Skip to main content
Glama

projects

Manage Coolify projects: list, get, create, update, delete, and control environments and resources.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
operationYesOperation to perform
idNoProject UUID
environmentNameOrUuidNoEnvironment name or UUID (for environment operation)
bodyNoJSON request body

Implementation Reference

  • The main handler function for the 'projects' tool. Routes operations (list, get, create, update, delete, environment, resources) to the corresponding generated SDK functions via safeApiCall.
    export async function projectsHandler(args: ProjectsToolArgs) {
      const { operation, id, environmentNameOrUuid, body } = args;
      
      switch (operation) {
        case 'list':
          return await safeApiCall(() => listProjects());
          
        case 'get':
          if (!id) throw new Error('ID required for get operation');
          return await safeApiCall(() => getProjectByUuid({ path: { uuid: id } }));
          
        case 'create':
          if (!body) throw new Error('Body required for create operation');
          const createData = JSON.parse(body);
          return await safeApiCall(() => createProject({ body: createData }));
          
        case 'update':
          if (!id || !body) throw new Error('ID and body required for update operation');
          const updateData = JSON.parse(body);
          return await safeApiCall(() => updateProjectByUuid({ 
            path: { uuid: id }, 
            body: updateData 
          } as any));
          
        case 'delete':
          if (!id) throw new Error('ID required for delete operation');
          return await safeApiCall(() => deleteProjectByUuid({ path: { uuid: id } }));
          
        case 'environment':
          if (!id || !environmentNameOrUuid) throw new Error('ID and environmentNameOrUuid required for environment operation');
          return await safeApiCall(() => getEnvironmentByNameOrUuid({ 
            path: { 
              uuid: id, 
              environment_name_or_uuid: environmentNameOrUuid 
            } 
          }));
          
        case 'resources':
          return await safeApiCall(() => listResources());
          
        default:
          throw new Error(`Unknown operation: ${operation}`);
      }
    }
  • Registers the 'projects' tool with the MCP server, defining the Zod schema (operation enum, optional id/environmentNameOrUuid/body) and calling projectsHandler.
    server.tool(
      'projects',
      {
        operation: z.enum([
          'list', 'get', 'create', 'update', 'delete', 'environment', 'resources'
        ]).describe("Operation to perform"),
        id: z.string().optional().describe("Project UUID"),
        environmentNameOrUuid: z.string().optional().describe("Environment name or UUID (for environment operation)"),
        body: z.string().optional().describe("JSON request body")
      },
      async ({ operation, id, environmentNameOrUuid, body }) => {
        try {
          console.error('Projects tool received args:', JSON.stringify({ operation, id, environmentNameOrUuid, body }, null, 2));
          
          const result = await projectsHandler({ 
            operation, 
            id, 
            environmentNameOrUuid, 
            body 
          });
          return {
            content: [{ 
              type: 'text', 
              text: JSON.stringify(result, null, 2) 
            }]
          };
        } catch (error) {
          return {
            content: [{ 
              type: 'text', 
              text: `Error: ${error instanceof Error ? error.message : String(error)}` 
            }],
            isError: true
          };
        }
      }
    );
  • TypeScript interface defining the input schema for the projects handler: operation, id, environmentNameOrUuid, body.
    interface ProjectsToolArgs {
      operation: string;
      id?: string;
      environmentNameOrUuid?: string;
      body?: string;
    }
  • Auto-generated SDK function listProjects that makes a GET request to /projects.
    export const listProjects = <ThrowOnError extends boolean = false>(options?: Options<ListProjectsData, ThrowOnError>) => {
        return (options?.client ?? _heyApiClient).get<ListProjectsResponses, ListProjectsErrors, ThrowOnError>({
            security: [
                {
                    scheme: 'bearer',
                    type: 'http'
                }
            ],
            url: '/projects',
            ...options
        });
    };
  • The safeApiCall wrapper used by projectsHandler to execute API calls with error handling.
    export async function safeApiCall<T>(apiCall: () => Promise<T>): Promise<T> {
      try {
        return await apiCall();
      } catch (error) {
        return handleApiError(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/FelixAllistar/coolify-mcp'

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