CodeArts MCP
by David-piex
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_HTTP_HOST | No | HTTP bind address (default 127.0.0.1, set 0.0.0.0 for container) | 127.0.0.1 |
| MCP_HTTP_PORT | No | HTTP port (default 3000) | 3000 |
| MCP_TRANSPORT | No | Transport mode: 'stdio' or 'http' | |
| HUAWEICLOUD_AK | No | Access key for stdio mode | |
| HUAWEICLOUD_SK | No | Secret key for stdio mode | |
| MCP_SERVER_NAME | No | Server name | |
| CODEARTS_MCP_URL | No | CLI remote HTTP MCP endpoint | |
| HUAWEICLOUD_REGION | No | Region for stdio mode (e.g., cn-north-4) | |
| MCP_AUTH_DATA_PATH | No | Path to encrypted auth store (default .codearts-mcp/auth-store.json) | .codearts-mcp/auth-store.json |
| MCP_SERVER_VERSION | No | Server version | |
| CODEARTS_CLI_CONFIG | No | CLI profile config file path (default ~/.codearts-mcp-cli.json) | ~/.codearts-mcp-cli.json |
| CODEARTS_CLI_FORMAT | No | CLI default output format: json, text, or table (default json) | json |
| MCP_AUTH_MASTER_KEY | No | Master key for session encryption (required in http mode) | |
| CODEARTS_CLI_PROFILE | No | CLI default profile name | |
| CODEARTS_CLI_TRANSPORT | No | CLI default transport mode: 'local' or 'http' (default local) | local |
| MCP_AUTH_COOKIE_SECURE | No | Set Secure flag on cookies when using HTTPS (default false) | false |
| CODEARTS_MCP_AUTH_TOKEN | No | CLI Bearer auth token for remote mode | |
| MCP_HTTP_ALLOWED_ORIGINS | No | Comma-separated allowed origins for browser CORS | |
| MCP_ENABLED_PRODUCT_FAMILIES | No | Comma-separated list of product families to expose | |
| MCP_AUTH_WRITE_RATE_LIMIT_WINDOW_MS | No | Auth write rate limit window in ms (default 60000) | 60000 |
| MCP_AUTH_WRITE_RATE_LIMIT_MAX_REQUESTS | No | Auth write rate limit max requests per session per window (default 3000) | 3000 |
| MCP_PRODUCT_WRITE_RATE_LIMIT_WINDOW_MS | No | Write rate limit window in ms (default 60000) | 60000 |
| MCP_PRODUCT_WRITE_RATE_LIMIT_MAX_REQUESTS | No | Write rate limit max requests per session per window (default 3000) | 3000 |
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 | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/David-piex/codearts-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server