LearnHub MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AWS_ENDPOINT_URL | No | AWS endpoint URL, e.g. http://localhost:4566 when using Floci for S3. | |
| LEARNHUB_CLIENT_TOKEN | Yes | Client token used to resolve the tenant (e.g. demo-token-acme). | |
| LEARNHUB_TENANT_REGISTRY | No | Tenant registry location. Use an S3 URI (e.g. s3://learnhub-config/tenants.json) to use S3 instead of a local JSON file. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Read-only access to your organization's LearnHub users, trainings and enrollments.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_usersB | List users of your organization, optionally filtered by role, status or a name/email search. Large result sets are stored and summarized. |
| get_userA | Get one user's full profile by id. |
| list_trainingsC | List trainings (courses), optionally filtered by status or category. |
| get_trainingC | Get one training's details by id. |
| list_training_participantsB | List the learners enrolled in a training with their progress and score, optionally filtered by completion status. |
| list_stored_resultsA | List large results saved earlier in this session. |
| read_stored_resultB | Read a page of a stored result by result_id, using offset and limit. |
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 7 tools
Each tool has a clearly distinct scope: users vs. trainings vs. participants vs. stored-result pagination. The list/get pairs target different granularity, and the stored-result tools are cleanly split between listing saved results and reading a page.
All tool names follow a predictable snake_case verb_noun pattern (list_*, get_*, read_*). Minor verb variation between get and read is contextually appropriate and does not create confusion.
Seven tools is well-scoped for an LMS read/inspection server. Each tool earns its place and there is no obvious bloat or thinness.
The surface covers read/list access for users, trainings, participants, and paginated stored results, but lacks any create, update, delete, or enrollment mutation operations. For a learning-management domain, this leaves notable lifecycle gaps.