Give your financial agent access to the Financial Industry Business Ontology (FIBO).
Paste into Claude Code:
Install fibo-mcp from https://github.com/NeuroFusionAI/fibo-mcp
If already in fibo-mcp directory, skip clone and cd. Run all commands from the fibo-mcp directory:
git clone https://github.com/NeuroFusionAI/fibo-mcp.git && cd fibo-mcp
uv sync
claude mcp add --scope user fibo-mcp -- uv run --directory "$(pwd)" main.py
# Restart Claude Code to load the MCPMaterialization expands the graph from 130K → 616K triples with inferred facts. First run takes ~2 minutes, then cached.
# Step 1: Build cache first (Ctrl+C after "Ready to serve")
uv run main.py --materialize
# Step 2: Add MCP (instant startup from cache)
claude mcp add --scope user fibo-mcp -- uv run --directory "$(pwd)" main.py --materializeThe repo includes a diagramming skill (.claude/skills/diagramming_expert/) for ASCII visualizations.
When installing via Claude Code, ask user:
Diagramming skill scope:
- Project scope only (default - already in .claude/skills/)
- User scope (all projects) - copy to ~/.claude/skills/
# User scope skill (optional)
cp -r .claude/skills/diagramming_expert ~/.claude/skills/Add to your MCP config file:
{
"mcpServers": {
"fibo-mcp": {
"command": "uv",
"args": ["run", "--directory", "/path/to/fibo-mcp", "main.py"]
}
}
}With materialization:
{
"mcpServers": {
"fibo-mcp": {
"command": "uv",
"args": ["run", "--directory", "/path/to/fibo-mcp", "main.py", "--materialize"]
}
}
}Build cache first:
uv run main.py --materialize(Ctrl+C after "Ready to serve")
# Claude Code
claude mcp remove fibo-mcp
# Remove user-scope skill (if installed)
rm -rf ~/.claude/skills/diagramming-expert| Without fibo-mcp | With fibo-mcp |
|---|---|
|
Money is a medium of exchange, a store of value, and a unit of account that facilitates economic transactions. Forms of Money:
Money's value ultimately rests on collective trust and acceptance. |
Claude automatically queries FIBO... According to FIBO: Currency: "medium of exchange value, defined by reference to the geographical location of the monetary authorities responsible for it" FIBO distinguishes:
|
| Without fibo-mcp | With fibo-mcp |
|---|---|
|
A country is a distinct territorial body or political entity with its own government, defined borders, and sovereignty. Key characteristics:
There are approximately 195 recognized countries today. |
Claude automatically queries FIBO... Sovereign State: "non-physical juridical entity that is represented by one centralized government that has sovereignty over a geographic area" Key characteristics from FIBO:
Related: Federated Sovereignty, Regional Sovereignty |
| Without fibo-mcp | With fibo-mcp |
|---|---|
|
A corporation is a legal entity separate from its owners:
|
Claude automatically queries FIBO... Stock Corporation: "corporation that has shareholders, each of whom receives a portion of the ownership of the corporation through shares of stock" Contractually Capable Entity: "unique entity that is legally or financially responsible for the performance of financial transactions, or has the legal right in its jurisdiction to enter independently into legal contracts" Formation: Articles of Incorporation, Corporate Bylaws |
Finance has a semantics problem—the same "trade," "counterparty," or "position" can mean different things across desks, systems, vendors, and jurisdictions. FIBO provides a formal, machine-readable ontology (OWL/RDF) so data from contracts, market feeds, and internal systems can be integrated and queried with shared meaning.
Contributors include Citigroup, Deutsche Bank, Goldman Sachs, State Street, Wells Fargo, CFTC, US Treasury OFR, and others. Standardized by EDM Council and OMG.
# Start HTTP server
uv run main.py --http --port 8000
# Expose via ngrok (in another terminal)
ngrok http 8000from openai import OpenAI
client = OpenAI()
resp = client.responses.create(
model="gpt-5.2",
tools=[{
"type": "mcp",
"server_label": "fibo",
"server_url": "https://your-ngrok-url.ngrok.io/mcp",
"require_approval": "never",
}],
input="What is a derivative according to FIBO?",
)| Data | 129K triples (299 RDF/OWL files), 616K with materialization |
| Coverage | 3,371 classes, 16,057 entities, 1,259 properties |
| Cache | ./data/fibo.ttl (base), ./data/fibo_materialized.ttl (with --materialize) |
| Update | uv run main.py --force-download |
| Flag | Description |
|---|---|
--materialize |
Enable OWL-RL inference (130K → 616K triples, ~2min first run, cached) |
--bm25-top-k N |
Number of BM25 search results (default: 10) |
--force-download |
Re-download FIBO data |
--http |
Run as HTTP server instead of stdio |
--port N |
HTTP server port (default: 8000) |
