TypeScriptを使用したElasticsearch MCPサーバーの作成

npm init -y

npm install @elastic/elasticsearch @modelcontextprotocol/sdk openai zod && npm install --save-dev ts-node @types/node typescript

{
    "id": 5,
    "title": "Logging Standards for Microservices",
    "content": "Consistent logging across microservices helps with debugging and tracing. Use structured JSON logs and include request IDs and timestamps. Avoid logging sensitive information. Centralize logs in Elasticsearch or a similar system. Configure log rotation to prevent storage issues and ensure logs are searchable for at least 30 days.",
    "tags": ["logging", "microservices", "standards"]
}

// index.ts
import { z } from "zod";
import { Client } from "@elastic/elasticsearch";
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import OpenAI from "openai";

const ELASTICSEARCH_ENDPOINT =
  process.env.ELASTICSEARCH_ENDPOINT ?? "http://localhost:9200";
const ELASTICSEARCH_API_KEY = process.env.ELASTICSEARCH_API_KEY ?? "";
const OPENAI_API_KEY = process.env.OPENAI_API_KEY ?? "";
const INDEX = "documents";

const openai = new OpenAI({
  apiKey: OPENAI_API_KEY,
});

const _client = new Client({
  node: ELASTICSEARCH_ENDPOINT,
  auth: {
    apiKey: ELASTICSEARCH_API_KEY,
  },
});

const DocumentSchema = z.object({
  id: z.number(),
  title: z.string(),
  content: z.string(),
  tags: z.array(z.string()),
});

const SearchResultSchema = z.object({
  id: z.number(),
  title: z.string(),
  content: z.string(),
  tags: z.array(z.string()),
  score: z.number(),
});

type Document = z.infer<typeof DocumentSchema>;
type SearchResult = z.infer<typeof SearchResultSchema>;

const server = new McpServer({
  name: "Elasticsearch RAG MCP",
  description:
    "A RAG server using Elasticsearch. Provides tools for document search, result summarization, and source citation.",
  version: "1.0.0",
});

server.registerTool(
  "search_docs",
  {
    title: "Search Documents",
    description:
      "Search for documents in Elasticsearch using full-text search. Returns the most relevant documents with their content, title, tags, and relevance score.",
    inputSchema: {
      query: z
        .string()
        .describe("The search query terms to find relevant documents"),
      max_results: z
        .number()
        .optional()
        .default(5)
        .describe("Maximum number of results to return"),
    },
    outputSchema: {
      results: z.array(SearchResultSchema),
      total: z.number(),
    },
  },
  async ({ query, max_results }) => {
    if (!query) {
      return {
        content: [
          {
            type: "text",
            text: "Query parameter is required",
          },
        ],
        isError: true,
      };
    }

    try {
      const response = await _client.search({
        index: INDEX,
        size: max_results,
        query: {
          bool: {
            must: [
              {
                multi_match: {
                  query: query,
                  fields: ["title^2", "content", "tags"],
                  fuzziness: "AUTO",
                },
              },
            ],
            should: [
              {
                match_phrase: {
                  title: {
                    query: query,
                    boost: 2,
                  },
                },
              },
            ],
          },
        },
        highlight: {
          fields: {
            title: {},
            content: {},
          },
        },
      });

      const results: SearchResult[] = response.hits.hits.map((hit: any) => {
        const source = hit._source as Document;

        return {
          id: source.id,
          title: source.title,
          content: source.content,
          tags: source.tags,
          score: hit._score ?? 0,
        };
      });

      const contentText = results
        .map(
          (r, i) =>
            `[${i + 1}] ${r.title} (score: ${r.score.toFixed(
              2,
            )})\n${r.content.substring(0, 200)}...`,
        )
        .join("\n\n");

      const totalHits =
        typeof response.hits.total === "number"
          ? response.hits.total
          : (response.hits.total?.value ?? 0);

      return {
        content: [
          {
            type: "text",
            text: `Found ${results.length} relevant documents:\n\n${contentText}`,
          },
        ],
        structuredContent: {
          results: results,
          total: totalHits,
        },
      };
    } catch (error: any) {
      console.log("Error during search:", error);

      return {
        content: [
          {
            type: "text",
            text: `Error searching documents: ${error.message}`,
          },
        ],
        isError: true,
      };
    }
  }
);

server.registerTool(
  "summarize_and_cite",
  {
    title: "Summarize and Cite",
    description:
      "Summarize the provided search results to answer a question and return citation metadata for the sources used.",
    inputSchema: {
      results: z
        .array(SearchResultSchema)
        .describe("Array of search results from search_docs"),
      question: z.string().describe("The question to answer"),
      max_length: z
        .number()
        .optional()
        .default(500)
        .describe("Maximum length of the summary in characters"),
      max_docs: z
        .number()
        .optional()
        .default(5)
        .describe("Maximum number of documents to include in the context"),
    },
    outputSchema: {
      summary: z.string(),
      sources_used: z.number(),
      citations: z.array(
        z.object({
          id: z.number(),
          title: z.string(),
          tags: z.array(z.string()),
          relevance_score: z.number(),
        })
      ),
    },
  },
  async ({ results, question, max_length, max_docs }) => {
    if (!results || results.length === 0 || !question) {
      return {
        content: [
          {
            type: "text",
            text: "Both results and question parameters are required, and results must not be empty",
          },
        ],
        isError: true,
      };
    }

    try {
      const used = results.slice(0, max_docs);

      const context = used
        .map(
          (r: SearchResult, i: number) =>
            `[Document ${i + 1}: ${r.title}]\\n${r.content}`
        )
        .join("\n\n---\n\n");

