@lisp MCP Server
by atlisp-org
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOST | No | HTTP listen address. | 0.0.0.0 |
| PORT | No | HTTP port the server listens on. | 8110 |
| DEBUG | No | Enable debug mode. | false |
| LLM_MODEL | No | LLM model name. | gpt-4o-mini |
| TRANSPORT | No | Transport mode: http, stdio, or ws. | http |
| BUSY_DELAY | No | Delay in milliseconds between busy retries. | 500 |
| DEBUG_FILE | No | Path to the debug log file. | |
| ENABLE_SSE | No | Enable the SSE endpoint. | true |
| CONFIG_FILE | No | Path to the configuration file. | ~/.atlisp/atlisp.config.json |
| CORS_ORIGIN | No | Comma-separated list of allowed CORS origins; '*' allows all, values starting with '*.' match as subdomain suffixes. Only the host is matched (protocol and port are ignored). | localhost,*.atlisp.cn,atlisp.cn |
| ENABLE_CORS | No | Enable CORS. | true |
| LLM_API_KEY | No | API key for the LLM used for sampling. | |
| LLM_API_URL | No | LLM API endpoint URL. | https://api.openai.com/v1/chat/completions |
| MCP_API_KEY | No | API key used to authenticate requests to the MCP server. | |
| BUSY_RETRIES | No | Number of retries when CAD is busy. | 10 |
| SSL_KEY_PATH | No | Path to the SSL private key file (enables HTTPS when used with SSL_CERT_PATH). | |
| SSL_CERT_PATH | No | Path to the SSL certificate file (enables HTTPS when used with SSL_KEY_PATH). | |
| LLM_MAX_TOKENS | No | Maximum tokens for LLM responses. | 4096 |
| RATE_LIMIT_MAX | No | Maximum number of requests per rate limit window. | 100 |
| LLM_TEMPERATURE | No | LLM sampling temperature. | 0.7 |
| MESSAGE_TIMEOUT | No | Message timeout in milliseconds. | 60000 |
| METRICS_ENABLED | No | Enable the /metrics endpoint. | true |
| ERROR_REPORT_URL | No | Endpoint used for error reporting. | https://atlisp.cn/api/error/report |
| FUNCTION_LIB_URL | No | URL of the function library JSON. | http://s3.atlisp.cn/json/functions.json |
| RATE_LIMIT_WINDOW | No | Rate limit window in milliseconds. | 60000 |
| API_KEY_RATE_LIMIT | No | Per-API-key rate limit. | 1000 |
| HEARTBEAT_INTERVAL | No | Heartbeat interval in milliseconds. | 30000 |
| RESOURCE_CACHE_TTL | No | Resource cache TTL in milliseconds. | 5000 |
| AUTO_INSTALL_ATLISP | No | Automatically install/load the @lisp core and function library after connecting to CAD (false/0/off/no disables it). | true |
| REQUEST_LOG_ENABLED | No | Enable request logging. | true |
| ERROR_REPORT_ENABLED | No | Report ERROR-level logs to atlisp.cn to help improve the project. Set to false/0/off to disable. | true |
| ATLISP_BOOTSTRAP_RETRY | No | Retry interval in milliseconds after a failed auto-install. | 60000 |
| FUNCTION_LIB_CACHE_TTL | No | Function library cache TTL in milliseconds. | 300000 |
| ATLISP_BOOTSTRAP_TIMEOUT | No | Timeout in milliseconds for each auto-install/load command. | 120000 |
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
ActivityActive
ResponsivenessNo issues