Skip to main content
Glama
noetive

io.noetive/mcp-server

Official
by noetive

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
NOETIVE_MODELNoEmbedding model to use when a call does not name one, for example Qwen3-Embedding-4B.
NOETIVE_NAMESPACENoNamespace to route a call to when the call does not name one. The name you gave it, such as acme-platform.
NOETIVE_DIMENSIONSNoEmbedding dimensionality to use when a call does not name one, for example 1024. A whole number from 1 to 65535 that matches the model.
NOETIVE_KEY_SECRETYesYour API key from the Noetive dashboard. Every tool reaches Noetive, so every tool needs it.
NOETIVE_EMBEDDINGS_URLNoAn OpenAI-compatible /v1/embeddings endpoint you run. Set it and your text is embedded here instead of by Noetive.
NOETIVE_DISABLE_GLOBAL_NSNoSet to 1 to close the shared global namespace on this server. Unset leaves it available.
NOETIVE_EMBEDDINGS_KEY_SECRETNoBearer token for that endpoint, when it needs one. Endpoints on your own machine usually do not.

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