mcp-ai-agent-guidelines
by Anselmoo
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Observability log level (debug, info, warn, error) | info |
| HIDDEN_TOOLS | No | Comma-separated list of tool names to exclude from ListTools | |
| MCP_SLIM_MODE | No | Set to true to expose only minimal surface: task-bootstrap, meta-routing, and project-onboard | false |
| MCP_WORKSPACE_ROOT | No | Absolute path to the project directory the server should write state into (required when using npx via Claude Desktop, Cursor, or Windsurf) | |
| ENABLE_PHYSICS_SKILLS | No | Required by input validation when physics skills are not otherwise authorized; physics skills also require conventional-evidence schema validation | false |
| ALLOW_INTENSIVE_SKILLS | No | Must be true to allow resource-intensive skills such as bench-eval-suite, eval-prompt-bench, qm-path-integral-historian, and gr-spacetime-debt-metric | false |
| ALLOW_GOVERNANCE_SKILLS | No | Must be true to allow gov-* skills through criticalSkillGuard | false |
| DISABLE_ADAPTIVE_ROUTING | No | Set to true to hide routing-adapt and block adapt-* skills; enabled by default (opt-out model) | false |
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
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/Anselmoo/mcp-ai-agent-guidelines'
If you have feedback or need assistance with the MCP directory API, please join our Discord server