FreeWebAI MCP Server
by Amengclass
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CDP_HOST | No | Chrome DevTools endpoint host | 127.0.0.1 |
| CDP_PORT | No | Chrome DevTools endpoint port | 9222 |
| HUB_HOST | No | daemon HTTP bind host | 127.0.0.1 |
| HUB_PORT | No | daemon HTTP bind port | 8787 |
| HUB_HEADLESS | No | Set to 1 to run Chrome headless (not recommended) | |
| HUB_MINIMIZE | No | Set to 1 to hide Chrome window | |
| PROXY_SERVER | No | Proxy server URL (e.g. http://127.0.0.1:7897) required in mainland China | |
| HUB_TIMEOUT_MS | No | Single call timeout budget in milliseconds | 120000 |
| HUB_GEMINI_FAST | No | Skip Gemini Pro model activation (faster, uses page default model) | 1 |
| AGENTCHAT_LIB_PATH | No | Path to AgentChat's skills/lib | auto-detect |
| HUB_POLL_INTERVAL_MS | No | Response polling interval in milliseconds | 1000 |
| HUB_STABILITY_WINDOW_MS | No | Completion stability window in milliseconds | 3000 |
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
ActivitySlowing
ResponsivenessNo issues