Gallica/BnF MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Port to listen on for HTTP server | 3000 |
| LOG_LEVEL | No | Logging level: error, warn, info, debug | info |
| HTTP_RETRIES | No | Maximum number of retry attempts | 3 |
| HTTP_TIMEOUT | No | HTTP request timeout in milliseconds | 30000 |
| MCP_ICON_URL | No | Absolute URL to icon - defaults to /icon.svg relative to server URL | /icon.svg |
| GALLICA_SRU_URL | No | SRU search endpoint | https://gallica.bnf.fr/SRU |
| GALLICA_BASE_URL | No | Base URL for Gallica API | https://gallica.bnf.fr |
| DEFAULT_MAX_RECORDS | No | Default maximum search results | 10 |
| DEFAULT_START_RECORD | No | Default starting record for pagination | 1 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_by_titleC | Search for documents in the Gallica digital library by title. |
| search_by_authorC | Search for documents in the Gallica digital library by author. |
| search_by_subjectC | Search for documents in the Gallica digital library by subject. |
| search_by_dateC | Search for documents in the Gallica digital library by date. Accepts YYYY, YYYY-MM, or YYYY-MM-DD format. |
| search_by_document_typeB | Search for documents in the Gallica digital library by document type (e.g., monographie, periodique, image, manuscrit, carte, musique, etc.). |
| advanced_searchC | Perform an advanced search using custom CQL query syntax. Examples: dc.creator all "Victor Hugo" and dc.type all "monographie", dc.subject all "Paris" and dc.type all "carte", dc.language all "eng". |
| natural_language_searchB | Search the Gallica digital library using natural language. This is a simplified search that uses the "gallica all" operator to search across all fields. |
| get_item_detailsA | Get full metadata for a Gallica item by its ARK identifier. Returns bibliographic data, available formats, and helpful URLs. |
| get_item_pagesB | Enumerate pages of a document. Returns logical page numbers, IIIF image URLs, and text availability flags. |
| get_page_imageA | Get IIIF image URL for a specific page. Returns URL and metadata, not binary data. |
| get_page_textA | Retrieve OCR or TEI text for a specific page when available. Returns null if text is not available. |
| sequential_reportingB | Generate a research report in a sequential, step-by-step manner using Gallica BnF sources. This tool follows a sequential approach to report generation:
Parameters:
|
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 12 tools
Most tools have distinct purposes, but there is significant overlap between the six specific search tools (search_by_author, search_by_title, etc.) and the general natural_language_search and advanced_search tools, which could cause confusion about when to use each. The sequential_reporting tool stands out as a high-level workflow tool that might be misapplied instead of using the underlying search and retrieval tools directly.
The naming is mostly consistent with a verb_noun pattern (e.g., get_item_details, search_by_author), but there are minor deviations: advanced_search uses an adjective instead of a verb, and sequential_reporting uses an adjective rather than a verb, breaking the pattern slightly. Overall, the naming is readable and follows a clear convention.
With 12 tools, the count is reasonable for a digital library server, covering search, retrieval, and reporting functions. It is slightly on the higher side but well-scoped for the domain, as it includes multiple search facets and detailed item handling, without being overwhelming.
The tool set provides strong coverage for searching and retrieving documents, including metadata, pages, images, and text. However, there are minor gaps: no tools for user account management (e.g., saving favorites or history) or batch operations (e.g., downloading multiple items), which might be useful for advanced research workflows but are not essential for core functionality.