Digiforma MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DIGIFORMA_API_URL | No | Endpoint GraphQL (défaut : `https://app.digiforma.com/api/v1/graphql`). | https://app.digiforma.com/api/v1/graphql |
| DIGIFORMA_API_TOKEN | Yes | Le token Bearer généré depuis votre compte Digiforma. |
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 |
|---|---|
| digiforma_graphqlA | Run an arbitrary GraphQL query or mutation against the Digiforma API. Use this for anything not covered by the convenience tools below, or to run introspection queries to discover the full schema (e.g. |
| digiforma_introspect_schemaA | Fetch the list of GraphQL type names exposed by the Digiforma API (a lightweight introspection query). Useful to discover which objects and fields are available before writing a custom digiforma_graphql query. |
| digiforma_list_traineesA | List trainees (learners/apprenants) registered in Digiforma, with their basic contact info. |
| digiforma_get_traineeA | Get a single trainee by id, including their training sessions. |
| digiforma_list_training_sessionsA | List training sessions (sessions de formation) configured in Digiforma. |
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 5 tools
Each tool has a clearly distinct purpose: the GraphQL and introspection tools serve as meta-access, while list/get trainee and list training sessions target specific resources with no overlap. Even the generic GraphQL tool is explicitly framed as a fallback, avoiding confusion.
All tools follow a consistent 'digiforma_' prefix followed by a verb_noun pattern (e.g., list_trainees, get_trainee, introspect_schema). The naming is uniform and predictable, making it easy for an agent to infer behavior.
With 5 tools, the server is well-scoped for a domain focused on trainees and training sessions. The inclusion of a generic GraphQL tool covers edge cases without bloating the count, making it neither too thin nor too heavy.
The convenience tools cover the primary read operations (list/get trainees, list sessions), and the generic GraphQL tool enables any missing operations such as create/update/delete. Minor gaps exist for convenient mutation access, but the fallback prevents dead ends.