mcpdeployment
The mcpdeployment server provides mathematical operations, text manipulation, JSON formatting, security scanning, and informational resources.
Tools
add– Add two integersreverse_text– Reverse a stringformat_json– Pretty-print JSON datacalculate– Evaluate mathematical expressionsscan_mcp_server– Scan MCP servers for security vulnerabilities (YARA-based or advanced LLM/API-based)check_scanner_status– Check scanner configuration and status
Resources
demo://info– Server metadatademo://timestamp– Current time and uptimedemo://examples– Usage examplesdemo://file/data– Read sample data
Prompts
code_review– Code review templatesummarize– Text summarization templatedebug_helper– Debugging assistance template
Additional Capabilities
Deploy locally via stdio (IDE integration) or as a remote HTTP server
Integrate with MCP clients such as Cursor IDE, Claude Desktop, VS Code, Windsurf, and Claude Code
Extend functionality by adding new tools, resources, or prompts via
src/mcpserver/server.py
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcpdeploymentdeploy my server with config.json"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Demo Server
A demonstration MCP (Model Context Protocol) server showcasing Tools, Resources, and Prompts with integrated security scanning.
Features
🛠️ Tools (6)
add- Add two numbersreverse_text- Reverse a stringformat_json- Pretty-print JSONcalculate- Evaluate mathematical expressionsscan_mcp_server- Scan MCP servers for vulnerabilitiescheck_scanner_status- Check scanner configuration
📚 Resources (4)
demo://info- Server metadatademo://timestamp- Current time and uptimedemo://examples- Usage examplesdemo://file/data- Read sample data
💬 Prompts (3)
code_review- Code review templatesummarize- Text summarization templatedebug_helper- Debugging assistance template
Quick Start
Prerequisites
Python 3.11+
uv package manager
Installation
# Clone the repository
git clone https://github.com/manutri1986/mcpdeployment.git
cd mcpdeployment
# Install dependencies (automatic with uv)
uv syncRun the Server
Local Development (stdio transport):
# Start MCP server for IDE integration
uv run mcp-serverThe server communicates via stdio and will wait for MCP protocol connections.
Remote Deployment (HTTP transport):
# Start HTTP server for remote access
MCP_REMOTE_HOST=127.0.0.1 MCP_REMOTE_PORT=8000 uv run mcp-server-remote
# Or use the test script
./scripts/test_http_local.sh📖 Full HTTP deployment guide: docs/HTTP_DEPLOYMENT.md
Security Scanning
Quick Scan
# Run security scan (YARA analyzer - fast, no API key needed)
uv run python scripts/scanners/yara_scanner.py
# Quick scan (sample components only)
uv run python scripts/scanners/yara_scanner.py --quick
# Advanced scanners (require API keys)
uv run python scripts/scanners/llm_api_scanner.py # OpenAI LLM analysis
uv run python scripts/scanners/cisco_api_scanner.py # Cisco AI DefenseScanner Coverage:
✅ Tools (6) - All scanned
✅ Prompts (3) - All scanned
⚠️ Resources (4) - Cannot scan via stdio
Setup Advanced Scanning (Optional)
For deeper analysis with LLM and API analyzers:
# Run setup script
./scripts/setup_scanner.sh
# Or set environment variables manually
export MCP_SCANNER_API_KEY="your_api_key"
export MCP_SCANNER_ENDPOINT="https://us.api.inspect.aidefense.security.cisco.com/api/v1"Get your API key: Cisco AI Defense
📖 Full documentation: docs/SCANNER_SETUP.md
Using with MCP Clients
Cursor IDE
Configuration included at .cursor/mcp.json. After setup:
Restart Cursor IDE
Test: "Use the add tool to calculate 5 + 3"
Or: "Access the demo://info resource"
Claude Desktop, VS Code, Windsurf
Add to your MCP client configuration:
{
"mcpServers": {
"mcpdeployment": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/manutri1986/mcpdeployment.git",
"mcp-server"
]
}
}
}Configuration file locations:
Client | Config Path |
Claude Desktop (macOS) |
|
Claude Desktop (Windows) |
|
Cursor |
|
Windsurf |
|
VS Code |
|
Claude Code |
|
Project Structure
mcpdeployment/
├── src/mcpserver/ # MCP server implementation
│ ├── __init__.py
│ ├── __main__.py # Entry point (stdio transport)
│ ├── __main_remote__.py # Entry point (HTTP transport)
│ └── server.py # Tools, resources, prompts
├── scripts/ # Utility scripts
│ ├── scanners/ # Security scanner implementations
│ │ ├── yara_scanner.py
│ │ ├── llm_api_scanner.py
│ │ └── cisco_api_scanner.py
│ ├── setup_scanner.sh # Scanner configuration
│ └── test_http_local.sh # Local HTTP testing
├── tests/ # Test files
│ └── test_scanner.py # Test scanner setup
├── reports/ # Generated scan reports (gitignored)
├── docs/ # Documentation
│ ├── methodology/ # Scanner methodology docs
│ ├── SCANNER_SETUP.md
│ ├── SCANNER_LIMITATIONS.md
│ └── HTTP_DEPLOYMENT.md # Remote deployment guide
├── data/ # Sample data
│ └── sample_data.json
├── STRUCTURE.md # Detailed structure guide
├── CLAUDE.md # AI assistant guidance
├── README.md # This file
└── pyproject.toml # Project configuration📖 See STRUCTURE.md for detailed directory structure and purpose.
Architecture
Built with FastMCP, a Python framework for MCP servers.
Key Pattern:
from mcp.server.fastmcp import FastMCP
mcp = FastMCP("Demo")
@mcp.tool()
def your_tool(arg: type) -> type:
"""Tool description"""
return result
@mcp.resource("uri://path")
def your_resource() -> str:
"""Resource description"""
return json.dumps(data)
@mcp.prompt()
def your_prompt(arg: type) -> str:
"""Prompt description"""
return f"Prompt text with {arg}"See CLAUDE.md for detailed architecture notes.
Development
Test Scanner
# Verify scanner is configured
uv run python tests/test_scanner.pyAdding Components
Edit src/mcpserver/server.py:
Add function with appropriate decorator (
@mcp.tool(),@mcp.resource(),@mcp.prompt())Update scanner scripts in
scripts/scanners/to include new tools/prompts in scan listsRun security scan:
uv run python scripts/scanners/yara_scanner.py
Documentation
CLAUDE.md - Development guide for AI assistants
docs/HTTP_DEPLOYMENT.md - Remote HTTP deployment guide
docs/SCANNER_SETUP.md - Scanner configuration
docs/SCANNER_LIMITATIONS.md - What can/cannot be scanned
Troubleshooting
Server won't start
Check Python version:
uv run python --version(needs 3.11+)Reinstall dependencies:
uv sync
Tools not appearing in client
Restart client completely
Check client logs for errors
Verify configuration file syntax
Scanner errors
Verify installation:
uv pip list | grep cisco-ai-mcp-scannerTest setup:
uv run python tests/test_scanner.py
License
MIT
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Tools
- addC
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/manutrip-pm-AI-Defense/mcpdeployment'
If you have feedback or need assistance with the MCP directory API, please join our Discord server