Skip to main content
Glama
ximenchuifeng

Codex Kimi Bridge

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
KIMI_MODELNoThe Kimi model to use.
KIMI_THINKINGNoThinking mode for Kimi.
KIMI_CODE_HOMENoPath to the Kimi Code home directory.
KIMI_AUTO_STARTNoWhether to auto-start the Kimi server when needed.true
KIMI_SERVER_URLNoThe base URL of the Kimi server.http://127.0.0.1:58627
KIMI_SERVER_TOKENNoThe Bearer token for authenticating with the Kimi server.
KIMI_PERMISSION_MODENoPermission mode for Kimi.
KIMI_PREFLIGHT_CACHE_MSNoCache lifetime for preflight checks in milliseconds.5000

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
kimi_delegate_taskD
kimi_delegate_and_waitD
kimi_wait_until_idleD
kimi_get_handoffD
kimi_review_packageD
kimi_continue_taskD
kimi_get_diffD
kimi_abortD
kimi_bridge_statusD
kimi_recent_sessionsD
kimi_find_recent_sessionD

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ximenchuifeng/codex-kimi-bridge'

If you have feedback or need assistance with the MCP directory API, please join our Discord server