AI Chat MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| host | No | 监听地址；非回环地址必须配置 authToken (Listening address; non-loopback addresses require an authToken) | 127.0.0.1 |
| port | No | 监听端口 (Listening port) | 8080 |
| authToken | No | 可选 Bearer Token，空字符串表示不校验；设为 "random" 会生成随机 Token 并打印到启动日志，重启后失效 (Optional bearer token; empty means no auth; 'random' generates a random token logged at startup) | |
| jsonGraceMs | No | 客户端返回 JSON 前的宽限等待时间（毫秒）(Grace period in milliseconds before replying with JSON for fast responses) | 3000 |
| maxBodyBytes | No | 请求体最大字节数 (Maximum request body size in bytes) | 1048576 |
| sseKeepAliveMs | No | SSE 心跳间隔（毫秒）(SSE keep-alive interval in milliseconds) | 15000 |
| defaultTimeoutMs | No | 每次单独对话轮次的默认超时时间（毫秒）(Default timeout for a single conversation turn in milliseconds) | 600000 |
| enableLegacyStreamableHttp | No | 是否同时提供旧版 SSE 传输 (Whether to also expose the legacy /sse transport) | 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
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
ResponsivenessNo issues