      // Generate summary with OpenAI
      const completion = await openai.chat.completions.create({
        model: "gpt-4o-mini",
        messages: [
          {
            role: "system",
            content:
              "You are a helpful assistant that answers questions based on provided documents. Synthesize information from the documents to answer the user's question accurately and concisely. If the documents don't contain relevant information, say so.",
          },
          {
            role: "user",
            content: `Question: ${question}\\n\\nRelevant Documents:\\n${context}`,
          },
        ],
        max_tokens: Math.min(Math.ceil(max_length / 4), 1000),
        temperature: 0.3,
      });

      const summaryText =
        completion.choices[0]?.message?.content ?? "No summary generated.";

      const citations = used.map((r: SearchResult) => ({
        id: r.id,
        title: r.title,
        tags: r.tags,
        relevance_score: r.score,
      }));

      const citationText = citations
        .map(
          (c: any, i: number) =>
            `[${i + 1}] ID: ${c.id}, Title: "${c.title}", Tags: ${c.tags.join(
              ", ",
            )}, Score: ${c.relevance_score.toFixed(2)}`,
        )
        .join("\n");

      const combinedText = `Summary:\\n\\n${summaryText}\\n\\nSources used (${citations.length}):\\n\\n${citationText}`;

      return {
        content: [
          {
            type: "text",
            text: combinedText,
          },
        ],
        structuredContent: {
          summary: summaryText,
          sources_used: citations.length,
          citations: citations,
        },
      };
    } catch (error: any) {
      return {
        content: [
          {
            type: "text",
            text: `Error generating summary and citations: ${error.message}`,
          },
        ],
        isError: true,
      };
    }
  }
);

const transport = new StdioServerTransport();
server.connect(transport);

npx tsc index.ts --target ES2022 --module node16 --moduleResolution node16 --outDir ./dist --strict --esModuleInterop

{
  "mcpServers": {
    "elasticsearch-rag-mcp": {
      "command": "node",
      "args": [   "/Users/user-name/app-dir/dist/index.js"
      ],
      "env": {
        "ELASTICSEARCH_ENDPOINT": "your-endpoint-here",
        "ELASTICSEARCH_API_KEY": "your-api-key-here",
        "OPENAI_API_KEY": "your-openai-key-here"
      }
    }
  }
}

Most Relevant Documents:
Access Control and Role Management (highest relevance) - This document covers role-based access control (RBAC) principles, including ensuring users only have necessary permissions, regular auditing of user roles, revoking inactive accounts, and implementing just-in-time access for sensitive operations.
User Authentication with OAuth 2.0 - This document explains OAuth 2.0 authentication, which enables secure delegated access without credential sharing. It covers configuring identity providers, token management with limited scope and lifetime, and secure storage of refresh tokens.
Container Security Guidelines - While primarily about container security, this document touches on access control aspects like running containers as non-root users and avoiding embedded credentials.
Incident Response Playbook - This mentions role assignment during incidents (incident commander, communications lead, etc.), which relates to access control in emergency scenarios.
Logging Standards for Microservices - This document includes guidance on avoiding logging sensitive information, which is relevant to authentication security.

Based on the documentation, here are the main recommendations to improve authentication and access control across your systems:

Key Recommendations

1. Implement Role-Based Access Control (RBAC)
Ensure users have only the permissions necessary for their job functions. This principle of least privilege minimizes security risks by limiting access to what's truly needed. [1]

2. Regular Access Audits
Conduct regular audits of user roles and promptly revoke access for inactive accounts. This helps prevent unauthorized access from dormant or compromised accounts. [1]

3. Just-in-Time (JIT) Access
Implement just-in-time access for sensitive operations, where permissions are granted only when needed and for a limited duration. This reduces the attack surface by minimizing standing privileges. [1]

4. OAuth 2.0 for Secure Authentication
Use OAuth 2.0 to enable secure delegated access without sharing user credentials. This protocol allows third-party applications to access resources on behalf of users without exposing passwords. [2]

5. Token Security and Management
Configure your identity provider to issue tokens with limited scope and lifetime

Store refresh tokens securely
Validate access tokens consistently to maintain security [2]
References

Access Control and Role Management (Tags: security, access-control)
User Authentication with OAuth 2.0 (Tags: authentication, oauth)
These recommendations work together to create a defense-in-depth approach, where multiple security layers protect your systems from unauthorized access.