AI Universal Bridge
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AI_BRIDGE_ALLOW_WRITES | No | Set to `true` to enable local workspace writes. Each write call still requires `confirm=true`. | false |
| AI_BRIDGE_REMOTE_TOKEN | No | Random token of at least 32 bytes required before running `npm run remote` to test the optional HTTP transport. The server listens only on 127.0.0.1 by default; use a secure HTTPS tunnel for external access. | |
| AI_BRIDGE_ALLOW_CODEX_WRITES | No | Set to `true` to enable the Codex `workspaceWrite` sandbox. Each run still requires `confirm_write=true`. | false |
| AI_BRIDGE_ALLOW_REMOTE_ACTIONS | No | Set to `true` to enable external MCP calls. Each call still requires `confirm=true`. | false |
| AI_BRIDGE_DAILY_API_CALL_LIMIT | No | Limits API calls per UTC day. This is not a cost limit. |
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
ResponsivenessOutdated data