home / mcp / bibliotheque nationale de france mcp server
Un serveur MCP (Model-Client-Protocol) pour accéder à l'API Gallica de la Bibliothèque nationale de France (BnF) et générer des rapports de recherche séquentiels.
Configuration
View docs{
"mcpServers": {
"kryzo-mcp-bibliotheque_nationale_de_france": {
"url": "https://mcp-bnf.example.local/mcp"
}
}
}You run a Python-based MCP server that lets you access the Gallica API from the Bibliothèque nationale de France and generate structured research reports. It provides search capabilities, auto-generated sequential reports, and integrated visuals to support your inquiries.
Start the MCP server locally and connect your MCP client to it to perform Gallica searches and generate reports. You will issue requests through your MCP client to search for documents, maps, or images in Gallica, then request sequential reports that compile sources, contextual sections, and visuals into a cohesive narrative.
Prerequisites: Python 3.8 or higher and Pip installed on your system.
Step 1: Clone the project repository and enter the directory.
git clone https://github.com/votre-nom/mcp-bnf.git
cd mcp-bnfStep 2: Install the Python dependencies.
pip install -r requirements.txtStep 3: Run the MCP server locally using the provided Python entry point.
py c:\chemin\vers\mcp-bnf\bnf_server.pyThe server is designed to be launched as a local stdio MCP server. You can use a MCP client to invoke search functions against the Gallica API and to generate sequential reports that include bibliographies, introductions, historical context, analyses, conclusions, and optional visuals such as images and maps.
No external configuration variables are shown as required for running the server. If you introduce environment-based configuration, place it in a secure runtime environment and do not expose credentials in command lines or code. Always limit network exposure to trusted clients when operating a local MCP server.
If the server does not start, verify that Python 3.8+ is installed, that you are running the exact path to bnf_server.py, and that the working directory is the repository root containing the bnf_server.py script and requirements.txt.
Search Gallica for documents, images, maps, and other items using criteria such as title, author, subject, date, and document type.
Generate comprehensive, structured reports that include a formatted bibliography, introduction, historical context, analysis, conclusion, and optional visuals.
Include relevant images and maps in reports to enrich the research narrative.