Extended Mind
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PCP_TOKEN | Yes | Bearer token for authentication | |
| GITHUB_TOKEN | Yes | GitHub personal access token with repo scope | |
| CLASSIFY_MODEL | No | Override the classification model | |
| OPENAI_API_KEY | No | OpenAI API key (if CLASSIFY_PROVIDER is openai) | |
| WEBHOOK_SECRET | Yes | GitHub webhook HMAC-SHA256 secret | |
| ANTHROPIC_API_KEY | No | Anthropic API key (if CLASSIFY_PROVIDER is anthropic) | |
| CLASSIFY_PROVIDER | No | LLM provider for classification: 'openai' or 'anthropic' (default: openai) | |
| CLASSIFY_MAX_TOKENS | No | Maximum tokens for classification (default: 4096) | |
| CLASSIFY_REASONING_EFFORT | No | Reasoning effort for OpenAI reasoning models: none/low/medium/high/xhigh |
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
- 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/SnowLightPath/extended-mind'
If you have feedback or need assistance with the MCP directory API, please join our Discord server