The FMP MCP Server provides AI-assisted financial research tools powered by the Financial Modeling Prep API, offering both high-level workflow tools and granular atomic tools.
Workflow Tools (orchestrate multiple data sources into comprehensive responses):
stock_brief– All-in-one snapshot: profile, price action, valuation, analyst consensus, insider signals, and headlinesmarket_context– Full market environment: Treasury rates, yield curve, sector rotation, breadth signals, movers, and economic calendarearnings_setup– Pre-earnings analysis: EPS/revenue estimates, beat/miss history, analyst momentum, price drift, and insider signalsearnings_preview– Pre-earnings scorecard with composite signal and bull/bear triggersfair_value_estimate– Multi-method valuation: DCF, PE/PS-based, peer multiples, and analyst targets with blended estimateearnings_postmortem– Post-earnings synthesis: beat/miss, YoY/QoQ trends, analyst reactions, price response, and guidance tone
Atomic Tools (granular data retrieval):
Company & Fundamentals:
company_overview,financial_statements(income/balance/cash flow + CAGRs),revenue_segments,dividends_infoAnalyst & Valuation:
analyst_consensus,peer_comparison,estimate_revisionsPrice & Market:
price_history(SMA, momentum, volatility),market_overview(sector performance, gainers/losers),stock_searchOwnership & Activity:
insider_activity,institutional_ownershipNews & Transcripts:
stock_news(with event-type flagging),earnings_transcript(paginated)Macro & Economic:
treasury_rates(yield curve, inversion flag),economic_calendarEarnings & ETFs:
earnings_calendar,earnings_info,etf_lookup(holdings or reverse lookup)Meta:
fmp_coverage_gaps– shows unimplemented FMP API endpoints
Key technical features: parallel API fetching, in-memory TTL caching, graceful degradation with partial data on errors, and pagination support for transcripts.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@FMP MCP ServerGive me a detailed stock brief for NVDA including valuation and analyst ratings"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
FMP MCP Server
A Model Context Protocol server that provides financial data from Financial Modeling Prep for AI-assisted investment research.
Built with FastMCP 2.0 and Python.
Tools
Workflow Tools (start here)
High-level tools that orchestrate multiple API calls into single research-ready responses:
Tool | Description |
| Quick comprehensive snapshot: profile, price action, valuation, analyst consensus, insider signals, headlines |
| Full market environment: rates, yield curve, sector rotation, breadth, movers, economic calendar |
| Pre-earnings positioning: consensus estimates, beat/miss history, analyst momentum, price drift, insider signals |
| Pre-earnings setup scorecard: composite signal, thesis alignment, and bull/bear triggers |
| Multi-method valuation: DCF, earnings-based, peer multiples, analyst targets, blended estimate |
| Post-earnings synthesis: beat/miss, trend comparison, analyst reaction, market response, guidance tone |
Atomic Tools (deeper dives)
Tool | Description |
| Company profile, quote, key metrics, and analyst ratings |
| Income statement, balance sheet, cash flow (annual/quarterly) |
| Analyst grades, price targets, and forward estimates |
| Historical daily prices with technical context |
| Search for stocks by name or ticker |
| Insider trading activity and transaction statistics |
| Top institutional holders and position changes |
| Recent news and press releases |
| Current Treasury yields and yield curve |
| Upcoming economic events and releases |
| Sector performance, gainers, losers, most active |
| Earnings call transcripts with pagination support |
| Revenue breakdown by product and geography |
| Peer group valuation and performance comparison |
| Dividend history, yield, growth, and payout analysis |
| Upcoming earnings dates with optional symbol filter |
| ETF holdings or stock ETF exposure (dual-mode with auto-detect) |
| Analyst sentiment momentum: forward estimates, grade changes, beat rate |
| Docs parity introspection: endpoint families not yet implemented in this MCP server |
Setup
Prerequisites
Python 3.11+
uv (recommended) or pip
An FMP API key
Install
uv syncConfigure
Set your API key as an environment variable:
export FMP_API_KEY=your_api_key_hereOr create a .env file:
FMP_API_KEY=your_api_key_hereRun
uv run fastmcp run server.pyClaude Desktop / Claude Code
Add to your MCP config:
{
"mcpServers": {
"fmp": {
"command": "uv",
"args": ["run", "--directory", "/path/to/fmp", "fastmcp", "run", "server.py"],
"env": {
"FMP_API_KEY": "your_api_key_here"
}
}
}
}Testing
uv run pytest tests/ -vAll tools are tested with mocked API responses using respx.
Live e2e tests (real API) can be run in pooled parallel mode:
uv run pytest tests/test_live.py -m live_full -n 4 -qArchitecture
server.py # FastMCP entry point, registers all tool modules
tools/_helpers.py # Shared SDK helpers: safe calls, TTL cache, model dumping/normalization
tools/
overview.py # company_overview, stock_search
financials.py # financial_statements, revenue_segments
valuation.py # analyst_consensus, peer_comparison, estimate_revisions
market.py # price_history, dividends_info, earnings_calendar, etf_lookup
ownership.py # insider_activity, institutional_ownership
news.py # stock_news
macro.py # treasury_rates, economic_calendar, market_overview
transcripts.py # earnings_transcript (with pagination)
workflows.py # stock_brief, market_context, earnings_setup, earnings_preview, fair_value_estimate, earnings_postmortemKey design decisions:
Module pattern: Each tool file exports
register(mcp, client)to keep tools organizedSDK-first FMP client: Uses
AsyncFMPDataClient(fmp-data==2.2.0) directly for typed endpoint coverageParallel fetches: Workflow tools use
asyncio.gather()to call multiple endpoints concurrentlyGraceful degradation:
_safe_call()returns defaults on error so composite tools return partial data instead of failing entirelyIn-memory TTL cache: Avoids redundant API calls with configurable TTLs per data type (60s for quotes, 24h for profiles)
License
MIT
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.