Vala-Fi MCP Server
A Bloomberg Terminal you can talk to. Query company relationships — suppliers, customers, competitors, supply chain paths — directly from Claude, Cursor, or any MCP-compatible AI assistant.
README
Vala-Fi MCP Server
A Bloomberg Terminal you can talk to. Query company relationships — suppliers, customers, competitors, supply chain paths — directly from Claude, Cursor, or any MCP-compatible AI assistant.
Every relationship is extracted from SEC 10-K filings. Every edge has a citation. No black boxes.
Why This Exists
Bloomberg Terminal costs $24,000/year. FactSet starts at $12,000. PitchBook won't even show you pricing without a sales call.
Vala-Fi gives you the same company relationship data for free.
We extract supplier, customer, and competitor relationships from SEC 10-K annual filings using AI — the same source of truth that institutional investors rely on. The difference: you get it as a structured API with graph traversal, not a 200-page PDF.
5,200+ companies. 8,000+ relationships. 11 sectors. Free during beta.
Quick Start
1. Get a free API key
Sign up at valafi.dev/signup — takes 10 seconds, no credit card.
2. Configure your AI assistant
Remote Server (Recommended — zero install)
No packages to install. Just paste the config and go.
Claude Desktop — add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):
{
"mcpServers": {
"vala-fi": {
"url": "https://mcp.valafi.dev/mcp",
"headers": {
"X-API-Key": "vfi_your_key_here"
}
}
}
}
Cursor — add to .cursor/mcp.json:
{
"mcpServers": {
"vala-fi": {
"url": "https://mcp.valafi.dev/mcp",
"headers": {
"X-API-Key": "vfi_your_key_here"
}
}
}
}
Windsurf / Claude Code — same config format as above.
Local Server (Alternative — runs on your machine)
If you prefer running the server locally (required for Claude Desktop):
{
"mcpServers": {
"vala-fi": {
"command": "/full/path/to/uvx",
"args": ["vala-fi-mcp"],
"env": {
"VALAFI_API_KEY": "vfi_your_key_here"
}
}
}
}
Find your uvx path by running which uvx in your terminal. Requires Python 3.10+ and uv.
3. Start asking questions
That's it. Your AI assistant now has access to a financial knowledge graph.
Available Tools
| Tool | Description |
|---|---|
get_company_profile |
Company name, sector, industry, exchange |
get_supply_chain |
Upstream/downstream relationships (1-3 hops) |
get_customers |
All known customers with SEC citations |
get_competitors |
All known competitors with SEC citations |
find_path |
Shortest path between two companies |
get_exposure |
Supply chain concentration risk analysis |
get_sector_graph |
Full sector relationship subgraph (paid tier) |
Prompts
Pre-built prompt templates you can invoke directly:
| Prompt | Description |
|---|---|
analyze_supply_chain |
Deep-dive a company's suppliers, customers, competitors, and concentration risk |
compare_companies |
Compare two companies — shared suppliers, paths, competitive overlap |
portfolio_risk_check |
Cross-portfolio supply chain risk assessment (pass comma-separated tickers) |
due_diligence |
Structured due diligence memo from SEC filing data |
Resources
| Resource URI | Description |
|---|---|
valafi://sectors |
List of all 11 sectors covered in the knowledge graph |
valafi://api-info |
API overview, endpoint URL, and free tier limits |
What You Can Do
Ask your AI assistant questions like:
- "Who are Apple's top suppliers?"
- "Find the connection between Tesla and NVIDIA"
- "What companies depend on TSMC as a sole supplier?"
- "Show me all competitors of Microsoft mentioned in SEC filings"
- "What's the supply chain risk for my portfolio: AAPL, MSFT, GOOGL?"
Every answer comes with the SEC filing citation so you can verify it yourself.
Use Cases
Solo Developer / Indie Hacker
You're building a stock analysis tool and need to understand company relationships without paying for a Bloomberg Terminal. Vala-Fi gives you structured supply chain data through a simple API.
AI Agent Builder
You're building an autonomous research agent that needs to answer questions like "What happens to Apple if TSMC has a production issue?" Plug in Vala-Fi as an MCP tool and your agent can traverse the financial graph.
Quantitative Researcher
You're modeling supply chain risk or building factor models that incorporate inter-company dependencies. Query the graph programmatically and get SEC-cited evidence for every relationship.
Due Diligence Analyst
You're evaluating an acquisition target and need to quickly map their supplier/customer network. One API call gives you the full picture with citations.
Financial Content Creator
You're writing analysis and need to verify company relationships. Instead of reading 10-K filings manually, query the graph and get the exact excerpt.
Free Tier Limits
| Limit | Value |
|---|---|
| Requests per day | 50 |
| Unique tickers per day | 10 |
| Results per query | 5 |
| Max hop depth | 2 |
| Strength scores | Included |
| SEC citations | All results |
| Sector graph | Paid only |
Need more? Contact us.
Example Session
You: Who are NVIDIA's main suppliers according to SEC filings?
Claude: Based on NVIDIA's SEC 10-K filings, here are their key suppliers:
1. **TSMC** (TSM) - Primary foundry partner manufacturing NVIDIA's GPUs
"Taiwan Semiconductor Manufacturing Company Limited manufactures
our GPUs and Tegra processors..." — NVIDIA 10-K
2. **Samsung Electronics** - Secondary foundry for certain chip production
"Samsung manufactures different different different different..." — NVIDIA 10-K
3. **Amkor Technology** (AMKR) - Packaging and testing services
"We use third-party foundries, including TSMC and Samsung,
and packaging and test providers such as Amkor..." — NVIDIA 10-K
Direct API Usage (Without MCP)
Don't need an AI assistant? Use the REST API directly:
# Get Apple's suppliers
curl -H "X-API-Key: vfi_your_key" \
https://api.valafi.dev/v1/company/AAPL/supply-chain
# Find path between Tesla and NVIDIA
curl -H "X-API-Key: vfi_your_key" \
https://api.valafi.dev/v1/path/TSLA/NVDA
# Get supply chain risk for a company
curl -H "X-API-Key: vfi_your_key" \
https://api.valafi.dev/v1/exposure/AAPL
Full API documentation: valafi.dev/docs
Data Source
All relationship data is extracted from SEC 10-K annual filings using AI. We do not scrape news, social media, or third-party databases.
- Source: SEC EDGAR
- Coverage: 5,200+ public companies across 11 GICS sectors
- Update frequency: As new 10-K filings are published (primarily Q1 and Q3)
- Relationship types: supplier, customer, competitor, partner, and more
Links
- Website: valafi.dev
- API Docs: valafi.dev/docs
- Get API Key: valafi.dev/signup
- Pricing: valafi.dev/pricing
License
MIT — use it however you want.
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
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.