Open Enthrium

aka OE MCP · Enterprise MCP Server · Apache-2.0 · Claude Code · Cursor · Windsurf · Codex · Claude Desktop · VS Code

Connect any AI coding assistant to your enterprise data — databases, files, APIs, and more — via a single binary.

OE MCP Server is a standalone binary that implements theModel Context Protocol (MCP)and exposes your enterprise data sources as tools that AI apps can use directly.

{ "mcpServers": { "oe-mcp": { "type": "stdio", "command": "npx", "args": ["-y", "@openenthrium/oe-mcp", "--stdio", "/path/to/oe-mcp.json"] } } }

{ "mcpServers": { "oe-mcp": { "type": "stdio", "command": "npx.cmd", "args": ["-y", "@openenthrium/oe-mcp", "--stdio", "C:\\path\\to\\oe-mcp.json"] } } }

Note:-ytells npx to skip the install confirmation prompt. Without it, npx waits for keyboard input and the MCP connection never opens.

Prefer a standalone binary? Download for your platform:

# Linux / macOS — make executable chmod +x oe-mcp-linux

2. Create your config file(oe-mcp.json)

{ "connectors": [ { "name": "my-postgres", "type": "postgresql", "host": "localhost", "port": 5432, "database": "mydb", "user": "postgres", "password": "secret" }, { "name": "my-codebase", "type": "filesystem", "basePath": "/home/user/projects/myapp" } ], "memory": [ { "key": "project_context", "value": "This is our main application database." } ] }

3. Add to your AI app's MCP config(Claude Code, Cursor, Windsurf, Codex, Claude Desktop, VS Code)

{ "mcpServers": { "oe-mcp": { "type": "stdio", "command": "/path/to/oe-mcp-win.exe", "args": ["--stdio", "/path/to/oe-mcp.json"] } } }

Reload your AI app — the MCP tools appear automatically.

Once connected, ask Claude in plain language:

"What connectors do you have access to?"

Claude will list every connected tool with its available actions. Example response:

You can also run/mcpin Claude Code to see the server status and total tool count.

OE MCP has built-in persistent memory that survives restarts. Use plain language or direct tool calls:

"Remember that our production database host is prod-db.company.com"

Claude callsmemory_setwithkey = main_db_host,value = prod-db.company.com.

"What is our production database host?"

Claude callsmemory_getwithkey = main_db_hostand returns the stored value.

"What do you remember about our project?"

Claude callsmemory_listand returns all stored key-value pairs.

"Forget the production database host."

Claude callsmemory_deletewithkey = main_db_hostto remove it.

Memory is stored inoe-mcp-memory.jsonnext to youroe-mcp.jsonand persists across sessions and restarts.

Use--servewhen you want to run OE MCP as a standalone HTTP server — for cloud deployments or sharing one server across a team.

# Start the MCP server oe-mcp-win.exe --serve --port 4040 oe-mcp.json # OE MCP Server listening on http://localhost:4040/mcp

In Claude Desktopclaude_desktop_config.json:

{ "mcpServers": { "oe-mcp": { "url": "http://localhost:4040/mcp" } } }

Deployoe-mcp-linuxto any cloud server — AWS EC2, fly.io, Railway, DigitalOcean — and multiple developers connect to it via URL. No binary needed on each developer machine.

# On your cloud server ./oe-mcp-linux --serve --port 4040 /etc/oe-mcp/oe-mcp.json

Each developer adds to their Cursor / Windsurf:

{ "connectors": [ { "name": "<display-name>", "type": "<connection-type>", "...": "connector-specific credentials" } ], "memory": [ { "key": "<key>", "value": "<value>" } ] }

