Schema | yargi-mcp-nvidia-semantic

yargi-mcp-nvidia-semantic

Describes the environment variables required to run the server.

Name	Required	Description	Default
`NVIDIA_API_KEY`	No	NVIDIA API key (legacy, used for both embedding and LLM).
`EMBEDDING_PROVIDER`	No	Embedding provider. Set to 'local' to use NVIDIA API via LOCAL_EMBEDDING_* variables.	local
`LOCAL_EMBEDDING_MODEL`	No	Embedding model name, e.g. nvidia/nv-embed-v1.	nvidia/nv-embed-v1
`BEDESTEN_RATE_CAPACITY`	No	Initial capacity for the Bedesten rate limiter.	1
`BEDESTEN_RATE_REFILL_S`	No	Rate limiter refill interval in seconds.	4.0
`EMBEDDING_PROMPT_STYLE`	No	Prompt style for embeddings.	raw
`LOCAL_EMBEDDING_API_KEY`	No	NVIDIA API key for embeddings (starts with nvapi-).
`BEDESTEN_RATE_MAX_WAIT_S`	No	Maximum wait time in seconds for Bedesten rate limiter.	60
`LOCAL_EMBEDDING_BASE_URL`	No	Base URL for the NVIDIA embedding API.	https://integrate.api.nvidia.com/v1
`LOCAL_EMBEDDING_DIMENSION`	No	Dimension of the embedding vectors.	4096
`LOCAL_EMBEDDING_INPUT_TYPE`	No	Input type for asymmetric models: 'auto' or 'off'.	auto
`BEDESTEN_SEMANTIC_BATCH_SIZE`	No	Number of decisions to process in a semantic search batch.	30
`BEDESTEN_SEMANTIC_MAX_RETRIES`	No	Maximum retries for Bedesten rate-limited requests.	3

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.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

This server cannot be deployed

ActivitySlowing

ResponsivenessNo issues