MCPとは — AIと外部ツールをつなぐ標準規格

> 昨日のapi-gatewayのデプロイでエラー出てた？

⏺ deploy-server - search_recent_deploy_errors (MCP)(service: "api-gateway", hours: 24)
  ⎿  ### Deploy errors: api-gateway (last 24h)
     total: 2
     - 14:03 Migration timeout on users table
     - 14:11 Rollback triggered by health check

⏺ 昨日のapi-gatewayのデプロイでは2件のエラーが発生しています。usersテーブルの
  migration timeoutと、それに続くhealth checkによるrollbackです。

> rollbackの手順を教えて

⏺ deploy-server - resources/list (MCP)
  ⎿  file:///runbooks/deploy.md, file:///runbooks/oncall.md

⏺ deploy-server - resources/read (MCP)(uri: "file:///runbooks/deploy.md")
  ⎿  # Deploy runbook
     ## Rollback
     1. Freeze deploys
     2. Revert the release tag
     3. Re-run health checks

⏺ rollbackは3ステップです。デプロイを凍結し、リリースタグをrevertし、
  health checkを再実行してからパイプラインを再開します。

> /investigate_deploy_failure api-gateway

⏺ deploy-server - search_recent_deploy_errors (MCP)(service: "api-gateway", hours: 24)
  ⎿  ### Deploy errors: api-gateway (last 24h)
     total: 2 ...

⏺ deploy-server - get_deploy_status (MCP)(service: "api-gateway")
  ⎿  release v2.14.1 deployed 13:58 ...

⏺ エラーはv2.14.1から始まっており、原因はusersテーブルのmigrationである
  可能性が高いです。推奨: v2.14.0にロールバックし、migrationはオフピークに
  再実行してください。

> deploy-serverでstagingをロールバックして

⏺ deploy-server - rollback_release (MCP)(environment: "staging")

  deploy-server → elicitation/create
    message: "Roll back staging to v2.14.0?"
    fields:  reason (string)

  user → accept { reason: "migration timeout" }

  ⎿  Rolled back staging to v2.14.0 (reason: migration timeout)

⏺ stagingをv2.14.0にロールバックしました。理由として「migration timeout」を
  記録しています。

{
  "mcpServers": {
    "example-server": {
      "command": "npx",
      "args": ["-y", "@example/mcp-server"],
      "env": {
        "EXAMPLE_API_TOKEN": "${EXAMPLE_API_TOKEN}"
      }
    }
  }
}

{
  "mcpServers": {
    "deploy-server": {
      "type": "http",
      "url": "https://mcp.example.com/mcp",
      "headers": {
        "Authorization": "Bearer ${DEPLOY_MCP_TOKEN}",
        "X-Organization": "${DEPLOY_MCP_ORG}"
      }
    }
  }
}

import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';
import { z } from 'zod';

const server = new McpServer({ name: 'deploy-server', version: '1.0.0' });

server.registerTool(
  'search_recent_deploy_errors',
  {
    title: 'Search recent deploy errors',
    description:
      'Searches deploy logs for errors in the given service and time range. ' +
      'Use when investigating a failed or unstable deployment.',
    inputSchema: {
      service: z.string().describe('Service name (e.g. "api-gateway")'),
      hours: z.number().max(72).default(24).describe('Hours to look back'),
    },
  },
  async ({ service, hours }) => {
    const errors = await fetchDeployErrors(service, hours);
    const lines = [
      `### Deploy errors: ${service} (last ${hours}h)`,
      `total: ${errors.length}`,
      ...errors.map((e) => `- ${e.occurredAt} ${e.summary}`),
    ];
    return { content: [{ type: 'text', text: lines.join('\n') }] };
  }
);

server.registerPrompt(
  'investigate_deploy_failure',
  {
    description: 'Investigate a failed deployment step by step',
    argsSchema: {
      service: z.string().describe('Service name to investigate'),
    },
  },
  async ({ service }) => ({
    messages: [
      {
        role: 'user',
        content: {
          type: 'text',
          text: [
            'Investigate the failed deployment in the following order.',
            `1. Call \`search_recent_deploy_errors\` with service "${service}".`,
            '2. Call `get_deploy_status` and find the release that introduced the errors.',
            '3. Summarize the likely causes and propose a rollback decision.',
          ].join('\n'),
        },
      },
    ],
  })
);

await server.connect(new StdioServerTransport());

{
  "mcpServers": {
    "deploy-server": {
      "command": "node",
      "args": ["./dist/deploy-server.js"]
    }
  }
}