Skip to main content
Glama
devlimelabs

MCP Environment & Installation Manager

by devlimelabs

localize-mcp-server

Configure and install MCP servers locally using specific packages and settings from a configuration file.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
configPathYesPath to configuration file
serverNameYesName of the server in the configuration
packageNameYesPackage name to use

Implementation Reference

  • Handler function for the 'localize-mcp-server' tool. Performs input validation (non-empty strings) and delegates the core logic to watcherService.updateServerConfig, returning success response or throwing errors.
      async ({ configPath, serverName, packageName }, extra) => {
        if (!configPath.trim()) {
          throw new Error("Config path cannot be empty");
        }
        
        if (!serverName.trim()) {
          throw new Error("Server name cannot be empty");
        }
        
        if (!packageName.trim()) {
          throw new Error("Package name cannot be empty");
        }
        
        const result = await watcherService.updateServerConfig(configPath, serverName, packageName);
        
        if (!result.success) {
          throw new Error(`Failed to update server configuration: ${result.error}`);
        }
        
        return {
          content: [
            {
              type: "text",
              text: JSON.stringify({
                success: true,
                configPath,
                serverName,
                packageName
              }, null, 2)
            }
          ]
        };
      }
    );
  • Zod input schema defining the required parameters: configPath (string), serverName (string), packageName (string).
    {
      configPath: z.string().describe("Path to configuration file"),
      serverName: z.string().describe("Name of the server in the configuration"),
      packageName: z.string().describe("Package name to use")
    },
  • MCP server tool registration call for 'localize-mcp-server', specifying input schema and inline handler function.
    server.tool(
      "localize-mcp-server",
      {
        configPath: z.string().describe("Path to configuration file"),
        serverName: z.string().describe("Name of the server in the configuration"),
        packageName: z.string().describe("Package name to use")
      },
      async ({ configPath, serverName, packageName }, extra) => {
        if (!configPath.trim()) {
          throw new Error("Config path cannot be empty");
        }
        
        if (!serverName.trim()) {
          throw new Error("Server name cannot be empty");
        }
        
        if (!packageName.trim()) {
          throw new Error("Package name cannot be empty");
        }
        
        const result = await watcherService.updateServerConfig(configPath, serverName, packageName);
        
        if (!result.success) {
          throw new Error(`Failed to update server configuration: ${result.error}`);
        }
        
        return {
          content: [
            {
              type: "text",
              text: JSON.stringify({
                success: true,
                configPath,
                serverName,
                packageName
              }, null, 2)
            }
          ]
        };
      }
    );
  • Supporting method in WatcherService that implements the core localization logic: verifies package installation, parses and updates MCP config to point to local bin/dist/index.js, persists changes, updates caches and references.
    async updateServerConfig(
      configPath: string,
      serverName: string,
      packageName: string
    ): Promise<ConfigUpdateResult> {
      try {
        // Check if package is installed
        const installedPackage = this.packageManager.getInstalledPackage(packageName);
        if (!installedPackage) {
          return {
            success: false,
            configPath,
            serverName,
            packageName,
            error: `Package not installed: ${packageName}`
          };
        }
        
        // Read the config file
        const config = await readJsonFileOrDefault<McpConfig>(configPath, { mcpServers: {} });
        
        // Check if server exists
        if (!config.mcpServers || !config.mcpServers[serverName]) {
          return {
            success: false,
            configPath,
            serverName,
            packageName,
            error: `Server not found in config: ${serverName}`
          };
        }
        
        // Update the command to use the local package
        const server = config.mcpServers[serverName];
        
        // If bin path exists, use that
        if (installedPackage.binPath) {
          server.command = 'node';
          server.args = [installedPackage.binPath];
        } else {
          // Otherwise, use node with the package's main file
          server.command = 'node';
          server.args = [path.join(installedPackage.localPath, 'dist/index.js')];
        }
        
        // Write the updated config
        await fs.writeFile(configPath, JSON.stringify(config, null, 2));
        
        // Update the cache
        this.configCache.set(configPath, config);
        
        // Add config reference
        await this.packageManager.addConfigReference(packageName, {
          path: configPath,
          platform: this.getPlatformForConfig(configPath),
          serverName
        });
        
        return {
          success: true,
          configPath,
          serverName,
          packageName
        };
      } catch (error) {
        return {
          success: false,
          configPath,
          serverName,
          packageName,
          error: error instanceof Error ? error.message : String(error)
        };
      }
    }
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/devlimelabs/mcp-env-manager-mcp'

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