Agent Gateway MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AGENT_GATEWAY_PI_MODEL | No | Default Pi model; defaults to 'opencode-go/deepseek-v4-flash'. | opencode-go/deepseek-v4-flash |
| AGENT_GATEWAY_PI_COMMAND | No | Executable for PI provider. | |
| AGENT_GATEWAY_CODEX_MODEL | No | Default Codex model. | |
| AGENT_GATEWAY_PI_PROVIDER | No | Default Pi provider; defaults to 'opencode-go'. | opencode-go |
| AGENT_GATEWAY_KIMI_COMMAND | No | Executable for KIMI provider. | |
| AGENT_GATEWAY_CODEX_COMMAND | No | Executable for CODEX provider. | |
| AGENT_GATEWAY_ZCODE_COMMAND | No | Executable for ZCODE provider. Overrides auto-detection. | |
| AGENT_GATEWAY_CLAUDE_COMMAND | No | Executable for CLAUDE provider. | |
| AGENT_GATEWAY_PI_API_KEY_ENV | No | Windows user-environment key read for Pi; defaults to 'OPENCODE_API_KEY'. | OPENCODE_API_KEY |
| AGENT_GATEWAY_PI_PREFIX_ARGS | No | JSON array inserted before normal CLI arguments for PI provider. | |
| AGENT_GATEWAY_CLAUDE_CLEAN_ENV | No | When set to '1', removes Anthropic endpoint overrides only for the Claude child process. | |
| AGENT_GATEWAY_KIMI_PREFIX_ARGS | No | JSON array inserted before normal CLI arguments for KIMI provider. | |
| AGENT_GATEWAY_CODEX_PREFIX_ARGS | No | JSON array inserted before normal CLI arguments for CODEX provider. | |
| AGENT_GATEWAY_ZCODE_PREFIX_ARGS | No | JSON array inserted before normal CLI arguments for ZCODE provider. | |
| AGENT_GATEWAY_CLAUDE_PREFIX_ARGS | No | JSON array inserted before normal CLI arguments for CLAUDE provider. |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| agents_listA | List supported local CLI agents and their structured transport, resume, and permission capabilities. |
| agents_spawnA | Start a local CLI agent asynchronously and return a task id immediately. Use read-only unless edits are required. Parallel write tasks must use independent Git worktrees. |
| agents_resumeA | Resume a completed CLI agent session as a new asynchronous task. Never use this to inject into a session still open in an interactive TUI. |
| agents_statusB | Return the current state of an asynchronous agent task. |
| agents_waitA | Wait for an agent task to reach a terminal state, bounded by wait_seconds. |
| agents_logsA | Read agent stdout/stderr from a character cursor. Pass the returned cursor to fetch only new output. |
| agents_cancelA | Cancel a running agent task. This does not attach to or modify unrelated interactive TUI sessions. |
| kimi_statusA | Check whether the local Kimi Code CLI is callable and report its version. |
| kimi_runA | Start a new non-interactive Kimi Code agent session in a working directory. The Kimi CLI may read, edit, and run commands in that directory. Scope the prompt and work_dir carefully. |
| kimi_resumeA | Resume a Kimi Code session. Do not resume a session that is still open in an interactive TUI, because two writers can race on the same session. |
| kimi_list_sessionsA | List local Kimi Code sessions, optionally filtered by working directory. |
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 11 tools
Each tool has a clear, distinct purpose. The generic agents_* tools manage asynchronous tasks, while kimi_* tools are specific to Kimi Code sessions; even similar operations like agents_resume and kimi_resume are differentiated by target system and description.
All tools follow a consistent snake_case pattern with clear domain prefixes: agents_* for generic agent management and kimi_* for Kimi-specific operations. The pattern is predictable and uniform.
With 11 tools, the server is well-scoped for its purpose of managing local CLI agents and Kimi sessions. The count falls within the ideal range and each tool serves a distinct function.
The generic agent lifecycle (spawn, resume, status, wait, logs, cancel) is complete, and Kimi-specific tools cover status, run, resume, and listing. Minor gaps exist, such as no explicit kimi_cancel, but the generic cancel may cover it, so core workflows are supported.