Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MCP_JWT_ISSUERYesThe public origin of the Next.js deployment without a trailing slash (e.g., https://brain.example.com). Used as the JWT issuer for MCP-to-Convex authentication.
OPENAI_API_KEYYesYour OpenAI API key used for semantic search embeddings (text-embedding-3-small). Must be set on the Convex deployment.
ANTHROPIC_API_KEYYesYour Anthropic API key used for Smart Save analysis with Claude Haiku. Must be set on the Convex deployment.
MCP_JWT_PRIVATE_JWKYesThe private JSON Web Key (JWK) used to sign short-lived Convex identity tokens. Keep server-side and never expose as a NEXT_PUBLIC_ variable.
MCP_OAUTH_ENCRYPTION_KEYYesServer-only encryption key for dynamic OAuth client registrations and short-lived authorization codes. Rotating it requires connected MCP clients to re-authorize.

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

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/jordan-hivemind/kithmind'

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