Schema | softagenda MCP

softagenda MCP

Describes the environment variables required to run the server.

Name	Required	Description	Default
`HOST`	No	HTTP mode only. Host the server listens on. It listens only on localhost unless you set `HOST`.	127.0.0.1
`PORT`	No	HTTP mode only. Port the server listens on.	8787
`TRUST_PROXY`	No	`1` to key limits on the first `X-Forwarded-For` address. Only use it behind a proxy you control.	0
`OPENAI_MODEL`	No	Required when using the `openai` provider.
`LIMIT_PER_DAY`	No	Shared daily budget (HTTP only).	300
`LIMIT_PER_HOUR`	No	Preps per person per hour (HTTP only). IPv6 is grouped by /64.	5
`MCP_AUTH_TOKEN`	No	HTTP mode only. Require `Authorization: Bearer <token>`.
`OPENAI_API_KEY`	No	Required when using the `openai` provider.
`ALLOWED_ORIGINS`	No	Comma-separated browser origins allowed to call the server. Requests without an `Origin` header are always allowed.
`ANTHROPIC_MODEL`	No	Model to use for the `anthropic` provider.	claude-sonnet-5-5
`OPENAI_BASE_URL`	No	Any Responses-API-compatible gateway for the `openai` provider.	https://api.openai.com/v1
`ANTHROPIC_API_KEY`	No	Required when using the `anthropic` provider.
`GENERATION_DISABLED`	No	`1` refuses every prep with a "busy" message.	0
`SOFTAGENDA_PROVIDER`	No	The AI provider to use: `anthropic` or `openai`.	anthropic

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

This server cannot be deployed

ActivityMaintained

ResponsivenessNo issues