Skip to main content
Glama
bill-kopp-ai-dev

Percival Deep Research

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
FAST_LLMYesModel identifier for the fast LLM, must be prefixed with 'openai:', e.g., 'openai:e2ee-qwen-2-5-7b-p'.
RETRIEVERYesWeb search engine to use, e.g., 'duckduckgo' (default, no API key required).
SMART_LLMNoModel identifier for the smart LLM, must be prefixed with 'openai:', e.g., 'openai:minimax-m27'.
STRATEGIC_LLMNoModel identifier for the strategic LLM, must be prefixed with 'openai:', e.g., 'openai:zai-org-glm-4.7-flash'.
OPENAI_API_KEYYesAPI key for the Generative LLM Provider (e.g., Venice, MiniMax, OpenRouter).
OPENAI_BASE_URLYesBase URL for the LLM provider API, e.g., https://api.venice.ai/api/v1.

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

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/bill-kopp-ai-dev/percival-deep-research'

If you have feedback or need assistance with the MCP directory API, please join our Discord server