Skip to main content
Glama
tmhr1850

Backlog MCP Server

createIssue

Add new issues to Backlog projects for task tracking and management. Use this tool to create project items and organize work.

Instructions

課題の追加

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • Generic handler function for all MCP tools defined in endpoints. For 'createIssue', it uses path 'issues', POST method, validates input params like projectId, summary, issueTypeId etc., calls fetchFromBacklog to create the issue via Backlog API, and returns the created issue JSON.
    const handler = async (params: Record<string, unknown>): Promise<McpResponse> => {
      try {
        // パラメータのバリデーション
        const validatedParams = await endpoint.schema.parseAsync(params);
    
        // URL中のプレースホルダーを置換
        let path = endpoint.path;
        
        // URIスキーム(例:space://info)の場合はBacklog APIのパスに変換
        if (path.includes('://')) {
          // URIスキームを取り除いてAPIパスに変換
          const uriParts = path.split('://');
          const resourceType = uriParts[0];
          const resourcePath = uriParts[1];
          
          // リソースタイプに応じてAPIパスを構築
          switch (resourceType) {
            case 'space':
              path = 'space';
              break;
            case 'projects':
              if (resourcePath === 'list') {
                path = 'projects';
              } else {
                path = `projects/${resourcePath}`;
              }
              break;
            case 'issues':
              if (resourcePath.includes('/list')) {
                const projectPart = resourcePath.split('/')[0];
                path = 'issues';
                validatedParams.projectIdOrKey = projectPart;
              } else if (resourcePath.includes('/details')) {
                const issuePart = resourcePath.split('/')[0];
                path = `issues/${issuePart}`;
              }
              break;
            case 'wikis':
              if (resourcePath.includes('/list')) {
                const projectPart = resourcePath.split('/')[0];
                path = 'wikis';
                validatedParams.projectIdOrKey = projectPart;
              }
              break;
            case 'users':
              path = 'users';
              break;
            default:
              path = resourcePath;
          }
        }
        
        // 通常のパスパラメータの置換処理
        for (const [key, value] of Object.entries(validatedParams)) {
          if (typeof value === "string" || typeof value === "number") {
            const placeholder = `{${key}}`;
            if (path.includes(placeholder)) {
              path = path.replace(placeholder, String(value));
              // プレースホルダーとして使用したパラメータは削除
              delete validatedParams[key];
            }
          }
        }
    
        // メソッドの追加
        if (endpoint.method !== "GET") {
          validatedParams.method = endpoint.method;
        }
    
        // APIリクエストの実行
        const data = await fetchFromBacklog(path, validatedParams);
        return {
          content: [{ 
            type: "text" as const, 
            text: JSON.stringify(data, null, 2) 
          }],
        };
      } catch (error: any) {
        // エラーメッセージの整形
        const errorMessage = error.errors 
          ? `バリデーションエラー: ${JSON.stringify(error.errors)}`
          : `エラー: ${error.message}`;
    
        return {
          content: [{ 
            type: "text" as const, 
            text: errorMessage 
          }],
          isError: true,
        };
      }
    };
  • Input schema for createIssue tool using Zod, defining required fields like projectId, summary, issueTypeId and optional fields like priorityId, dates.
    {
      name: "createIssue",
      description: "課題の追加",
      path: "issues",
      method: "POST",
      schema: z.object({
        projectId: projectIdSchema,
        summary: summarySchema,
        description: descriptionSchema,
        issueTypeId: issueTypeIdSchema,
        priorityId: priorityIdSchema,
        startDate: dateFormatSchema,
        dueDate: dateFormatSchema,
      }),
      type: "tool",
    },
  • Code block that registers the tool with MCP server.tool(), called in loop for each endpoint including createIssue.
    if (endpoint.type === "tool") {
      // ツールの登録
      server.tool(
        endpoint.name,
        endpoint.description,
        async (args: Record<string, unknown>) => handler(args)
      );
  • Core helper function that sends HTTP POST request to Backlog API /issues endpoint with form data to actually create the issue.
    export async function fetchFromBacklog(
      endpoint: string,
      params: Record<string, any> = {}
    ): Promise<any> {
      try {
        // 環境変数のバリデーション
        const domain = process.env.BACKLOG_DOMAIN?.trim();
        const apiKey = process.env.BACKLOG_API_KEY?.trim();
        
        if (!domain || !apiKey) {
          throw new Error(
            "環境変数BACKLOG_DOMAINまたはBACKLOG_API_KEYが設定されていません"
          );
        }
    
        // パラメータのサニタイズ
        const sanitizedParams = Object.fromEntries(
          Object.entries(params).map(([key, value]) => [
            key,
            typeof value === "string" ? value.trim() : value
          ])
        );
    
        // エンドポイントのパスパラメータを置換
        let processedEndpoint = endpoint;
        if (endpoint.includes("{")) {
          // {issueId}のようなパスパラメータを実際の値で置換
          const matches = endpoint.match(/\{([^}]+)\}/g) || [];
          for (const match of matches) {
            const paramName = match.slice(1, -1); // {issueId} -> issueId
            if (sanitizedParams[paramName]) {
              processedEndpoint = processedEndpoint.replace(
                match,
                sanitizedParams[paramName]
              );
              delete sanitizedParams[paramName]; // URLに埋め込んだパラメータは削除
            } else {
              throw new Error(`パスパラメータ ${paramName} が指定されていません`);
            }
          }
        }
    
