@imbenrabi/financial-modeling-prep-mcp-server-2
AMCP server package financial-modeling-prep-mcp-server
Install
agr install @imbenrabi/financial-modeling-prep-mcp-server-2 --target claudeThis artifact does not publish files for Claude.
Document
{ "name": "financial-modeling-prep-mcp-server", "version": "2.6.12", "mcpName": "io.github.imbenrabi/financial-modeling-prep-mcp-server", "description": "Model Context Protocol server for Financial Modeling Prep (FMP) API, exposing 250+ tools for financial data, market insights, and analysis.", "main": "dist/index.js", "type": "module", "bin": { "fmp-mcp": "dist/index.js" }, "files": [ "dist", "LICENSE", "README.md" ], "scripts": { "build": "tsc", "start": "node dist/index.js", "prePublishOnly": "npm run build", "dev": "tsx watch src/index.ts", "setup": "npm install", "test": "vitest", "test:run": "vitest run", "test:coverage": "vitest run --coverage", "typecheck": "tsc --noEmit", "lint": "oxlint --deny-warnings", "lint:fix": "oxlint --fix", "knip": "knip", "knip:fix": "knip --fix", "version:validate": "tsx scripts/version-sync.ts validate", "version:sync": "tsx scripts/version-sync.ts sync", "version:info": "tsx scripts/version-sync.ts info", "test:npm-publish": "tsx scripts/test-npm-publish.ts", "verify:npm-ready": "tsx scripts/verify-npm-ready.ts", "verify:registry-submission": "node --import tsx/esm scripts/verify-registry-submission.ts", "publish:manual": "tsx scripts/manual-publish.ts publish", "publish:dry-run": "tsx scripts/manual-publish.ts publish --dry-run", "publish:validate": "tsx scripts/manual-publish.ts validate", "publish:troubleshoot": "tsx scripts/manual-publish.ts troubleshoot", "test:publish-workflow": "tsx scripts/test-manual-publish.ts", "test:complete-workflow": "tsx scripts/test-complete-workflow.ts", "test:automated-pipeline": "tsx scripts/test-automated-pipeline.ts", "test:registry-suite": "tsx scripts/test-registry-suite.ts", "test:registry": "vitest run tests/unit/registry-tests/", "test:registry-watch": "vitest tests/unit/registry-tests/", "test:registry-coverage": "vitest run tests/unit/registry-tests/ --coverage", "test:installation-verification": "tsx scripts/test-installation-verification.ts", "test:installation-ci": "vitest run tests/unit/registry-tests/InstallationMethodVerification.test.ts --reporter=verbose --testTimeout=15000", "verify:installation": "tsx scripts/verify-installation-methods.ts", "audit:prod": "npm audit --omit=dev" }, "author": "imbenrabi", "license": "Apache-2.0", "dependencies": { "@modelcontextprotocol/sdk": "^1.27.1", "axios": "^1.13.2", "commander": "^14.0.0", "fastify": "^5.7.2", "minimist": "^1.2.8", "toolception": "^0.6.3", "zod": "^3.22.4" }, "devDependencies": { "@types/minimist": "^1.2.5", "@types/node": "^25.0.0", "@vitest/coverage-v8": "^3.2.4", "knip": "^6.9.0", "oxlint": "^1.62.0", "tsx": "^4.19.2", "typescript": "^5.9.2", "vitest": "^3.2.4" }, "engines": { "node": ">=25.3.0", "npm": ">=11.11.0" }, "repository": { "type": "git", "url": "https://github.com/imbenrabi/Financial-Modeling-Prep-MCP-Server" }, "bugs": { "url": "https://github.com/imbenrabi/Financial-Modeling-Prep-MCP-Server/issues" }, "homepage": "https://github.com/imbenrabi/Financial-Modeling-Prep-MCP-Server", "keywords": [ "mcp", "ai", "assistant", "fmp", "financial modeling prep", "financial data", "financial analysis", "financial planning", "financial reporting", "quotes", "symbols", "ticker", "ticker symbols", "stock symbols", "stock quotes", "stock", "stocks", "stock prices", "stock market", "stock data", "stock analysis", "stock planning", "stock reporting", "exchange", "exchanges", "financial news", "stock news", "stock market data", "stock market", "stock market news", "stock market analysis", "stock market planning", "stock market reporting", "stock market quotes", "stock market symbols", "model context protocol", "fmp api", "ai tools", "server", "node", "typescript", "market data", "statements", "news", "indexes", "economics", "crypto", "forex", "commodities", "esg", "technical indicators", "sec-filings", "earnings" ] }
Repository README
Describes imbenrabi/Financial-Modeling-Prep-MCP-Server as a whole, which may contain artifacts other than this one. Where this artifact had no useful description of its own, its summary was taken from here.
