havona-mcp
MCP server connecting AI assistants to Havona trade finance API for managing trade contracts, checking blockchain status, and extracting document fields.
README
havona-mcp
MCP server for the Havona trade finance API. Connect any MCP-compatible AI assistant to live trade contracts, blockchain status, and document extraction.
Tools
| Tool | Description |
|---|---|
list_trades |
List recent trade contracts |
get_trade |
Fetch a trade by ID |
create_trade |
Create a new trade contract |
update_trade_status |
Update status (DRAFT → ACTIVE → COMPLETED) |
blockchain_status |
Check chain connection + contract address |
get_trade_blockchain_record |
Get on-chain confirmation for a trade |
list_agents |
List registered ERC-8004 AI agents |
get_agent_reputation |
Get agent reputation score |
list_supported_document_types |
List extractable ETR document types |
extract_trade_document |
Extract fields from a PDF (AI, no persistence) |
graphql_query |
Raw GraphQL passthrough |
Install
pip install havona-mcp
Or from source:
git clone https://github.com/havona-labs/havona-mcp
cd havona-mcp
pip install -e .
Configuration
Copy .env.example to .env:
HAVONA_API_URL=https://api.yourdomain.com
AUTH0_DOMAIN=your-tenant.us.auth0.com
AUTH0_AUDIENCE=https://api.yourdomain.com
AUTH0_CLIENT_ID=your_client_id
HAVONA_EMAIL=trader@yourdomain.com
HAVONA_PASSWORD=your_password
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"havona": {
"command": "python",
"args": ["-m", "havona_mcp"],
"env": {
"HAVONA_API_URL": "https://api.yourdomain.com",
"AUTH0_DOMAIN": "your-tenant.us.auth0.com",
"AUTH0_AUDIENCE": "https://api.yourdomain.com",
"AUTH0_CLIENT_ID": "your_client_id",
"HAVONA_EMAIL": "trader@yourdomain.com",
"HAVONA_PASSWORD": "your_password"
}
}
}
}
Restart Claude Desktop. You can now ask:
"Show me my recent trades" "What's the blockchain status?" "Create a draft trade for 50,000 barrels of crude oil" "Extract the fields from this commercial invoice PDF"
Cursor / other MCP clients
python -m havona_mcp # stdio (default)
python -m havona_mcp --sse # SSE transport for web clients
Architecture
Claude Desktop / Cursor
│ MCP protocol (stdio or SSE)
▼
havona-mcp (this repo)
│ Python function calls
▼
havona-sdk
│ HTTPS + Bearer token
▼
Havona API → DGraph + Confidential EVM
License
MIT — see LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.