Esa.io Search

v0.9.2Search & Data Extractionstable

Search posts in esa.io. Response is paginated. For efficient search, you can use customized queries like the following: keyword for partial match, 'keyword' for exact match, keyword1 keyword2 for AND

mcpmodel-context-protocolesaesa.iodocumentation
Share:
54
Stars
0
Downloads
0
Weekly
0/5

What is Esa.io Search?

Esa.io Search is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to search posts in esa.io. response is paginated. for efficient search, you can use customized queries like the following: keyword for partial match, 'keyword' for exact match, keyword1 keyword2 for and

Search posts in esa.io. Response is paginated. For efficient search, you can use customized queries like the following: keyword for partial match, 'keyword' for exact match, keyword1 keyword2 for AND

This server falls under the Search & Data Extraction category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • html_deploy
  • routine_create
  • routine_delete
  • routine_list
  • routine_get

Use Cases

Documentation and knowledge base search
Post discovery in Esa.io
esaio

Maintainer

LicenseMIT
Languagetypescript
Versionv0.9.2
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y @esaio/esa-mcp-server

Manual Installation

npx -y @esaio/esa-mcp-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Esa.io Search

The esa MCP Server connects AI assistants to esa.io, the team knowledge-base platform popular among engineering and documentation teams in Japan. It exposes over 30 tools covering article search, creation, updating, archiving, commenting, category browsing, and attachment retrieval — giving Claude direct read/write access to your team's esa workspace. Engineers use it to quickly find internal documentation, create new posts, and manage the full lifecycle of team knowledge without leaving their AI chat interface.

Prerequisites

  • An esa.io team account with a personal access token (PAT v2 recommended, with read:post, write:post, and read:team scopes)
  • Docker installed (recommended) OR Node.js 18+ for npx usage
  • Claude Desktop or another MCP-compatible AI client
  • Your esa.io team name (the subdomain used to access your team, e.g. 'myteam' from myteam.esa.io)
1

Generate an esa.io personal access token

Log into your esa.io team, go to Settings > Applications > Personal access tokens, and create a new token. Grant it at minimum read:post and write:post scopes. Copy the token immediately as it won't be shown again.

2

Pull the Docker image (recommended method)

Pull the official Docker image from GitHub Container Registry. This is the recommended installation method as it requires no local Node.js setup.

docker pull ghcr.io/esaio/esa-mcp-server
3

Test the server connection

Verify your token and server work by running the container interactively. Replace 'your_token' with your actual ESA_ACCESS_TOKEN.

ESA_ACCESS_TOKEN=your_token docker run -i --rm -e ESA_ACCESS_TOKEN ghcr.io/esaio/esa-mcp-server
4

Configure Claude Desktop

Add the esa MCP Server to your Claude Desktop configuration. Set ESA_ACCESS_TOKEN to your personal access token and LANG to your preferred language code.

{
  "mcpServers": {
    "esa": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "-e", "ESA_ACCESS_TOKEN", "-e", "LANG", "ghcr.io/esaio/esa-mcp-server"],
      "env": {
        "ESA_ACCESS_TOKEN": "your_esa_personal_access_token",
        "LANG": "ja"
      }
    }
  }
}
5

Restart Claude Desktop and start searching

Restart Claude Desktop to load the esa tools. Claude can now search posts using esa's query syntax, including keyword, 'exact phrase', book:category, and tag:name qualifiers.

Esa.io Search Examples

Client configuration

Claude Desktop configuration using the official Docker image for esa MCP Server.

{
  "mcpServers": {
    "esa": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "ESA_ACCESS_TOKEN",
        "-e", "LANG",
        "ghcr.io/esaio/esa-mcp-server"
      ],
      "env": {
        "ESA_ACCESS_TOKEN": "your_personal_access_token",
        "LANG": "ja"
      }
    }
  }
}

Prompts to try

Example prompts for searching and managing esa.io posts through Claude.

- "Search for posts about 'deployment' in esa"
- "Find all posts with the tag 'onboarding' in esa"
- "Create a new esa post titled 'Sprint 42 Retrospective' in the Engineering category"
- "Show me the most recent posts in esa"
- "Summarize the post about our release process in esa"
- "List all comments on the post about API design guidelines"

Troubleshooting Esa.io Search

401 Unauthorized error when starting the server

Your ESA_ACCESS_TOKEN is invalid or expired. Go to esa.io Settings > Applications > Personal access tokens, revoke the old token, and create a new one with the required scopes (read:post, write:post, read:team). Update the token in your Claude Desktop config.

Docker container exits immediately with no output

Ensure you are running Docker with the -i (interactive) flag so stdin remains open for MCP stdio communication. The full command must include both -i and --rm flags: docker run -i --rm -e ESA_ACCESS_TOKEN ...

Search returns no results even though posts exist

Check your search query syntax. Use single quotes for exact phrase matching ('keyword'), space-separated terms for AND logic, and qualifiers like book:category-name or tag:tagname. Also verify the personal access token has read:post scope.

Frequently Asked Questions about Esa.io Search

What is Esa.io Search?

Esa.io Search is a Model Context Protocol (MCP) server that search posts in esa.io. response is paginated. for efficient search, you can use customized queries like the following: keyword for partial match, 'keyword' for exact match, keyword1 keyword2 for and It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Esa.io Search?

Install via npm with the command: npx -y @esaio/esa-mcp-server. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with Esa.io Search?

Esa.io Search works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Esa.io Search free to use?

Yes, Esa.io Search is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Search & Data Extraction MCP Servers

Explore all search & data extraction servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "esa": { "command": "npx", "args": ["-y", "@esaio/esa-mcp-server"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Esa.io Search?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides