2Bot
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TWOBOT_HOST | No | HTTP bind host | 127.0.0.1 |
| TWOBOT_PORT | No | HTTP bind port | 9000 |
| TWOBOT_BASE_URL | No | Optional public HTTPS URL for docs/ops | |
| TWOBOT_LOG_LEVEL | No | Logging level | INFO |
| TWOBOT_TRANSPORT | No | Transport mode: stdio or http | stdio |
| CODEX_ALLOWED_ROOTS | No | Optional cwd allowlist (: separated on macOS/Linux) | |
| TWOBOT_ENABLE_NO_AUTH | No | Enable no-auth mode for initial ChatGPT testing | true |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| run_codex_promptB | Run a prompt via local Codex CLI ( 2Bot always uses non-interactive mode and sends the prompt over stdin. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
With only one tool, there is zero ambiguity—no other tools exist to confuse with run_codex_prompt. The tool's purpose is distinct by default.
The single tool name 'run_codex_prompt' follows a clean verb_noun pattern, making it clear and predictable. With only one tool, consistency is inherently maintained.
A single tool is extremely thin for an MCP server, even for a narrow purpose. While it might serve a specific need, it feels like a minimal wrapper rather than a coherent tool set, earning a low score.
The tool covers the basic action of running a codex prompt, but the surface is incomplete—no ability to list past runs, check status, cancel, or configure the CLI. For the implied domain, notable operations are missing.