Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
FOUNDRY_MODENoServer mode: full (16 tools) or minimal (1 wake tool)full
OPENAI_API_KEYNoOpenAI API key for LLM provider credentials
ANTHROPIC_API_KEYNoAnthropic API key for LLM provider credentials
FOUNDRY_MCP_API_KEYSNoComma-separated API keys required for tool access (disabled by default)
FOUNDRY_MCP_LOG_LEVELNoLogging level (DEBUG, INFO, etc.)INFO
FOUNDRY_MCP_SPECS_DIRNoPath to specs directory (auto-detected from workspace if not provided)
FOUNDRY_MCP_FEATURE_FLAGSNoAdditional feature flags to enable (e.g., planning_tools). Based on spec rollout by default
FOUNDRY_MCP_WORKFLOW_MODENoExecution mode: single, autonomous, or batchsingle
FOUNDRY_MCP_RESPONSE_CONTRACTNoForce response contract version (v2). Auto-negotiated by default

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/tylerburleigh/foundry-mcp'

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