mcp-server-elasticsearch: Instructions file for Claude Code

CLAUDE.md

mcp-server-elasticsearch CLAUDE.md is an instructions file for Claude Code from zx8086/mcp-server-elasticsearch. It costs 989 tokens per session, scanned A, original, Apache-2.0.

Instructions for developing an Elasticsearch MCP server. Elasticsearch is a search and data-storage system, and an MCP server lets AI assistants interact with connected tools.

In plain words
What is it for?
Use them when building, testing, linting, configuring, or checking connectivity for this TypeScript server running on Bun.
Why use it?
They explain the project's commands, architecture, configuration checks, and the required way to validate tool changes directly.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is zx8086/mcp-server-elasticsearch's own configuration. It tells Claude Code how to work on mcp-server-elasticsearch itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-server-elasticsearch configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zx8086/mcp-server-elasticsearch. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/zx8086/mcp-server-elasticsearch/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/zx8086/mcp-server-elasticsearch

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcp-server-elasticsearch CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zx8086/mcp-server-elasticsearch/claude-md/github.svg)](https://agentmods.dev/instructions/zx8086/mcp-server-elasticsearch/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/zx8086/mcp-server-elasticsearch/claude-md"><img src="https://agentmods.dev/badge/instructions/zx8086/mcp-server-elasticsearch/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mcp-server-elasticsearch CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/zx8086/mcp-server-elasticsearch/claude-md"><img src="https://agentmods.dev/badge/instructions/zx8086/mcp-server-elasticsearch/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 989 This file is loaded in full into every session.
When invoked 989 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00989 $0.00989
Opus 5 $0.00495 $0.00495
Sonnet 5 $0.00198 $0.00198
Haiku 4.5 $0.00099 $0.00099

Measured 8d ago against content hash abb4efac2dbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-server-elasticsearch CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project: MCP Server Elasticsearch

Elasticsearch MCP server enabling AI assistants to interact with Elasticsearch clusters. 96+ tools across 19 categories for comprehensive operations. Built with TypeScript on Bun runtime.

Commands

bun run dev                    # Start dev server with hot reload
bun run build                  # Build production bundle
bun run test                   # Run unit + validation tests
bun run test:all               # All tests (comprehensive)
bun run test:watch             # Live testing during development
bun run lint                   # Biome linting
bun run lint:fix               # Fix linting issues
bun run format                 # Format code

bun run validate-config        # Validate .env configuration
bun run validate-config:full   # Validate + test ES connection
bun run test-connection        # Test Elasticsearch connectivity
LOG_LEVEL=debug bun run dev    # Enable debug logging

Tool Validation (Critical)

Always validate changes by starting the server and calling tools directly:

bun run build && bun run dev
# In another terminal:
echo '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"elasticsearch_list_indices","arguments":{"limit":5}}}' | bun run dist/index.js

Do NOT use bun run inspector - it requires browser access.

Architecture

Configuration System

Single source of truth pattern: defaultConfig object holds all defaults, Zod schemas validate without .default(), environment overrides merged before validation. Key file: src/config.ts.

Transport Modes

Set via MCP_TRANSPORT: stdio (default, CLI/desktop) or sse (web/n8n integration). Handling in src/index.ts.

Tool Organization (src/tools/)

19 categories: core, document, search, index_management, indices, mapping, alias, cluster, bulk, analytics, advanced, diagnostics, ilm, watcher, template, tasks, enrich, autoscaling, notifications.

Security Model

  • Read-only mode (src/utils/readOnlyMode.ts): strict or warning mode
  • Security validation (src/utils/securityEnhancer.ts): SQL injection, XSS, command injection detection with Elasticsearch-specific exemptions (e.g., logs-*,metrics-* patterns)
  • Read-only tools skip security validation

Read the full file on GitHub · 116 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 116 lines · 989 tokens per session scan A abb4efac2dbe

Subscribe to this mod's changes

mcp-server-elasticsearch CLAUDE.md is an instructions file published in the GitHub repository zx8086/mcp-server-elasticsearch (1 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 989 tokens to every session, about $0.0049 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories