Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LINGIE_MCP_LOGNoLocal file log path. Set to 'off' to disable. Auto-rotates after 5MB (default: %LOCALAPPDATA%\Lingie\mcp-server.log).
LINGIE_API_PORTNoWorkflow API port. Defaults to LocalApiPort in settings.json (usually 17856).
LINGIE_API_TOKENNoWorkflow API Bearer token. Overrides LocalApiBearerToken from settings.json.
LINGIE_GATEWAY_URLNoGateway URL. Defaults to api_server.json.
LINGIE_GATEWAY_PORTNoGateway port. Defaults to api_port in api_server.json (usually 58100).
LINGIE_MCP_OUTPUT_DIRNoOutput file download directory. Default: %LOCALAPPDATA%\Lingie\mcp-outputs.
LINGIE_GATEWAY_APP_KEYNoGateway AppKey. Set together with LINGIE_GATEWAY_USER_TOKEN to enable gateway tools. Defaults to credential from mcp-credentials.json.
LINGIE_MCP_MAX_BLOCK_MSNoBlocking wait safe window in milliseconds. Set 0 to disable (default: 20000).
LINGIE_GATEWAY_USER_TOKENNoGateway Bearer user token. Set together with LINGIE_GATEWAY_APP_KEY to enable gateway tools.

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

CapabilityDetails
tools
{
  "listChanged": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
lingie_healthA

检查灵姬客户端本地 API 的可用性:服务是否在线、本地 ComfyUI 引擎是否运行、是否需要认证。开始生成前建议先调用。

lingie_list_workflowsA

列出灵姬中可用的工作流(图片生成/视频生成/音频等)。返回 id、名称、类别、是否免费。生成分两步:先用 lingie_workflow_capabilities 查看参数,再用 lingie_run_workflow 提交。

lingie_workflow_capabilitiesA

查看指定工作流的参数模式(每个参数的名称、类型、是否必填、默认值、可选值与提交方式)。提交 lingie_run_workflow 前务必先调用本工具了解如何填 params。

lingie_run_workflowA

在灵姬中执行一个工作流(本地 ComfyUI 引擎)。提交后默认等待完成并返回输出文件的本地路径;若约 20 秒内未完成(MCP 宿主对单次调用通常只有 ~30 秒超时,超时会被掐断丢结果),自动降级为返回 run_id,任务在后台继续,用 lingie_run_result 轮询并在完成后取回本地文件。设 wait=false 立即返回 run_id。取消用 lingie_cancel_run(注意:会中断本地引擎当前正在执行的任务)。

lingie_run_statusA

查询灵姬生成任务(run_id)的当前状态、进度与输出清单(只查询,不下载输出文件)。

lingie_run_resultA

查询灵姬生成任务(run_id)并取回结果:仍在生成时返回状态与进度;已完成时把输出文件下载到本地并返回文件路径列表。配合 lingie_run_workflow 超时降级后的轮询使用。

lingie_cancel_runA

取消一个灵姬生成任务。注意:本地 ComfyUI 引擎一次只执行一个任务,取消操作会中断当前正在执行的任务(不一定是该 run_id 对应的任务)。请确认后再调用。

lingie_upload_fileA

把本地文件(图片/视频/音频)上传到灵姬的 ComfyUI 输入目录,供图生图、参考图、首帧等参数使用。返回的 filename 填入相应参数即可。

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/MechaBabyAi/Lingie.Mcp'

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