Distillery

@norrietaylor

About Distillery

Persistent shared context for AI coding sessions — capture, search, synthesize with 18 MCP tools and ambient intelligence

#stdio #http #knowledge-management #productivity

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "distillery": {
      "url": "https://distillery-mcp.fly.dev/mcp",
      "transport": "http"
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Distillery?

Distillery is a team knowledge base accessed through Claude Code skills. It captures raw information from working sessions, meetings, bookmarks, and conversations, storing them as vector embeddings in DuckDB for natural language retrieval. It runs locally over stdio or as a hosted HTTP service with GitHub OAuth.

How to use Distillery?

Install via claude plugin marketplace add norrietaylor/distillery then claude plugin install distillery. For a private knowledge base, run locally with uvx distillery-mcp and set a JINA_API_KEY. Run /setup to configure.

Key features of Distillery

14 Claude Code slash commands for knowledge management
Semantic search with provenance via /recall
Multi-entry synthesis with citations via /pour
Duplicate detection during capture via /distill
Feed monitoring and ambient digests via /watch and /radar
GitHub issues and PR syncing via /gh-sync

Use cases of Distillery

Capture team decisions and rationale during working sessions
Search and retrieve past discussions or technical decisions
Summarize meeting minutes and update them over time
Sync GitHub issues and PRs into a searchable knowledge base
Generate team activity digests and briefings

FAQ from Distillery

What dependencies are required?

Python 3.11+ and a JINA_API_KEY from jina.ai for local or hosted use. The demo server at distillery-mcp.fly.dev requires no setup.

Where is my data stored?

When running locally with uvx, data is stored in a local DuckDB database on your machine. The demo server stores data temporarily and is for evaluation only.

How do I switch from the demo server to a local instance?

Override the plugin's demo server by adding a distillery entry in ~/.claude/settings.json with uvx command and your JINA_API_KEY.

What transports does Distillery support?

It runs over stdio for local use or as an HTTP service with GitHub OAuth for team access.

Is sensitive data safe on the demo server?

No. The demo server at distillery-mcp.fly.dev is for evaluation only; do not store sensitive or confidential data.

Frequently asked questions

What dependencies are required?

Python 3.11+ and a JINA_API_KEY from jina.ai for local or hosted use. The demo server at distillery-mcp.fly.dev requires no setup.

Where is my data stored?

When running locally with uvx, data is stored in a local DuckDB database on your machine. The demo server stores data temporarily and is for evaluation only.

How do I switch from the demo server to a local instance?

Override the plugin's demo server by adding a `distillery` entry in `~/.claude/settings.json` with `uvx` command and your JINA_API_KEY.

What transports does Distillery support?

It runs over stdio for local use or as an HTTP service with GitHub OAuth for team access.

Is sensitive data safe on the demo server?

No. The demo server at distillery-mcp.fly.dev is for evaluation only; do not store sensitive or confidential data.

Comments

Basic information

More Other MCP servers

Peekaboo MCP – lightning-fast macOS screenshots for AI agents

steipete

Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.

4.8K