Distillery Mcp

Name: Distillery Mcp
Author: norrietaylor

by norrietaylorcommunityv0.6.1

Distillery is a team knowledge base accessed through Claude Code skills, refining raw information into searchable knowledge stored as vector embeddings in DuckDB. It can run locally or as a hosted HTTP service with GitHub OAuth for team access.

From the registry: Knowledge base for Claude Code with semantic search, feed intelligence, and teams

GitHub Repository

Install & configure

Prerequisites

required
uv / uvx
Install uv to get the uvx launcher.
https://docs.astral.sh/uv/
required
Jina API key
Get a free API key from jina.ai for embeddings.
https://jina.ai

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `distillery-mcp` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **uv / uvx** — Install uv to get the uvx launcher. (https://docs.astral.sh/uv/)
- **Jina API key** — Get a free API key from jina.ai for embeddings. (https://jina.ai)

Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["distillery-mcp"]
- required environment variables:
  - `JINA_API_KEY`: Jina API key used for embeddings. (example: `<your-jina-api-key>`)

Note: A hosted demo server is available at distillery-mcp.fly.dev (evaluation only, no confidential data).

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: A hosted demo server is available at distillery-mcp.fly.dev (evaluation only, no confidential data).