webpilot
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| API_KEYS | No | JSON mapping of bearer tokens to user names, e.g. `{"a-long-random-token":"me"}`. When set, every /api route requires `Authorization: Bearer <token>`. Required when running in Docker, where requests into the container aren't loopback. | |
| LLM_PROVIDER | No | Selects the model provider. `LLM_PROVIDER=auto` (the default) uses the first key it finds among GEMINI_API_KEY, ANTHROPIC_API_KEY and OPENAI_API_KEY. | auto |
| OPENAI_MODEL | No | Model name to use with an OpenAI-compatible server. | |
| GEMINI_API_KEY | No | Google Gemini API key. Free tier, no card required. | |
| OPENAI_API_KEY | No | OpenAI API key (paid), or any key for an OpenAI-compatible server such as Ollama. | |
| ALLOWED_DOMAINS | No | Allow-list of domains the agent may open, e.g. `["wikipedia.org","127.0.0.1","localhost"]`. By default any public website is allowed (`["*","127.0.0.1","localhost"]`). | |
| BROWSER_CHANNEL | No | Browser channel to use instead of the bundled Chromium, e.g. `msedge` for an existing Microsoft Edge installation. | |
| OPENAI_BASE_URL | No | Base URL for an OpenAI-compatible server (e.g. Ollama). | |
| ANTHROPIC_API_KEY | No | Anthropic Claude API key (paid). |
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