Unsafe eval() Enables Remote Code Execution in MCP Calculator

MCP Calculate Server is a mathematical calculation service based on MCP protocol and SymPy library. Prior to 0.1.1, the use of eval() to evaluate mathematical expressions without proper input sanitization leads to remote code execution. This vulnerability is fixed in 0.1.1.

Casky was already ahead

This CVE exploits attack patterns that Casky's 301matched skills already investigate — long before this vulnerability was disclosed. Claude's reasoning model maps these techniques to MITRE ATT&CK, so practitioners who ran these skills have already seen the threat behaviour in their findings.

Analysis

MCP Calculate Server versions prior to 0.1.1 suffer from a critical remote code execution vulnerability (CVSS 9.8) due to unsafe use of Python's eval() function when processing mathematical expressions. The service fails to sanitize user input before passing it to eval(), allowing attackers to inject arbitrary Python code that executes with the privileges of the server process. This affects any organization deploying MCP Calculate Server as part of their infrastructure, particularly those using it in data processing pipelines, automated calculation services, or integrated development environments where untrusted user input may reach the calculator.

Casky's 301 mapped skills leverage Claude's extended reasoning to detect the attack patterns underlying this vulnerability across both initial access (TA0001) and resource development (TA0043) phases. Practitioners using Casky would identify suspicious patterns such as mathematical expressions containing Python syntax (import statements, function definitions, or shell commands embedded in calc parameters), anomalous process spawning from the MCP service, unexpected file system access, or network connections initiated from the calculator process. Claude's reasoning capabilities enable detection of obfuscated payloads and code injection techniques that might bypass signature-based detection, while Casky's MITRE ATT&CK mapping connects observable indicators directly to adversary tactics—helping security teams understand not just *that* an exploit occurred, but *why* it represents a critical threat to their environment.

Live Threat IntelligenceComing soon

Casky Risk Score

—

EPSS Probability

—

Shodan Exposure

—

GreyNoise Signal

—

Composite risk scoring from EPSS, CISA KEV, Shodan, and GreyNoise — 21 security APIs correlated into a single Casky Risk Score. Coming in Casky Pro. Join early access →

301 Casky skills cover this attack pattern

These skills use Claude AI's reasoning model to surface findings in the same attack categories as CVE-2026-44717.

analyzing-apt-group-with-mitre-navigator

threat intelligence · low

Run

analyzing-campaign-attribution-evidence

threat intelligence · low

Run

analyzing-certificate-transparency-for-phishing

threat intelligence · low

Run

MITRE ATT&CK Techniques

TA0001 TA0043

Investigate the attack patterns behind CVE-2026-44717

Casky has 301 skills that investigate the attack patterns behind CVE-2026-44717. Run one and get CVSS-scored findings in 3 minutes.

Run the skill that detects this →

X Instagram LinkedIn