Skip to main content
Glama
nulab

Backlog MCP Server

add_project

Creates a new project in Backlog with a name and key, supporting optional settings for chart, subtasking, and text formatting.

Instructions

Creates a new project

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesProject name
keyYesProject key
chartEnabledNoWhether to enable chart (default: false)
subtaskingEnabledNoWhether to enable subtasking (default: false)
projectLeaderCanEditProjectLeaderNoWhether project leaders can edit other project leaders (default: false)
textFormattingRuleNoText formatting rule (default: 'backlog')
organizationNoOptional organization name. Use list_organizations to inspect available organizations.

Implementation Reference

  • The main implementation of the 'add_project' tool. Defines the schema (input validation via Zod) and the handler function that calls backlog.postProject() to create a new project. The handler accepts name, key, chartEnabled, subtaskingEnabled, projectLeaderCanEditProjectLeader, and textFormattingRule with defaults.
    import { z } from 'zod';
    import { Backlog } from 'backlog-js';
    import { buildToolSchema, ToolDefinition } from '../types/tool.js';
    import { TranslationHelper } from '../createTranslationHelper.js';
    import { ProjectSchema } from '../types/zod/backlogOutputDefinition.js';
    
    const addProjectSchema = buildToolSchema((t) => ({
      name: z.string().describe(t('TOOL_ADD_PROJECT_NAME', 'Project name')),
      key: z.string().describe(t('TOOL_ADD_PROJECT_KEY', 'Project key')),
      chartEnabled: z
        .boolean()
        .optional()
        .describe(
          t(
            'TOOL_ADD_PROJECT_CHART_ENABLED',
            'Whether to enable chart (default: false)'
          )
        ),
      subtaskingEnabled: z
        .boolean()
        .optional()
        .describe(
          t(
            'TOOL_ADD_PROJECT_SUBTASKING_ENABLED',
            'Whether to enable subtasking (default: false)'
          )
        ),
      projectLeaderCanEditProjectLeader: z
        .boolean()
        .optional()
        .describe(
          t(
            'TOOL_ADD_PROJECT_LEADER_CAN_EDIT',
            'Whether project leaders can edit other project leaders (default: false)'
          )
        ),
      textFormattingRule: z
        .enum(['backlog', 'markdown'])
        .optional()
        .describe(
          t(
            'TOOL_ADD_PROJECT_TEXT_FORMATTING',
            "Text formatting rule (default: 'backlog')"
          )
        ),
    }));
    
    export const addProjectTool = (
      backlog: Backlog,
      { t }: TranslationHelper
    ): ToolDefinition<
      ReturnType<typeof addProjectSchema>,
      (typeof ProjectSchema)['shape']
    > => {
      return {
        name: 'add_project',
        description: t('TOOL_ADD_PROJECT_DESCRIPTION', 'Creates a new project'),
        schema: z.object(addProjectSchema(t)),
        outputSchema: ProjectSchema,
        handler: async ({
          name,
          key,
          chartEnabled,
          subtaskingEnabled,
          projectLeaderCanEditProjectLeader,
          textFormattingRule,
        }) =>
          backlog.postProject({
            name,
            key,
            chartEnabled: chartEnabled ?? false,
            subtaskingEnabled: subtaskingEnabled ?? false,
            projectLeaderCanEditProjectLeader:
              projectLeaderCanEditProjectLeader ?? false,
            textFormattingRule: textFormattingRule ?? 'backlog',
          }),
      };
    };
  • ToolDefinition type and buildToolSchema helper, used to define the structure of the add_project tool (name, description, schema, outputSchema, handler).
    export type ToolDefinition<
      Shape extends z.ZodRawShape,
      OutputShape extends z.ZodRawShape,
    > = {
      name: string;
      description: string;
      schema: z.ZodObject<Shape>;
      outputSchema: z.ZodObject<OutputShape>;
      handler: (
        input: z.infer<z.ZodObject<Shape>> & {
          fields?: string;
          organization?: string;
        }
      ) => Promise<
        z.infer<z.ZodObject<OutputShape>> | z.infer<z.ZodObject<OutputShape>>[]
      >;
      importantFields?: (keyof z.infer<z.ZodObject<OutputShape>>)[];
    };
  • The ProjectSchema Zod schema, which serves as the outputSchema for the add_project tool, defining the shape of a Backlog project object returned by the handler.
    export const ProjectSchema = z.object({
      id: z.number(),
      projectKey: z.string(),
      name: z.string(),
      chartEnabled: z.boolean(),
      useResolvedForChart: z.boolean(),
      subtaskingEnabled: z.boolean(),
      projectLeaderCanEditProjectLeader: z.boolean(),
      useWiki: z.boolean(),
      useFileSharing: z.boolean(),
      useWikiTreeView: z.boolean(),
      useOriginalImageSizeAtWiki: z.boolean(),
      useSubversion: z.boolean(),
      useGit: z.boolean(),
      textFormattingRule: TextFormattingRuleSchema,
      archived: z.boolean(),
      displayOrder: z.number(),
      useDevAttributes: z.boolean(),
    });
  • src/tools/tools.ts:6-6 (registration)
    Import of addProjectTool from './addProject.js'.
    import { addProjectTool } from './addProject.js';
  • Registration of the add_project tool within the 'project' toolset group. addProjectTool(backlog, helper) is added to the tools array.
    addProjectTool(backlog, helper),
Behavior2/5

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

No annotations provided, and the description lacks any behavioral information such as idempotency, permissions required, or side effects. It only states the action without detailing what 'creates' implies.

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 very concise, consisting of a single sentence. It is front-loaded but could benefit from more detail given the tool's complexity. Still, it is efficient with no unnecessary words.

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?

With 7 parameters including several booleans and an enum, the tool is moderately complex. The description fails to provide high-level context about the project creation process, how the options affect the project, or what the output might be.

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 each parameter. The description adds no additional meaning or context about parameter relationships or defaults beyond what is in the schema.

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

Purpose3/5

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

Description states 'Creates a new project', which is clear verb+resource. However, it does not differentiate from sibling creation tools like add_issue or addDocument, leaving ambiguity about which entity is created.

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?

No guidance on when to use this tool versus alternatives. The description does not mention context or prerequisites, such as needing an existing workspace or organization.

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/nulab/backlog-mcp-server'

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