← Back to directory
F

FinanceMCP

Community
A professional financial data MCP server based on the MCP protocol, integrating Tushare API to provide real-time financial data and technical indicator analysis for AI assistants like Claude.
Category
Other #150 of 230
Stars
★ 859 Very popular
Transport
stdio (local process)
Runtime
Node.js 18+ · Hosted (no local runtime)
Credentials
API key / credential required
License
MIT
Last commit
Tools
18
50FMRS · D

Overall, FinanceMCP is a powerful and comprehensive financial data MCP server, offering a wide range of tools and flexible data source integration. However, it is limited by Tushare API permissions and third-party data sources; users should be aware of credit limits and stability. It is a non-official project, suitable for individuals and investment enthusiasts; production environments require careful evaluation.

Strongest · Setup experience 13/20 Weakest · Reliability 5/20

Reliability
5/20
Security and permissions
9/20
Maintenance
10/20
Documentation
13/20
Setup experience
13/20
Why each score
Reliability 5/20
Only the README and repo metadata were supplied; the server manifest is not cached and no source code, tests, or CI artifacts were provided, so the MCP init handshake and actual tool behavior cannot be verified. The README is internally inconsistent: tool count is stated as 14 in one place and 18 in another; '10 major markets' are claimed but only 8 categories are listed (A-shares, US stocks, HK stocks, FX, futures, funds, bonds, options); API integration counts conflict (43+ vs 100+). Therefore the happy path is plausible but not reproducible; per the static calibration reliability cannot exceed 12, and further deductions apply for missing verifiable evidence and contradictory documentation.
Security and permissions 9/20
Credential passing is clearly disclosed in the docs (env, X-Tushare-Token, Authorization: Bearer, X-Api-Key), and all config examples use placeholders rather than real tokens, so no red line is triggered. However, there is no source-level evidence of secure storage, least privilege, or scoping; the legacy free shared endpoint uses plain HTTP (http://106.14.205.176:3101/sse); finance_news is a web-scraping behavior with no confirmation step; and users' own Tushare tokens are sent to a third-party public cloud service whose data boundary is not fully explained. These uncovered gaps justify the deduction.
Maintenance 10/20
The repository is not archived and has a clear MIT license, and the README's 4.3.0→4.7.2 changelog suggests ongoing iteration; however, no commit history, releases/tags, issue-response records, dependency-update evidence, or security-response channel were provided. Version claims come entirely from the README (untrusted evidence); only the non-archived status and license metadata are verifiable. The score therefore reflects 'active but with governance/versioning gaps' (the 10-point anchor), with no upward adjustment due to missing evidence.
Documentation 13/20
The README is layered and fairly complete: install (npm global/local, npx, Smithery, manual build), auth (Tushare token acquisition and student credit benefits), Claude Desktop config JSON for stdio/Streamable HTTP/SSE, troubleshooting, per-domain example queries for stocks/funds/HK/US/crypto, rate-limit and points disclosures, and deployment-mode/logging-guide links. Deductions: all content is README self-report and cannot be independently verified; the docs contradict themselves internally (14 vs 18 tools, '10 markets' vs 8 listed, 43+ vs 100+ interfaces); some tools lack full parameter schemas; and cost/troubleshooting details are missing for several tools, so the 20-point tier is not reached.
Setup experience 13/20
Install paths are clear and varied: global npm install, npx, Smithery, or manual clone + npm install + build; Claude Desktop (Windows/macOS) config examples for stdio/Streamable HTTP/SSE, the Windows npx.cmd caveat, and troubleshooting steps are provided. However, the supplied material contains no verifiable execution evidence (real CI workflows or committed tests covering key paths), so per the static calibration the setup score cannot exceed 15; additionally, HTTP/SSE modes require a manual build step (npm run build), adding fragility, hence 13.

Static review · not runListed 2026-08-07

Read the FMRS scoring method →

Fit and risk

What it can accessUses the network

Best for

  • Financial professionals and investment analysts needing real-time financial data and analysis
  • AI application developers seeking to integrate financial data capabilities
  • Researchers needing multi-market data for stocks, funds, bonds, crypto, etc.
  • Users who want intelligent Q&A via MCP clients like Claude Desktop

Not for

  • Non-financial MCP needs that do not require financial data services
  • Production environments requiring official support or enterprise-grade service guarantees
  • Users with strict data source permission requirements (need to apply for Tushare credits)

Required permissions

  • Requires a Tushare API token for access
  • Crypto data uses Binance public market endpoints, no API key required
  • stdio mode does not require network ports, but HTTP mode requires port opening and network access

Risks and side effects

  • Dependency on Tushare API; some premium data require credits, free tokens may be limited
  • Public cloud services (e.g., finvestai.top) are hosted on personal servers, risk of abuse and instability
  • Data accuracy depends on third-party sources, may have latency or errors
  • Self-hosting requires protecting sensitive keys like TUSHARE_TOKEN

Setup

Before you start

Runtime:Node.js 18+ · Hosted (no local runtime)

TUSHARE_TOKEN requiredsecret Tushare API token obtained from your account dashboard at tushare.pro; some advanced data requires points/credits.
  1. Ensure Node.js >= 18.
  2. Register on tushare.pro and obtain TUSHARE_TOKEN.
  3. Install globally or locally via npm (npm install -g finance-mcp or npm install finance-mcp).
  4. Add the MCP server configuration to Claude Desktop's config file (stdio or streamableHttp).
  5. Restart Claude Desktop and verify.
claude_desktop_config.json
{
  "mcpServers": {
    "finance-mcp": {
      "type": "stdio",
      "command": "finance-mcp",
      "args": [],
      "env": {
        "TUSHARE_TOKEN": "your_tushare_token_here"
      }
    }
  }
}

Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.