{ "connectors": [ { "name": "my-postgres", "type": "postgresql", "host": "db.company.com", "port": 5432, "database": "production", "user": "readonly", "password": "secret" }, { "name": "my-mysql", "type": "mysql", "host": "localhost", "port": 3306, "database": "mydb", "user": "root", "password": "secret" }, { "name": "my-mongo", "type": "mongodb", "uri": "mongodb://localhost:27017", "database": "mydb" }, { "name": "my-redis", "type": "redis", "host": "localhost", "port": 6379 }, { "name": "my-elastic", "type": "elasticsearch", "node": "https://localhost:9200", "apiKey": "xxxxxxxxxxxx" }, { "name": "my-s3", "type": "s3", "accessKeyId": "AKIAXXXXXXXX", "secretAccessKey": "xxxxxxxxxxxx", "region": "us-east-1", "bucket": "my-bucket" }, { "name": "my-gdrive", "type": "gdrive", "clientId": "xxxx.apps.googleusercontent.com", "clientSecret": "xxxx", "refreshToken": "xxxx" }, { "name": "my-github", "type": "github", "repoUrl": "https://github.com/your-org/your-repo", "personalAccessToken": "ghp_xxxxxxxxxxxx" }, { "name": "my-jira", "type": "jira", "host": "https://company.atlassian.net", "email": "you@company.com", "apiToken": "xxxx" }, { "name": "my-slack", "type": "slack", "botToken": "xoxb-xxxxxxxxxxxx" }, { "name": "my-gmail", "type": "gmail", "clientId": "xxxx.apps.googleusercontent.com", "clientSecret": "xxxx", "refreshToken": "xxxx" }, { "name": "my-smtp", "type": "smtp", "host": "smtp.company.com", "port": 587, "user": "you@company.com", "password": "secret" }, { "name": "my-server", "type": "ssh", "host": "server.company.com", "port": 22, "username": "ubuntu", "privateKey": "-----BEGIN OPENSSH PRIVATE KEY-----\nYOUR_PRIVATE_KEY_CONTENT\n-----END OPENSSH PRIVATE KEY-----" }, { "name": "my-codebase", "type": "filesystem", "basePath": "/home/user/projects" }, { "name": "my-api", "type": "rest-api", "baseUrl": "https://api.company.com", "headers": { "Authorization": "Bearer xxxx" } }, { "name": "my-hubspot", "type": "hubspot", "accessToken": "pat-xxxxxxxxxxxx" }, { "name": "my-kafka", "type": "kafka", "brokers": ["localhost:9092"] } ], "memory": [ { "key": "team", "value": "Platform Engineering" }, { "key": "environment", "value": "production" } ] }

Each connector exposes a set of tools prefixed with the connector name. Examples:

Built-in memory tools available in every session:

Memory is stored inoe-mcp-memory.jsonnext to youroe-mcp.jsonand survives restarts.

"Remember that our main database is on prod-db.company.com" → Claude callsmemory_setwith keymain_db_hostand valueprod-db.company.com

Built-in log tools that record every connector tool call:

Every connector tool call is automatically appended tooe-mcp-log.jsonnext to youroe-mcp.jsonwith timestamp, connector name, tool, input, and result. Memory and log tool calls are excluded.

"Show me the action log" → Claude callslog_listand returns recent connector activity

{ "ts": "2026-08-08T04:59:33.289Z", "connector": "my-postgres", "tool": "query", "input": { "sql": "SELECT  FROM users LIMIT 10" }, "result": "ok" }

chains: - next_agent: ./followup.yaml # relative path from this agent file trigger_type: auto # fires immediately after this agent completes - next_agent: ./notify.yaml trigger_type: manual # pauses — Claude asks you before running

Requires OE Runtime config.The agent directory must have a validoe-config.jsonwithllmandconnectorsconfigured. SeeOE Runtimefor agent authoring docs.

git clone https://github.com/enthrium/open-enthrium-ai-mcp-server.git cd open-enthrium-ai-mcp-server/server yarn install # stdio mode (Claude Code, Cursor, Windsurf, Codex, Claude Desktop, VS Code) node mcp/index.js --stdio /path/to/oe-mcp.json # serve mode (cloud/team deployments) node mcp/index.js --serve --port 4040 /path/to/oe-mcp.json

Downloadoe-mcp-samples.zipfor ready-to-use configs:

OE MCP Server is part of theOpen Enthriumplatform.

→ SeeCONTRIBUTING.mdfor how to add sample configs and connector adapters.

Apache-2.0— free to use, modify, and deploy for any purpose, including commercial use. No usage limits. No telemetry. No call-home.

⭐ Star this repo·🌐 Website·⚡ Agent Runtime

A context insertion and search server for Claude Desktop and Cursor IDE, using configurable API endpoints.