Metadata-Version: 2.4
Name: crdb-mcp-server
Version: 0.1.0
Summary: Model Context Protocol server with CockroachDB
Author-email: Virag Tripathi <virag.tripathi@gmail.com>
License-Expression: MIT
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Topic :: Software Development :: Quality Assurance
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Operating System :: OS Independent
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: sqlalchemy
Requires-Dist: sqlalchemy-cockroachdb
Requires-Dist: fastapi>=0.110.0
Requires-Dist: uvicorn[standard]>=0.29.0
Requires-Dist: psycopg2-binary>=2.9.9
Requires-Dist: python-dotenv>=1.0.1
Dynamic: license-file

# crdb-mcp-server

![PyPI](https://img.shields.io/pypi/v/crdb-mcp-server)
![Python](https://img.shields.io/pypi/pyversions/crdb-mcp-server)
![License](https://img.shields.io/github/license/viragtripathi/crdb-mcp-server)
![CI](https://github.com/viragtripathi/crdb-mcp-server/actions/workflows/python-ci.yml/badge.svg)

A Model Context Protocol (MCP) server implemented in Python using FastAPI and CockroachDB.

---

## 🧠 What This Is

`crdb-mcp-server` is a production-grade, spec-aligned MCP server that:

- Implements the [Model Context Protocol](https://modelcontextprotocol.io/introduction)
- Uses **CockroachDB** as a resilient, SQL-compatible backend
- Exposes full **CRUD APIs** for managing model contexts
- Stores context definitions as **JSONB**, allowing arbitrary input/output schema
- Works seamlessly with the [`crdb-mcpctl`](https://github.com/viragtripathi/crdb-mcpctl) CLI

---

## ✅ Feature Highlights

- ✅ REST API for MCP context management (`/contexts`)
- ✅ Schema bootstrapping via CLI flag or env var
- ✅ CRDB URL auto-detection and dialect fix
- ✅ ASCII banner and version info
- ✅ Structured logging and configurable log level
- ✅ Ready for `/run`, `/deploy`, `/evaluate` extensions

---

## 🚀 Quickstart

### 📦 Install from PyPI

```bash
pip install crdb-mcp-server
````

### 🏃 Run with schema init

```bash
crdb-mcp-server serve --init-schema --log-level INFO
```

Or:

```bash
export MCP_AUTO_INIT_SCHEMA=true
crdb-mcp-server serve
```

> Server runs at `http://localhost:8081` by default

---

## 🔧 CLI Usage

```bash
crdb-mcp-server serve --init-schema
crdb-mcp-server serve --port 8081 --host 127.0.0.1 --reload
crdb-mcp-server --version
crdb-mcp-server --banner
```

---

## 🔐 Configuring the Database

### ✅ Set the `CRDB_URL` environment variable

```bash
export CRDB_URL="postgresql://root@localhost:26257/defaultdb?sslmode=disable"
```

> Automatically rewritten to `cockroachdb://...` under the hood for compatibility.

Alternatively, set it directly:

```bash
export CRDB_URL="cockroachdb://root@localhost:26257/defaultdb?sslmode=disable"
```

✅ Both formats are supported.

---

## 🧪 API Endpoints

| Method | Path             | Description       |
|--------|------------------|-------------------|
| POST   | `/contexts`      | Create a context  |
| GET    | `/contexts`      | List all contexts |
| GET    | `/contexts/{id}` | Get context by ID |
| PUT    | `/contexts/{id}` | Update context    |
| DELETE | `/contexts/{id}` | Delete context    |

---

## 🧱 Schema Auto-Bootstrap

Run this manually:

```bash
crdb-mcp-server serve --init-schema
```

Or automatically with:

```bash
export MCP_AUTO_INIT_SCHEMA=true
```

The schema created is:

```sql
CREATE TABLE IF NOT EXISTS mcp_contexts (
  id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
  context_name STRING NOT NULL,
  context_version STRING NOT NULL,
  body JSONB NOT NULL,
  created_at TIMESTAMP DEFAULT now()
);
```

---

## 🔗 Related Projects

* [crdb-mcpctl](https://github.com/viragtripathi/crdb-mcpctl): CLI tool to manage MCP contexts, simulate LLM runs, export, and batch simulate across providers.

---

## 🙌 Contributions

This project is designed for internal and community use.

PRs welcome to extend functionality (auth, deployment support, `/evaluate`, telemetry, etc.).