.vscode/mcp.json
{
  "servers": {
    "finance-mcp": {
      "type": "stdio",
      "command": "finance-mcp",
      "args": [],
      "env": {
        "TUSHARE_TOKEN": "your_tushare_token_here"
      }
    }
  }
}

Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).

Terminal
claude mcp add finance-mcp -e TUSHARE_TOKEN=your_tushare_token_here -- finance-mcp

Run it in a terminal; replace any <…> placeholders with your own values first.

Check that it works

After configuring, restart Claude Desktop and ask "Get the current timestamp"; if the current_timestamp tool returns time information, the installation works.

Troubleshooting

  1. Ensure Node.js version >= 18
  2. Check that TUSHARE_TOKEN is correctly set
  3. Windows users may need to change command from npx to npx.cmd
  4. Check Claude Desktop logs: Windows at %APPDATA%\Claude\logs, macOS at ~/Library/Logs/Claude
  5. If using public cloud service, note rate limits; consider self-hosting

Things to try

Once connected, you can ask your AI assistant things like:

  • Analyze the technicals of Moutai (600519.SH) and compute MACD(12,26,9) and RSI(14)
  • Analyze NVIDIA (NVDA) 2024 financial performance, including the income statement and cash flow
  • Show the recent main money flow for BYD (002594.SZ)
  • Search for the latest policy and market news on the EV sector

Tools 18

current_timestamp read-only
Returns the current timestamp, supports UTC+8 timezone, multiple output formats.
finance_news read-only
Searches financial news via Baidu News crawler, supports space-separated multi-keyword OR filtering.
stock_data read-only
Retrieves stock/crypto data and technical indicators, covering 10 major markets and Binance crypto, supporting 5 technical indicators (MACD, RSI, KDJ, BOLL, MA).
stock_data_minutes read-only
Retrieves minute-level K-lines for A-shares (Tushare) and crypto (Binance), supporting multiple frequencies.
index_data read-only
Retrieves historical data for major market indices.
csi_index_constituents read-only
Retrieves CSI index constituents and weight summaries, including interval quotes, constituent weights, valuation/financial metrics.
macro_econ read-only
Retrieves 11 macro economic indicators including GDP, CPI, PPI, PMI, Shibor, etc.
company_performance read-only
A-share company financial analysis, including financial statements, management, shareholder structure, and more (13 data types).
Show 10 more tools
company_performance_hk read-only
HK stock company financial analysis, providing income statement, balance sheet, and cash flow statement.
company_performance_us read-only
US stock company financial analysis, including 4 major financial statements and comprehensive financial metrics.
fund_data read-only
Retrieves fund NAV, holdings, dividends, etc., with 85% performance improvement.
fund_manager_by_name read-only
Queries fund manager background and managed fund list.
convertible_bond read-only
Retrieves convertible bond basic information, issuance data, and conversion terms.
block_trade read-only
Retrieves block trade details and counterparty information.
money_flow read-only
Queries capital flow for individual stocks, market, and sectors, including main force, super large, large order analysis.
margin_trade read-only
Retrieves margin trading data, including underlying stocks, summaries, details, and refinancing.
dragon_tiger_inst read-only
Queries Dragon-Tiger List institutional details for a specified trading day and code.
hot_news_7x24 read-only
Retrieves 7x24 hot news based on the latest Tushare batch, deduplicated and separated by separators.

Use cases

Stock technical analysis: compute MACD, RSI, KDJ, BOLL, MA indicators.
Comprehensive analysis: combine financials, technical, capital flow, and news for investment evaluation.
CSI index constituent analysis: get constituent weights, valuation, and financial metrics.
Capital flow analysis: track capital dynamics of individual stocks, sectors, and the market.
Fund and bond queries: retrieve fund NAV, holdings, and convertible bond information.
HK and US stock financial analysis: deep dive into listed company financial statements.
Crypto analysis: view trends and technical indicators for Bitcoin and other cryptocurrencies.
Financial news and macro data: search latest news and obtain macro economic indicators.
Dragon-Tiger List queries: understand institutional buying/selling and market hotspots.

Supported clients

Claude Desktop

Listed from the project's documentation, not tested by this site.

Overview

FinanceMCP (Synapse) is a professional financial data MCP server built on the MCP protocol, integrating Tushare API and Binance API to provide comprehensive real-time financial data access for language models like Claude. It supports multi-dimensional financial data analysis including stocks, funds, bonds, macro economics, stablecoins, cryptocurrencies, and more. It includes tools for financial data queries, financial news, national statistics data, etc. The project is linked with MarkiNote to form the FinNote intelligent financial document system, aggregating over 100 financial data interfaces and organizing them into 18 MCP tools.

Similar servers

BioMCP 75 · B

One binary. One grammar. Evidence from the biomedical sources you already trust.

★ 654 · Tools 11 Compare with this →

Source revision 04df04cb31c7 Data synced 2026-10-12 Read the FMRS scoring method