About Fair Value Calculator
A hosted MCP server for AI assistants to look up model-based fair values, valuation status, and quality scores for listed stocks. It also supports stock screening and account watchlists.
Key features
- 01Valuation data for 40,000+ stocks
- 02Stock lookup and comparison
- 03Screening by valuation and quality
- 04Watchlist management and alerts
Use cases
- 01Check a stock's estimated fair value
- 02Compare stocks across valuation metrics
- 03Find stocks by region, sector, and criteria
- 04Track selected stocks with a watchlist
MCP support
Exposes hosted stock lookup, valuation, screening, and watchlist tools to MCP clients over Streamable HTTP. OAuth 2.1 is used for sign-in.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://www.fairvalue-calculator.com/mcpclaude mcp add --transport http com-fairvalue-calculator-fair-value https://www.fairvalue-calculator.com/mcp{"mcpServers":{"com-fairvalue-calculator-fair-value":{"type":"http","url":"https://www.fairvalue-calculator.com/mcp"}}}Open in Cursor{"servers":{"com-fairvalue-calculator-fair-value":{"type":"http","url":"https://www.fairvalue-calculator.com/mcp"}}}Open in VS Code{"mcpServers":{"com-fairvalue-calculator-fair-value":{"type":"http","url":"https://www.fairvalue-calculator.com/mcp"}}}{"mcpServers":{"com-fairvalue-calculator-fair-value":{"serverUrl":"https://www.fairvalue-calculator.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEFair Value Calculator MCP server
Hosted Model Context Protocol server of Fair Value Calculator. It lets an AI assistant look up what a listed stock is worth according to our valuation models, instead of estimating a number from memory.
This repository holds the documentation and the registry manifest (server.json). The server
itself is a hosted service; there is nothing to install or run locally, and its source code is
not part of this repository.
| Endpoint | https://www.fairvalue-calculator.com/mcp |
| Transport | Streamable HTTP |
| Authentication | OAuth 2.1 with dynamic client registration. A free account is enough. |
| Registry name | com.fairvalue-calculator/fair-value |
| Setup guides | https://www.fairvalue-calculator.com/integrations |
| Overview | https://www.fairvalue-calculator.com/mcp |
What it covers
Fair value per share, valuation status and a quality score for 40,000+ listed stocks worldwide. The fair value is blended from several valuation models on reported fundamentals and is recalculated daily. Method and limits: https://www.fairvalue-calculator.com/methodology.
The numbers are model estimates, not prices and not investment advice. Where the data does not support a figure, the server returns the verdict without a number instead of a weak estimate.
Tools
| Tool | What it does |
|---|---|
resolve_stock | Turns a name, ticker or ISIN into the matching listing, up to five matches. |
get_stock_preview | Verdict, distance to fair value in bands and quality score for one stock, without the exact number. |
get_stock_verdict | Fair value per share with currency, distance to the price, verdict, quality score and data level, with a link to the full analysis. |
compare_stocks | Several stocks side by side with the same values. |
screen_stocks | Stocks matching criteria: minimum distance to fair value, minimum quality, sector, region. |
get_watchlist | Reads the watchlist of the signed-in account. |
add_to_watchlist | Adds a stock to the watchlist. |
remove_from_watchlist | Removes a stock from the watchlist. |
set_watchlist_alerts | Switches the e-mail alerts of the account's watchlist on or off (Pro). |
suggest_watchlist_stocks | Suggests up to eight stocks that fit the saved watchlist: priced below fair value, high quality score, not held yet, ranked with their correlation to the stocks already on it; can also suggest a replacement of similar size for one stock. Changes nothing (Pro, not offered in ChatGPT yet). |
The three tools that change the watchlist or alerts ask for separate consent during sign-in.
Free accounts get the verdict tools with monthly limits; exact fair values for all stocks, comparisons of up to five stocks, alerts and watchlist suggestions are part of Pro. Current limits and prices: https://www.fairvalue-calculator.com/pro.
Connect
In any client that supports remote MCP servers, add the endpoint and sign in when prompted:
https://www.fairvalue-calculator.com/mcp
Claude Code:
claude mcp add --transport http fair-value-calculator https://www.fairvalue-calculator.com/mcp
Codex:
codex mcp add fair-value-calculator --url https://www.fairvalue-calculator.com/mcp
Cursor (.cursor/mcp.json):
{"mcpServers":{"fair-value-calculator":{"url":"https://www.fairvalue-calculator.com/mcp"}}}
VS Code: run "MCP: Add Server", choose HTTP and paste the endpoint.
This repository is also a Cursor plugin (plugins/fair-value-calculator), which registers the same endpoint.
Gemini CLI (this repository is also a Gemini CLI extension, gemini-extension.json):
gemini extensions install https://github.com/petz00711/fair-value-calculator-mcp
Step-by-step guides for Claude, ChatGPT, Claude Code, Cursor, VS Code and Codex: https://www.fairvalue-calculator.com/integrations.
Example questions
- "What is Apple worth according to Fair Value Calculator?"
- "Which European technology stocks are undervalued right now?"
- "Compare Microsoft, Alphabet and Meta."
- "Add Nestlé to my watchlist."
Open data
Monthly market valuation datasets (CC BY 4.0): https://github.com/petz00711/fvc-open-data, DOI 10.5281/zenodo.21639205.
Support
Questions and problem reports: [email protected], or open an issue here.
License
The documentation and manifest in this repository are licensed under CC BY 4.0. The hosted service is proprietary and is used under the terms at https://www.fairvalue-calculator.com/legal.php?doc=agb&lang=en.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.