agent-kanban
by warOnSaaS
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GITHUB_TOKEN | Yes | Token that can read and write that repo (fine-grained: Contents read/write, Administration read/write to invite the owner) | |
| OAUTH_SECRET | Yes | Long random string; signs sessions and tokens | |
| WORKSPACE_TZ | No | e.g. America/New_York (default UTC) | |
| RESEND_API_KEY | No | Optional, emails urgent alerts | |
| WORKSPACE_NAME | Yes | Shown to people, e.g. Acme Ops | |
| WORKSPACE_REPO | Yes | owner/repo of the workspace repo | |
| OAUTH_CLIENT_ID | No | Optional, for the ChatGPT GPT. See docs/chatgpt-gpt.md | |
| WORKSPACE_CONTACT | Yes | Who people message when stuck | |
| OAUTH_CLIENT_SECRET | No | Optional, for the ChatGPT GPT. See docs/chatgpt-gpt.md | |
| GITHUB_OAUTH_CLIENT_ID | Yes | From GitHub OAuth app step 2 | |
| WORKSPACE_CONTACT_EMAIL | Yes | Their email, offered when someone's GitHub account uses a different email | |
| GITHUB_OAUTH_CLIENT_SECRET | Yes | From GitHub OAuth app step 2 |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues