An MCP (Model Context Protocol) server for accessing the Financial Reports API, providing tools and resources to access company financial filings, industry classifications, and related data.
Note: The server now uses only the real Financial Reports API. All mock API logic and configuration has been removed for simplicity and reliability.
There are multiple ways to run this MCP server. Choose one of the following:
Docker is the recommended way to run the MCP server for reproducibility, isolation, and ease of use.
# Build (once)
docker build -t financial-reports-mcp .
# Run
docker run --rm -i \
-e API_KEY=your_api_key_here \
-e API_BASE_URL=https://api.financialreports.eu/ \
-e MCP_TRANSPORT=stdio \
financial-reports-mcp:latest
For Docker Compose users:
# Copy and configure .env
echo "Copy .env.example to .env and fill in secrets"
cp .env.example .env
# Start services
docker-compose up
For Claude Desktop, use the following configuration. Pass secrets as -e
arguments in args
for maximum compatibility and security:
{
"mcpServers": {
"financial-reports": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e", "API_KEY=your_api_key_here",
"-e", "API_BASE_URL=https://api.financialreports.eu/",
"-e", "MCP_TRANSPORT=stdio",
"financial-reports-mcp:latest"
]
}
}
}
Why? Passing secrets as
-e
arguments inargs
guarantees Docker always receives them, regardless of how the client implements environment variable support. This is the most robust and portable approach for Claude Desktop and similar clients.
Use the Smithery CLI to install and run the server in Claude:
npx -y @smithery/cli@latest install \
@itisaevalex/financial-reports-mcp-server \
--client claude \
--key smithery_api_key
python -m venv venv # Create venv
venv\Scripts\activate # Activate on Windows
pip install -r requirements.txt
python -m src.financial_reports_mcp
# or with uv
uv run src/financial_reports_mcp.py
Tip: If you use
uv
, it automatically loads.env
from the project root.
All example scripts and configs are now located in the examples/
directory, e.g.:
examples/test_server.py
— Run the full MCP test suiteexamples/docker_claude_config.json
— Example Claude Desktop config for Dockerexamples/uvx_claude_config.json
— Example Claude Desktop config for uvexamples/python_client_example.py
— Example Python client usageRun the test suite:
python examples/test_server.py
Create a .env
file in the root directory with the following variables:
API_KEY=your_api_key_here
API_BASE_URL=https://api.financialreports.eu/
MCP_TRANSPORT=stdio
src/
— Source code directory
financial_reports_mcp.py
— MCP server main entrypoint (all tools/resources defined here)api_client.py
— API client factoryreal_api/real_client.py
— Real API client implementation.env
- Environment variables (not in git)requirements.txt
- Project dependenciesDockerfile
& docker-compose.yml
- Docker configurationsetup.py
- Package installation configurationinstall.py
- Helper for Claude Desktop installationexamples/
- Example scripts and configsscripts/
- Install scriptsget_filing_type(filing_type_id)
— Get detailed information about a filing type by its IDlist_industries(industry_group, page, page_size, search)
— List all available GICS industriesget_industry(industry_id)
— Get detailed information about a GICS industrylist_industry_groups(sector, page, page_size, search)
— List all available GICS industry groupsget_industry_group(group_id)
— Get detailed information about a GICS industry groupget_sector(sector_id)
— Get detailed information about a GICS sectorlist_sub_industries(industry, page, page_size, search)
— List all available GICS sub-industriesget_sub_industry(sub_industry_id)
— Get detailed information about a GICS sub-industrylist_sources(page, page_size)
— List all available data sourcesget_source(source_id)
— Get detailed information about a data sourceget_processed_filing(processed_filing_id)
— Get processed content for a filingget_schema(format, lang)
— Get the OpenAPI3 schema for the APIsearch_companies(params)
— Search for companies by name, ISIN, LEI, etc.get_company_detail(company_id)
— Get detailed information about a companyget_latest_filings(params)
— Get the latest financial filingsget_filing_detail(filing_id)
— Get detailed information about a specific filinglist_sectors()
— List all available GICS sectorslist_filing_types()
— List all available filing typesget_sectors_resource()
— Markdown-formatted list of GICS sectorsget_filing_types_resource()
— Markdown-formatted list of filing typesget_company_profile(company)
— Markdown-formatted company profileget_company_recent_filings(company, limit)
— Markdown-formatted list of recent filingssearch_company_by_name()
— Prompt for searching a company by namefind_latest_annual_reports()
— Prompt for finding latest annual reportsfinancial-reports://sectors
: List of all GICS sectorsfinancial-reports://filing-types
: List of all filing typesfinancial-reports://companies/{company_id}/profile
: Company profilefinancial-reports://companies/{company_id}/recent-filings
: Recent filings for a companyI want to search for information about Deutsche Bank. Please help me find:
1. Basic company details like country, sector and industry
2. Recent financial filings
3. Key financial metrics if available
I'd like to see the latest annual reports from major European banks.
Please help me:
1. Find companies in the banking sector
2. Get their latest annual reports
3. Summarize key financial metrics from these reports if available
The server can be run on:
uv
is recommended for Claude DesktopFor Windows users specifically:
Communication Issues with Claude Desktop:
-i
flag for interactive mode"Module not found" errors:
pip install -r requirements.txt
Cannot connect to the MCP server:
Authentication errors with the API:
.env
fileWhen running directly, logs are output to the console. For Docker, you can view logs with:
docker logs <container-id>
This project is licensed under the MIT License with an attribution requirement for Data Alchemy Labs. See LICENSE for details.
{
"mcpServers": {
"financial-reports": {
"env": {},
"args": [
"run",
"--rm",
"-i",
"-e",
"API_KEY=your_api_key_here",
"-e",
"API_BASE_URL=https://api.financialreports.eu/",
"-e",
"MCP_TRANSPORT=stdio",
"financial-reports-mcp:latest"
],
"command": "docker"
}
}
}
Seamless access to top MCP servers powering the future of AI integration.