Claude MarketplacesSubmit
mastrophot avatar

Contract Security Scanner

mastrophot/near-mcp-contract-security

Brings smart contract security scanning into Claude with heuristic analysis for Solidity, Rust, and TypeScript contracts. Exposes three tools: scan_contract checks for reentrancy, integer overflow, access control flaws, front-running vectors, and oracle manipulation risks, returning a vulnerability list with severity ratings and line numbers. compare_security_models and audit_checklist generate language-specific security guidance. The scanner includes NEAR-specific context, scoring contracts against NEAR's security model and providing cross-chain migration recommendations. Install globally via npm and point Claude Desktop at the mcp-contract-security command. Useful when reviewing contract code during development or audits, especially if you're evaluating patterns across EVM and NEAR ecosystems.

tools
3
transport
STDIO
last updated
Mar 16, 2026
View on GitHub

Tools

3 tools

Public tool metadata for what this MCP can expose to an agent.

scan_contractScans contract source code for heuristic security patterns such as reentrancy, integer overflow/underflow risk, access control issues, front-running exposure, and oracle manipulation risk.

Scans contract source code for heuristic security patterns such as reentrancy, integer overflow/underflow risk, access control issues, front-running exposure, and oracle manipulation risk.

No parameter schema in public metadata yet.

compare_security_modelsCompares security models for the given language (optional input).

Compares security models for the given language (optional input).

No parameter schema in public metadata yet.

audit_checklistReturns an audit checklist for the given language (optional input).

Returns an audit checklist for the given language (optional input).

No parameter schema in public metadata yet.

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Readme

mcp-contract-security

MCP server for smart contract security scanning.

Implements the required tools:

  • scan_contract
  • compare_security_models
  • audit_checklist

Supports languages:

  • solidity
  • rust
  • typescript

What it checks

scan_contract currently detects heuristic patterns for:

  • Reentrancy
  • Integer overflow/underflow risk
  • Access control issues
  • Front-running exposure
  • Oracle manipulation risk

The output includes:

  • vulnerability list with severity/type/line
  • security_score
  • near_equivalent_score
  • NEAR-specific security notes and recommendation

Install

npm install -g mcp-contract-security

Published package:

MCP config (Claude Desktop)

{
  "mcpServers": {
    "contract-security": {
      "command": "mcp-contract-security"
    }
  }
}

Tool usage

scan_contract

Input:

{
  "code": "contract source code here",
  "language": "solidity"
}

compare_security_models

Input (optional):

View the full README on GitHub

Details

Repository
github.com/mastrophot/near-mcp-contract-security
Category
Security & Pentesting
Package
mcp-contract-security
Transport
STDIO
Registry
MCP registry, active

More from mastrophot

Related Security & Pentesting MCP servers

View all
1viridis-security avatarInjection Detectorviridis-security/mcp-services-sdkFormally-verified injection/exfiltration detector for AI agents (MCP-02).0stars
2weiseer avatarcve-cacheweiseer/cve-cache-mcpRecent CVE + GHSA cache for AI agents auditing dependencies (npm/PyPI/Cargo/Maven/Go).0stars
3shrike-security avatarShrikeshrike-security/shrike-mcpGoverns what AI agents do: tool calls, SQL, commands, files checked against policy before they run.2stars
4promptguardhq avatarPromptGuardpromptguardhq/promptguardScan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client0stars
5egoughnour avatarCode Firewall Mcpegoughnour/code-firewall-mcpStructural similarity-based code filter. Stops malicious code pattern reaching execution tools.0stars
6kloudle avatarKloudle Cloud Security Scannerio.github.kloudle/cloud-security-scannerAWS cloud security scanners for AI agents — S3, IAM, EC2, EKS, RDS, CloudTrail, CloudWatch Logs0stars