Financial Modeling Prep MCP Server
A Model Context Protocol (MCP) server for the Financial Modeling Prep API, exposing 250+ financial data tools to AI assistants.
Features
- 250+ Financial Tools across 24 categories — stocks, ETFs, crypto, forex, commodities, economics, and more
- Dynamic Tool Management — built on toolception for runtime enable/disable of toolsets via meta-tools
- Three Server Modes — Dynamic (meta-tools), Static (pre-loaded toolsets), or All Tools (default)
- Flexible Deployment — use the hosted instance or self-host via npm, Docker, or source
- HTTP/SSE Transport — compatible with Claude.ai, Claude Desktop, and MCP registries
Quick Start
Hosted Instance (Fastest)
No installation required. Connect directly:
https://financial-modeling-prep-mcp-server-production.up.railway.app/mcp
Provide your FMP_ACCESS_TOKEN in session configuration and start using 5 meta-tools to load toolsets on demand.
Self-Hosted (One-Liner)
npx financial-modeling-prep-mcp-server --fmp-token=YOUR_FMP_API_KEY
Or install globally:
npm install -g financial-modeling-prep-mcp-server
fmp-mcp --fmp-token=YOUR_FMP_API_KEY
Get your API key at financialmodelingprep.com.
Table of Contents
Installation
Prerequisites: Node.js 25.3.0 or higher (for v2.6.0+). For older versions (v2.5.x and below), Node.js 20+ is required.
Choose the method that fits your workflow:
- NPM —
npm install -g financial-modeling-prep-mcp-server - Docker — build from source or pull a pre-built image
- Source — clone and run with
npm install && npm run build
See docs/INSTALLATION.md for detailed steps per method.
Configuration
The server supports three operational modes controlled via CLI arguments, environment variables, or session configuration:
| Mode | How to Enable | Description |
|---|---|---|
| Dynamic | DYNAMIC_TOOL_DISCOVERY=true | Starts with 5 meta-tools; load toolsets at runtime |
| Static | FMP_TOOL_SETS=search,company | Pre-loads specified toolsets on session creation |
| All Tools (default) | (default) | Loads all 250+ tools immediately |
Precedence: CLI args > Environment variables > Session config > Defaults.
See docs/CONFIGURATION.md for the full configuration reference.
Usage
Connect to the server via HTTP/SSE transport:
- Claude.ai / Claude Desktop — add as a remote connector (Settings > Connectors)
- Custom clients — POST to
/mcpwithmcp-client-idheader - MCP registries — Smithery.ai, Glama.ai, and others
See docs/USAGE.md for client-specific setup, session headers, and request examples.
Available Tools
24 categories covering:
Search · Directory & Symbol Lists · Company Information · Financial Statements · Financial Metrics & Analysis · Technical Indicators · Quotes & Price Data · Market Indexes & Performance · Market Data · News & Press Releases · SEC Filings · Insider & Institutional Trading · ETFs & Funds · Government Trading · Cryptocurrency & Forex · Earnings · Special Data Sets · Commodities · Economics · Bulk Data Tools
See docs/API_REFERENCE.md for the complete tool catalog.
Registries
This server is listed on multiple MCP registries for easy discovery:
See docs/REGISTRIES.md for registry-specific setup instructions.
Contributing
Contributions are welcome. Please see CONTRIBUTING.md for development setup, testing, and pull request guidelines.
License
Trustgrade A
- passBody integrity
Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.
- warnType matchbest-effort: server code not analyzed
Whether the artifact is really the kind of thing its metadata claims it is.
- passFreshness
How long since the source repository was last pushed to.
- passPrompt injection
Scans the artifact's own text for instructions aimed at your agent rather than at you.
- passLicense
Whether the source repository declares an SPDX license permissive enough to redistribute.
How the grade is calculated
Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:
- Aevery check passed
- Bone warning
- Ctwo warnings
- Dprompt injection or body integrity failed, or three warnings
- Fone of those failed, and something else is wrong
These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.
Versions
git-048ecec6528e2026-08-06