Skip to main content
Glama
0xGval
by 0xGval

auditContract

Analyze Ethereum smart contracts for security vulnerabilities and code quality issues. Enter a contract address to receive detailed audit results including potential risks and recommendations.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
addressYes
chainNoeth

Implementation Reference

  • The core asynchronous handler function for the 'auditContract' tool. It initializes Web3, analyzes the contract address using helper functions, formats the results into MCP content format, and handles errors.
    async ({ address, chain }) => {
      try {
        // Use the web3 instance from the environment variable or default public node
        console.error('Creating Web3 instance with URL:', process.env.ETH_RPC_URL);
        const web3 = new Web3(process.env.ETH_RPC_URL || 'https://eth.llamarpc.com');
        
        // Perform the contract analysis
        console.error('Analyzing address:', address);
        const result = await analyzeAddress(web3, address);
        
        // Format the output for MCP response
        return {
          content: [{ 
            type: "text", 
            text: formatAnalysisResults(result)
          }]
        };
      } catch (error) {
        console.error('Error in auditContract:', error);
        return {
          content: [{ 
            type: "text", 
            text: `Error analyzing contract: ${error.message}`
          }]
        };
      }
    }
  • Zod-based input schema validating the 'address' parameter as a 42-character Ethereum address starting with 0x, and optional 'chain' parameter defaulting to 'eth'.
    { 
      address: z.string().regex(/^0x[a-fA-F0-9]{40}$/, "Invalid Ethereum address"),
      chain: z.string().optional().default("eth")
    },
  • tools/audit.js:19-55 (registration)
    The registerAuditTool exported function that registers the 'auditContract' tool on the MCP server instance using server.tool, providing the schema and handler.
    export function registerAuditTool(server) {
      console.error('Registering audit tool...');
      server.tool("auditContract",
        { 
          address: z.string().regex(/^0x[a-fA-F0-9]{40}$/, "Invalid Ethereum address"),
          chain: z.string().optional().default("eth")
        },
        async ({ address, chain }) => {
          try {
            // Use the web3 instance from the environment variable or default public node
            console.error('Creating Web3 instance with URL:', process.env.ETH_RPC_URL);
            const web3 = new Web3(process.env.ETH_RPC_URL || 'https://eth.llamarpc.com');
            
            // Perform the contract analysis
            console.error('Analyzing address:', address);
            const result = await analyzeAddress(web3, address);
            
            // Format the output for MCP response
            return {
              content: [{ 
                type: "text", 
                text: formatAnalysisResults(result)
              }]
            };
          } catch (error) {
            console.error('Error in auditContract:', error);
            return {
              content: [{ 
                type: "text", 
                text: `Error analyzing contract: ${error.message}`
              }]
            };
          }
        }
      );
      console.error('Audit tool registered successfully');
    }
  • main.js:63-63 (registration)
    Invocation of registerAuditTool during MCP server initialization, which executes the tool registration.
    registerAuditTool(server);
  • Primary helper function orchestrating the contract audit: address validation, contract detection, creation info, Etherscan verification, standard detection (ERC20/721/1155), bytecode analysis, basic security heuristics, and result compilation.
    async function analyzeAddress(web3, address) {
      try {
        // Validate address
        if (!web3.utils.isAddress(address)) {
          throw new Error('Invalid Ethereum address format');
        }
    
        // Clean and format the address
        const formattedAddress = web3.utils.toChecksumAddress(address);
        
        // Step 1: Check if address is a contract
        const isContract = await checkIfContract(web3, formattedAddress);
        
        let result = {
          address: formattedAddress,
          isContract: isContract,
          isVerified: false,
          contractName: null,
          contractCreator: null,
          creationTx: null,
          creationTimestamp: null,
          contractCode: null,
          sourceCode: null,
          abi: null,
          error: null
        };
    
        // If not a contract, return early
        if (!isContract) {
          result.error = 'Address is not a contract';
          
          // Check ETH balance
          const balance = await web3.eth.getBalance(formattedAddress);
          result.ethBalance = web3.utils.fromWei(balance, 'ether');
          
          // Check transaction count
          const txCount = await web3.eth.getTransactionCount(formattedAddress);
          result.transactionCount = txCount;
          
          return result;
        }
        
        // Get creation info
        const creationInfo = await getContractCreationInfo(formattedAddress);
        if (creationInfo) {
          result.contractCreator = creationInfo.contractCreator;
          result.creationTx = creationInfo.txHash;
          result.creationTimestamp = creationInfo.timestamp;
        }
        
        // Step 2: Check if contract is verified on Etherscan
        const verificationInfo = await checkIfVerified(formattedAddress);
        result.isVerified = verificationInfo.isVerified;
        
        // Get bytecode regardless of verification status
        const bytecode = await web3.eth.getCode(formattedAddress);
        result.contractCode = bytecode;
        
        // Step 3: If verified, get contract code and ABI
        if (verificationInfo.isVerified) {
          result.sourceCode = verificationInfo.sourceCode;
          result.contractName = verificationInfo.contractName;
          result.abi = verificationInfo.abi;
    
          // Check contract interfaces/standards (ERC20, ERC721, etc.)
          result.standards = await detectContractStandards(formattedAddress, verificationInfo.abi);
        } else {
          result.error = 'Contract is not verified on Etherscan';
          
          // Attempt to detect contract type from bytecode
          result.probableType = await detectContractTypeFromBytecode(bytecode);
        }
        
        // Add security analysis if verified (basic heuristics)
        if (verificationInfo.isVerified && verificationInfo.sourceCode) {
          result.securityAnalysis = analyzeContractSecurity(verificationInfo.sourceCode);
        }
        
        return result;
        
      } catch (error) {
        console.error('Error analyzing address:', error);
        return {
          address: address,
          isContract: false,
          isVerified: false,
          contractCode: null,
          sourceCode: null,
          error: error.message
        };
      }
    }
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/0xGval/evm-mcp-tools'

If you have feedback or need assistance with the MCP directory API, please join our Discord server