Ontology Mcp Server
Description
# Ontology MCP Server **Turn ISO 20022 banking messages into a queryable knowledge graph — accessible to any AI agent via MCP.** Banks, fintechs, and payment processors deal with thousands of ISO 20022 messages daily (pacs.008 payments, camt.056 cancellations, camt.029…
About
# Ontology MCP Server **Turn ISO 20022 banking messages into a queryable knowledge graph — accessible to any AI agent via MCP.** Banks, fintechs, and payment processors deal with thousands of ISO 20022 messages daily (pacs.008 payments, camt.056 cancellations, camt.029 responses). These XML files are dense…
Details
- Author
- mrcholis
- Downloads
- 170
- Categories
- Other
Jump to
- Ingests ISO 20022 XML into a queryable knowledge graph.
- Exposes 11 MCP tools for AI agents.
- Supports pacs.008, pacs.009, camt.053/054/056/026/029.
- Persistent storage with Oxigraph (RocksDB-backed).
- Real-time WebSocket streaming ingest.
- Built-in anomaly detection for high-value transactions.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Ontology Mcp ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install via pip install ontology-mcp and run python mcp_server.py. Alternatively, use Docker: docker pull ghcr.io/mrcholis/ontology-mcp:latest and docker run .... Connect any MCP client (e.g., Claude Desktop) by adding the server to your claude_desktop_config.json. A demo can be run with python -m ontology_mcp.demo.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"ontology mcp server": {
"ontology": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/mrcholis/ontology-mcp"
]
}
}
}
}McpServers
{
"ontology": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/mrcholis/ontology-mcp"
]
}
}Ontology MCP Server
Turn ISO 20022 banking messages into a queryable knowledge graph — accessible to any AI agent via MCP.
Banks, fintechs, and payment processors deal with thousands of ISO 20022 messages daily (pacs.008 payments, camt.056 cancellations, camt.029 responses). These XML files are dense, interconnected, and nearly impossible to query across — until now.
Ontology ingests ISO 20022 XML, extracts structured financial signals, builds an RDF knowledge graph, and exposes it as native tools that any MCP-compatible AI agent can use.
```bash
pip install ontology-mcp
python mcp_server.py
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
