Odel
open enterprise ai mcp server

open enterprise ai mcp server

Local
@openenterprise-infoJavaScriptUpdated Today

Connect Claude Code, Cursor & Windsurf to 2,600+ enterprise data sources with one binary.

Open Enterprise AI MCP Server

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

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

License: Apache 2.0 GitHub Release Windows Linux macOS Website Discord


What is OE MCP Server?

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

Connect Claude Code, Cursor, Windsurf, or Claude Desktop to your PostgreSQL database, local filesystem, GitHub, Slack, Google Drive, SSH servers, and more — without writing any integration code.

  • No code. Define connectors in a single YAML file.
  • 45+ connector categories. 2,600+ enterprise systems supported out of the box.
  • Two transport modes. --stdio for Claude Code VS Code / desktop apps; --serve for Cursor, Windsurf, and cloud deployments.
  • Persistent memory. Built-in memory_set / memory_get / memory_list / memory_delete tools — context survives across sessions.
  • Self-hosted. Runs on your own machine. No cloud dependency. Own your data.

Download

PlatformBinary
Windowsoe-mcp-win.exe
Linuxoe-mcp-linux
macOSoe-mcp-macos
Sample configsoe-mcp-samples.zip — ready-to-use oe-mcp.yaml for common connectors

Quick Start

1. Download the binary for your OS

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

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

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. Connect your AI app — see sections below for Claude Code, Cursor, and Windsurf.


Claude Code (VS Code Extension)

Claude Code launches the binary automatically as a child process via stdio. No manual server start needed.

Add to ~/.mcp.json (or your workspace .mcp.json):

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

Windows example:

"command": "C:\\oe-mcp\\oe-mcp-win.exe",
"args": ["--stdio", "C:\\oe-mcp\\oe-mcp.yaml"]

Reload VS Code — the MCP tools appear automatically in Claude Code.


Cursor / Windsurf / Claude Desktop (HTTP mode)

Start the server manually, then point your AI app at the URL.

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

In Cursor settings → MCP → Add server:

http://localhost:4040/mcp

In Claude Desktop claude_desktop_config.json:

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

Cloud Deployment (MCP as a Service)

Deploy oe-mcp-linux to 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.yaml

Each developer adds to their Cursor / Windsurf:

http://your-server.com:4040/mcp

Config File Reference (oe-mcp.yaml)

connectors:
  - name: <display-name>       # must be unique; shown as the tool prefix
    type: <connection-type>    # see Connector Catalog below
    # ... connector-specific credentials

memory:
  - key: <key>
    value: <value>             # seed defaults; overridden at runtime via memory_set

Example — Multiple Connectors

connectors:
  - name: production-db
    type: postgresql
    host: db.company.com
    port: 5432
    database: production
    user: readonly
    password: secret

  - name: company-github
    type: github
    token: ghp_...

  - name: team-slack
    type: slack
    botToken: xoxb-...

  - name: source-code
    type: filesystem
    basePath: /home/user/projects

memory:
  - key: team
    value: "Platform Engineering"
  - key: environment
    value: "production"

Built-in Tools

Connector Tools

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

ConnectorTools
postgresql / mysql / mongodbquery — run SQL or aggregation queries
filesystemlist_dir, read_file, write_file, append_file, delete_file, make_dir, file_info, search_files
githublist_repos, get_file, create_issue, list_issues, list_prs, get_pr, search_code
slacklist_channels, post_message, get_messages, get_thread
sshexecute_command, upload_file, download_file, list_files
gdrivelist_files, get_file, create_file, update_file, search_files
rest-apirequest — any HTTP method against any endpoint

Memory Tools

Built-in memory tools available in every session:

ToolDescription
memory_setStore a key-value pair that persists across sessions
memory_getRetrieve a stored value by key
memory_listList all stored key-value pairs
memory_deleteRemove a stored key

Memory is stored in oe-mcp-memory.json next to your oe-mcp.yaml and survives restarts.

Example usage in Claude Code:

"Remember that our main database is on prod-db.company.com" → Claude calls memory_set with key main_db_host and value prod-db.company.com


Connector Catalog

2,600+ connectors across 45+ categories:

CategoryExamples
SQL DatabasesPostgreSQL, MySQL, MSSQL, Oracle, SQLite, Snowflake, BigQuery, Redshift
NoSQL / CacheMongoDB, Redis, Elasticsearch, DynamoDB, Cassandra
Object StorageAWS S3, GCS, Azure Blob, MinIO, Cloudflare R2
Cloud DrivesGoogle Drive, OneDrive, Dropbox, Box
FilesystemLocal directories — list, read, write, search
EmailGmail, Outlook, Zoho Mail, SMTP
Team MessagingSlack, Microsoft Teams, Discord, Telegram
CRM / ProductivityHubSpot, Salesforce, Notion, Airtable
Issue TrackingGitHub, Jira, GitLab, Linear
REST APIAny HTTP/REST endpoint
GraphQLAny GraphQL endpoint
SSH / SFTPRemote command execution, file transfer
Message QueuesKafka, AWS SQS, Google Pub/Sub, RabbitMQ
SearchPerplexity, Google Search, Bing
LDAP / DirectoryActive Directory, OpenLDAP
OCR / VisionAzure Vision, Google Vision, AWS Textract
Image GenerationOpenAI, FLUX, Stable Diffusion
Speech & AudioElevenLabs, OpenAI TTS, Azure Speech
Web3 / BlockchainEthereum, Polygon, Solana
HelpdeskZendesk, Freshdesk, ServiceNow
+ moreHealthcare (FHIR), ERP (SAP), Marketing, Analytics, ...

Binary vs Node.js mode

The standalone binary works for all connector categories except Oracle, MSSQL, SQLite, and Snowflake — these use native C++ addons that cannot be bundled into a single executable.

If you need any of these four, run with Node.js instead:

git clone https://github.com/openenterprise-info/open-enterprise-ai-mcp-server.git
cd open-enterprise-ai-mcp-server/server
yarn install
# stdio mode (Claude Code)
node mcp/index.js --stdio /path/to/oe-mcp.yaml
# serve mode (Cursor, Windsurf, cloud)
node mcp/index.js --serve --port 4040 /path/to/oe-mcp.yaml

All other connectors (PostgreSQL, MySQL, MongoDB, Redis, S3, Slack, GitHub, REST API, SSH, filesystem, etc.) work directly with the binary — no Node.js required.


Sample Configs

Download oe-mcp-samples.zip for ready-to-use configs:

postgres · mysql · mongodb · github · slack · gdrive · ssh · filesystem · oracle · multi-connector

Each sample includes the complete oe-mcp.yaml with setup instructions in comments.


Transport Modes

ModeFlagBest for
stdio--stdioClaude Code VS Code extension, Claude Desktop — binary launched as child process automatically
HTTP--serveCursor, Windsurf, cloud deployments, multiple developers sharing one server

Both modes are supported in the same binary — just pass the appropriate flag.


Part of Open Enterprise

OE MCP Server is part of the Open Enterprise platform.

Agent Runtimeopen-enterprise-ai-agent-runtime — run YAML agents as CLI or HTTP server
🖥️ Platform (Docker)open-enterprise-community — full web app with workspaces, RAG, Agent Builder, DLP
🌐 Websiteopenenterprise.info

License

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