        // URLの構築
        const url = new URL(`https://${domain}/api/v2/${processedEndpoint}`);
        url.searchParams.append("apiKey", apiKey);
    
        // メソッドの判定
        const method = sanitizedParams.method || (endpoint.toLowerCase().includes("post") ? "POST" : "GET");
        delete sanitizedParams.method; // methodパラメータは削除
    
        // リクエストオプションの準備
        const options: RequestInit = {
          method,
          headers: {
            "User-Agent": "Backlog-MCP-Server/1.0.0",
            "Accept": "application/json"
          }
        };
    
        // POSTリクエストの場合はボディにパラメータを設定
        if (method === "POST") {
          // POSTリクエストの場合はFormDataを使用(Backlog APIの仕様に合わせる)
          const formData = new URLSearchParams();
          for (const [key, value] of Object.entries(sanitizedParams)) {
            if (value !== undefined && value !== null) {
              // 配列の場合は複数のパラメータとして追加
              if (Array.isArray(value)) {
                value.forEach(item => {
                  formData.append(`${key}[]`, String(item));
                });
              } else {
                formData.append(key, String(value));
              }
            }
          }
          options.body = formData.toString();
          options.headers = {
            ...options.headers,
            "Content-Type": "application/x-www-form-urlencoded"
          };
        } else {
          // GETリクエストの場合はURLにパラメータを追加
          for (const [key, value] of Object.entries(sanitizedParams)) {
            if (value !== undefined && value !== null) {
              // 配列の場合は複数のパラメータとして追加
              if (Array.isArray(value)) {
                value.forEach(item => {
                  url.searchParams.append(`${key}[]`, String(item));
                });
              } else {
                url.searchParams.append(key, String(value));
              }
            }
          }
        }
    
        // デバッグ情報(開発時のみ使用)
        if (process.env.NODE_ENV === 'development') {
          console.log(`[DEBUG] リクエスト: ${method} ${url.toString()}`);
          if (method === 'POST') {
            console.log(`[DEBUG] リクエストボディ: ${options.body}`);
          }
        }
    
        // リクエストの実行
        const response = await fetch(url.toString(), options);
        const data = await response.json();
    
        // Backlogエラーレスポンスのチェックとハンドリング
        if (isBacklogError(data)) {
          const error = data.errors[0];
          const errorDetails = error.moreInfo ? ` (詳細: ${error.moreInfo})` : '';
          throw new Error(`Backlogエラー [${error.code}]: ${error.message}${errorDetails}`);
        }
    
        if (!response.ok) {
          throw new Error(`HTTPエラー ${response.status}: ${response.statusText}`);
        }
    
        return data;
      } catch (error) {
        if (error instanceof Error) {
          // エラーの種類に応じて詳細なメッセージを提供
          if (error.message.includes('ENOTFOUND')) {
            throw new Error(`Backlog API接続エラー: ドメイン ${process.env.BACKLOG_DOMAIN} に接続できません`);
          } else if (error.message.includes('ETIMEDOUT')) {
            throw new Error(`Backlog API接続タイムアウト: リクエストがタイムアウトしました`);
          } else if (error.message.includes('SyntaxError')) {
            throw new Error(`Backlog APIレスポースエラー: 不正なJSONレスポンスを受信しました`);
          } else {
            throw new Error(`Backlog API呼び出しエラー: ${error.message}`);
          }
        }
        throw error;
      }
    } 
Behavior2/5

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

With no annotations, the description carries full burden but only states the action ('add issue') without disclosing behavioral traits. It doesn't mention permissions needed, side effects, response format, or error handling. For a mutation tool with zero annotation coverage, this is a significant gap in transparency.

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

Conciseness5/5

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

The description is a single, efficient phrase ('課題の追加') that directly states the tool's action. It's front-loaded with no wasted words, making it highly concise and well-structured for its minimal content.

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?

Given this is a mutation tool (create) with no annotations, no output schema, and siblings that are mostly read operations, the description is incomplete. It doesn't explain what an 'issue' is, how creation works, or what to expect upon success/failure, leaving critical gaps for agent usage.

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

Parameters4/5

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

The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description doesn't add param info, which is appropriate here. Baseline is 4 for zero parameters, as the schema fully covers the absence of inputs.

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

Purpose2/5

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

The description '課題の追加' (Japanese for 'add issue') states a verb and resource, but it's vague about what an 'issue' entails in this context and doesn't differentiate from siblings like getIssue or getIssues. It avoids tautology by not just restating the name, but lacks specificity about the system domain.

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 is provided on when to use this tool versus alternatives. The description doesn't mention prerequisites, context, or exclusions, leaving the agent to infer usage from sibling names alone. This is inadequate for a creation tool in a system with multiple read operations.

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/tmhr1850/backlog-mcp-server'

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