Skip to main content
Glama
GoCoder7
by GoCoder7

coolify_application_management

Manage Coolify applications: deploy, monitor status, start/stop/restart services, create new applications, and list existing ones through unified commands.

Instructions

Comprehensive application management: deploy, get info, list, check status, start/stop/restart, or create applications

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYesAction to perform on applications
applicationIdNoApplication ID (required for most actions except list/create)
forceNoForce deployment even if another is in progress
branchNoGit branch to deploy
serverIdNoFilter applications by server ID
statusNoFilter by application status
nameNoApplication name (for create action)
descriptionNoApplication description (for create action)
git_repositoryNoGit repository URL (for create action)
git_branchNoGit branch (for create action)
build_packNoBuild pack to use (for create action)

Implementation Reference

  • The primary handler function that implements all logic for the coolify_application_management tool, using a switch statement on the 'action' parameter to call appropriate Coolify API methods.
    export async function handleApplicationManagement(
      coolifyClient: CoolifyApiClient,
      args: any
    ): Promise<any> {
      try {
        const { action, applicationId, ...params } = args;
        let result;
        let message;
    
        switch (action) {
          case 'deploy':
            if (!applicationId) throw new Error('applicationId is required for deploy action');
            result = await coolifyClient.deployApplication(applicationId, {
              force: params.force,
              branch: params.branch
            });
            message = `Deployment triggered for application ${applicationId}`;
            break;
    
          case 'get':
            if (!applicationId) throw new Error('applicationId is required for get action');
            result = await coolifyClient.getApplication(applicationId);
            message = `Retrieved application ${applicationId}`;
            break;
    
          case 'list':
            result = await coolifyClient.getApplications();
            // Filter locally if parameters provided
            if (params.serverId || params.status) {
              result = result.filter((app: any) => {
                if (params.serverId && app.serverId !== params.serverId) return false;
                if (params.status && app.status !== params.status) return false;
                return true;
              });
            }
            message = `Found ${result.length} applications`;
            break;
    
          case 'status':
            if (!applicationId) throw new Error('applicationId is required for status action');
            result = await coolifyClient.getApplicationStatus(applicationId);
            message = `Retrieved status for application ${applicationId}`;
            break;
    
          case 'start':
            if (!applicationId) throw new Error('applicationId is required for start action');
            result = await coolifyClient.startApplication(applicationId);
            message = `Started application ${applicationId}`;
            break;
    
          case 'stop':
            if (!applicationId) throw new Error('applicationId is required for stop action');
            result = await coolifyClient.stopApplication(applicationId);
            message = `Stopped application ${applicationId}`;
            break;
    
          case 'restart':
            if (!applicationId) throw new Error('applicationId is required for restart action');
            result = await coolifyClient.restartApplication(applicationId);
            message = `Restarted application ${applicationId}`;
            break;
    
          case 'create':
            if (!params.name || !params.git_repository || !params.serverId) {
              throw new Error('name, git_repository, and serverId are required for create action');
            }
            result = await coolifyClient.createApplication({
              name: params.name,
              description: params.description,
              git_repository: params.git_repository,
              git_branch: params.git_branch,
              build_pack: params.build_pack,
            });
            message = `Created application ${params.name}`;
            break;
    
          default:
            throw new Error(`Unknown application action: ${action}`);
        }
    
        return {
          content: [
            {
              type: 'text',
              text: JSON.stringify({
                success: true,
                data: result,
                message: message
              }, null, 2)
            }
          ]
        };
      } catch (error) {
        return {
          content: [
            {
              type: 'text',
              text: JSON.stringify({
                success: false,
                error: error instanceof Error ? error.message : 'Unknown error occurred'
              }, null, 2)
            }
          ],
          isError: true
        };
      }
    }
  • The Tool object definition including the name, description, and detailed inputSchema for parameter validation and documentation.
    export const applicationManagementTool: Tool = {
      name: 'coolify_application_management',
      description: 'Comprehensive application management: deploy, get info, list, check status, start/stop/restart, or create applications',
      inputSchema: {
        type: 'object',
        properties: {
          action: {
            type: 'string',
            enum: ['deploy', 'get', 'list', 'status', 'start', 'stop', 'restart', 'create'],
            description: 'Action to perform on applications',
          },
          applicationId: {
            type: 'string',
            description: 'Application ID (required for most actions except list/create)',
          },
          // Deploy parameters
          force: {
            type: 'boolean',
            description: 'Force deployment even if another is in progress',
            default: false,
          },
          branch: {
            type: 'string',
            description: 'Git branch to deploy',
          },
          // List parameters
          serverId: {
            type: 'string',
            description: 'Filter applications by server ID',
          },
          status: {
            type: 'string',
            enum: ['running', 'stopped', 'building', 'error'],
            description: 'Filter by application status',
          },
          // Create parameters
          name: {
            type: 'string',
            description: 'Application name (for create action)',
          },
          description: {
            type: 'string',
            description: 'Application description (for create action)',
          },
          git_repository: {
            type: 'string',
            description: 'Git repository URL (for create action)',
          },
          git_branch: {
            type: 'string',
            description: 'Git branch (for create action)',
          },
          build_pack: {
            type: 'string',
            description: 'Build pack to use (for create action)',
          },
        },
        required: ['action'],
      },
    };
  • src/index.ts:125-134 (registration)
    Registration of the tool in the MCP server's list tools request handler, making the schema available to clients.
    this.server.setRequestHandler(ListToolsRequestSchema, async () => {
      return {
        tools: [
          applicationManagementTool,
          environmentConfigurationTool,
          systemManagementTool,
          documentationTool,
        ],
      };
    });
  • src/index.ts:150-152 (registration)
    Dispatch registration in the MCP tool call request handler switch statement, routing calls to the specific handler function.
    case 'coolify_application_management':
      return await handleApplicationManagement(this.coolifyClient, args);
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. While it lists actions, it doesn't explain what each action actually does, their side effects, authentication requirements, rate limits, or error conditions. For example, it doesn't clarify whether 'deploy' overwrites existing deployments or what 'force' actually forces. This is inadequate for a multi-action mutation tool with 11 parameters.

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

Conciseness4/5

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

The description is efficiently structured as a single sentence listing all available actions. It's appropriately sized for a multi-function tool, though it could be more front-loaded by grouping related actions (e.g., 'deploy and manage applications: create, list, get info, check status, start/stop/restart'). Every word earns its place.

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

Completeness2/5

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

For a complex tool with 11 parameters, multiple actions (including mutations like deploy, create, stop), no annotations, and no output schema, the description is insufficient. It doesn't explain what the tool returns, error conditions, prerequisites, or the relationships between actions and parameters. The agent would struggle to use this tool correctly without trial and error.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents all 11 parameters thoroughly with descriptions and enums. The description adds no additional parameter semantics beyond what's in the schema - it doesn't explain relationships between parameters (e.g., which parameters apply to which actions) or provide usage examples. The baseline of 3 is appropriate when the schema does all the work.

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

Purpose4/5

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

The description clearly states the tool performs comprehensive application management with specific verbs (deploy, get info, list, check status, start/stop/restart, create). It distinguishes itself from sibling tools by focusing specifically on applications rather than documentation, environment configuration, or system management. However, it doesn't explicitly differentiate between the various actions within the tool itself.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus its siblings (coolify_documentation, coolify_environment_configuration, coolify_system_management). It also doesn't indicate when to use specific actions within the tool (e.g., when to use 'deploy' vs 'create', or when 'force' parameter is appropriate). The agent must infer usage from parameter descriptions alone.

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/GoCoder7/coolify-mcp-server'

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