate the symbolic derivative of a mathematical expression. Returns the derivative as Read describe_available_tools Find the right tool for your math or finance problem. Describe your goal in natural langua

All 22 MCP Calc Tools tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in MCP Calc Tools → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about evaluate_pipeline

What does the evaluate_pipeline tool do? +

Execute a sequence of mathematical operations where $LAST in an expression is replaced by the previous result. Currently supports op. It is categorised as a Execute tool in the MCP Calc Tools MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on evaluate_pipeline? +

Register the MCP Calc Tools MCP server in PolicyLayer and add a rule for evaluate_pipeline: 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 MCP Calc Tools. Nothing to install.

What risk level is evaluate_pipeline? +

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

Can I rate-limit evaluate_pipeline? +

Yes. Add a rate_limit block to the evaluate_pipeline 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 evaluate_pipeline completely? +

Set action: deny in the PolicyLayer policy for evaluate_pipeline. 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 evaluate_pipeline? +

evaluate_pipeline is provided by the MCP Calc Tools MCP server (nbiish/mcp-calc-tools). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP Calc Tools tool call.

Start from MCP Calc Tools, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →