RAG memory for LLM agents over Garnet Vector Sets: store text as embeddings, recall by meaning.
What it says
The record the registry holds
How you get it
There is no address to call. This one is a package you install and run yourself, wherever your assistant runs.
GarnetMcp.Server · nuget · 0.1.2
the recordCopied from the official MCP registry, exactly as it holds it.
{
"server": {
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-10-17/server.schema.json",
"name": "io.github.tarazou9/garnet-mcp",
"description": "RAG memory for LLM agents over Garnet Vector Sets: store text as embeddings, recall by meaning.",
"title": "garnet-mcp",
"repository": {
"url": "https://github.com/tarazou9/garnet-mcp",
"source": "github"
},
"version": "0.1.2",
"packages": [
{
"registryType": "nuget",
"registryBaseUrl": "https://api.nuget.org/v3/index.json",
"identifier": "GarnetMcp.Server",
"version": "0.1.2",
"transport": {
"type": "stdio"
},
"environmentVariables": [
{
"value": "{garnet_host}",
"variables": {
"garnet_host": {
"description": "Hostname of the Garnet (or any Redis-compatible) server. Defaults to 127.0.0.1 when left blank."
}
},
"name": "Garnet__Host"
},
{
"value": "{garnet_port}",
"variables": {
"garnet_port": {
"description": "Port of the Garnet server. Defaults to 6379 when left blank."
}
},
"name": "Garnet__Port"
},
{
"value": "{embeddings_provider}",
"variables": {
"embeddings_provider": {
"description": "Embedding provider: 'AzureOpenAI' for real embeddings, or 'Fake' for a deterministic offline provider (no external calls)."
}
},
"name": "Embeddings__Provider"
},
{
"value": "{embeddings_endpoint}",
"variables": {
"embeddings_endpoint": {
"description": "Azure OpenAI endpoint, e.g. https://YOUR-RESOURCE.openai.azure.com/ (required when Embeddings__Provider=AzureOpenAI). Authenticated keyless via DefaultAzureCredential."
}
},
"name": "Embeddings__Endpoint"
},
{
"value": "{embeddings_deployment}",
"variables": {
"embeddings_deployment": {
"description": "Azure OpenAI embedding deployment name, e.g. text-embedding-3-small."
}
},
"name": "Embeddings__DeploymentName"
},
{
"value": "{embeddings_dimensions}",
"variables": {
"embeddings_dimensions": {
"description": "Embedding vector dimensions, e.g. 1536 for text-embedding-3-small."
}
},
"name": "Embeddings__Dimensions"
}
]
}
]
},
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"statusChangedAt": "2026-08-10T19:37:51.200207Z",
"publishedAt": "2026-08-10T19:37:51.200207Z",
"updatedAt": "2026-08-10T19:37:51.200207Z",
"isLatest": true
}
}
}
Make it installable
Draft an Agent Plugin from this
An MCP server is raw capability: some tools, wired to something. An Agent Plugin is the packaging that says what job it does, what it leaves behind and where it stops. The prompt below carries this record and asks for the packaging; your own assistant writes it, and nothing here is sent anywhere.
What this is
MCP server
application/mcp-server-record+jsonlocal · you run it yourselfversion 0.1.2last seen 2026-08-23
These are the publisher's own words, filed by them with the official MCP registry and mirrored here. This catalog did not read them from the publisher and has not run, called or installed anything.