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");
      }
    };
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

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