Schema | lesson-loop

lesson-loop

Describes the environment variables required to run the server.

Name	Required	Description	Default
`OPENAI_API_KEY`	Yes	Your OpenAI API key. Required for the MCP server to function. Used only on the server; never exposed to the frontend.
`TAVILY_API_KEY`	No	API key for Tavily. If present, used as the primary search backend. The system works without it.
`LESSONLOOP_MODEL`	No	The default model used for the main agent.	gpt-4o-mini
`LESSONLOOP_DB_PATH`	No	Path to the SQLite database file. Set this to a persistent volume to avoid data loss on redeployment.
`LESSONLOOP_MAX_STEPS`	No	Maximum number of LLM calls per run.	50
`LESSONLOOP_SCHEDULER`	No	If set to '1', automatically executes queued concepts via cron.	0
`LESSONLOOP_MAX_SECONDS`	No	Maximum time per run in seconds.	420
`LESSONLOOP_ARTIFACT_DIR`	No	Directory where generated lesson packs (artifacts) are stored. Set this to a persistent volume to avoid data loss on redeployment.
`LESSONLOOP_MAX_COST_USD`	No	Maximum cost per run in USD. The run stops automatically if this is exceeded.	0.50
`LESSONLOOP_REVIEW_MODEL`	No	The model used for the reviewer agent. Defaults to the value of LESSONLOOP_MODEL.
`LESSONLOOP_MAX_REVISIONS`	No	Maximum number of review → rewrite cycles.	1
`LESSONLOOP_WEBHOOK_TOKEN`	No	If set, enables POST /api/webhook/run for webhook-triggered runs.
`LESSONLOOP_RATE_LIMIT_PER_HOUR`	No	Number of runs allowed per IP address per hour.	10

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.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources