Skip to main content
Glama
devlimelabs

MCP Troubleshooter

by devlimelabs

read-mcp-logs

Extract and analyze the latest logs from an MCP server to diagnose and troubleshoot issues by specifying the number of lines and server name for targeted insights.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
linesNoNumber of lines to read from the end
serverNameNoSpecific server name to filter logs for

Implementation Reference

  • The async handler function that implements the core logic of the 'read-mcp-logs' tool. It reads MCP log files from the platform-specific log directory, filters for mcp*.log files, optionally filters by serverName, reads the last 'lines' number of lines from each, concatenates them with headers, and returns as markdown text content.
    async ({ lines, serverName }) => {
      try {
        // Ensure log directory exists
        try {
          await fs.access(logDirectory);
        } catch (error) {
          return {
            isError: true,
            content: [{ type: "text", text: `Log directory not found at ${logDirectory}. Claude Desktop might not be installed or hasn't generated logs yet.` }]
          };
        }
    
        // Get all log files
        const files = await fs.readdir(logDirectory);
        
        // Filter for MCP logs
        const mcpLogs = files.filter(file => file.startsWith("mcp"));
        
        if (mcpLogs.length === 0) {
          return {
            content: [{ type: "text", text: "No MCP log files found in the log directory." }]
          };
        }
    
        // Further filter for specific server if requested
        const targetLogs = serverName 
          ? mcpLogs.filter(file => file.includes(serverName))
          : mcpLogs;
        
        if (targetLogs.length === 0 && serverName) {
          return {
            content: [{ type: "text", text: `No logs found for server name '${serverName}'.` }]
          };
        }
    
        // Read and concatenate log content
        let combinedLogs = "";
        for (const logFile of targetLogs) {
          const filePath = path.join(logDirectory, logFile);
          try {
            let content = await fs.readFile(filePath, 'utf-8');
            
            // Get last N lines
            const allLines = content.split('\n');
            const lastLines = allLines.slice(-lines).join('\n');
            
            combinedLogs += `\n---- ${logFile} ----\n${lastLines}\n\n`;
          } catch (error) {
            combinedLogs += `\n---- ${logFile} ----\nError reading file: ${error.message}\n\n`;
          }
        }
    
        return {
          content: [{ type: "text", text: combinedLogs || "Log files exist but are empty." }]
        };
      } catch (error) {
        return {
          isError: true,
          content: [{ type: "text", text: `Error reading logs: ${error.message}` }]
        };
      }
    }
  • Zod input schema defining the parameters for the 'read-mcp-logs' tool: optional 'lines' (default 100) and optional 'serverName' for filtering.
    {
      lines: z.number().optional().default(100).describe("Number of lines to read from the end"),
      serverName: z.string().optional().describe("Specific server name to filter logs for")
    },
  • src/index.ts:64-132 (registration)
    Registration of the 'read-mcp-logs' tool on the MCP server using server.tool(), including name, input schema, and handler function.
    server.tool(
      "read-mcp-logs",
      {
        lines: z.number().optional().default(100).describe("Number of lines to read from the end"),
        serverName: z.string().optional().describe("Specific server name to filter logs for")
      },
      async ({ lines, serverName }) => {
        try {
          // Ensure log directory exists
          try {
            await fs.access(logDirectory);
          } catch (error) {
            return {
              isError: true,
              content: [{ type: "text", text: `Log directory not found at ${logDirectory}. Claude Desktop might not be installed or hasn't generated logs yet.` }]
            };
          }
    
          // Get all log files
          const files = await fs.readdir(logDirectory);
          
          // Filter for MCP logs
          const mcpLogs = files.filter(file => file.startsWith("mcp"));
          
          if (mcpLogs.length === 0) {
            return {
              content: [{ type: "text", text: "No MCP log files found in the log directory." }]
            };
          }
    
          // Further filter for specific server if requested
          const targetLogs = serverName 
            ? mcpLogs.filter(file => file.includes(serverName))
            : mcpLogs;
          
          if (targetLogs.length === 0 && serverName) {
            return {
              content: [{ type: "text", text: `No logs found for server name '${serverName}'.` }]
            };
          }
    
          // Read and concatenate log content
          let combinedLogs = "";
          for (const logFile of targetLogs) {
            const filePath = path.join(logDirectory, logFile);
            try {
              let content = await fs.readFile(filePath, 'utf-8');
              
              // Get last N lines
              const allLines = content.split('\n');
              const lastLines = allLines.slice(-lines).join('\n');
              
              combinedLogs += `\n---- ${logFile} ----\n${lastLines}\n\n`;
            } catch (error) {
              combinedLogs += `\n---- ${logFile} ----\nError reading file: ${error.message}\n\n`;
            }
          }
    
          return {
            content: [{ type: "text", text: combinedLogs || "Log files exist but are empty." }]
          };
        } catch (error) {
          return {
            isError: true,
            content: [{ type: "text", text: `Error reading logs: ${error.message}` }]
          };
        }
      }
    );
  • Platform-specific helper function getLogDirectory() used by the tool to determine the MCP logs path based on OS (Windows, macOS, Linux). Called globally at line 44 to set logDirectory.
    const getLogDirectory = () => {
      const platform = os.platform();
      if (platform === "win32") {
        return path.join(os.homedir(), "AppData", "Roaming", "Claude", "logs");
      } else if (platform === "darwin") {
        return path.join(os.homedir(), "Library", "Logs", "Claude");
      } else {
        return path.join(os.homedir(), ".local", "share", "Claude", "logs");
      }
    };
Install Server

Other Tools

Related 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/devlimelabs/mcp-troubleshooter-mcp'

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