io.github.norrietaylor/distillery-mcp
Official什么是 Distillery?
Distillery 是一个通过 Claude Code 技能访问的团队知识库。它将来自工作会话、会议、书签和对话的原始信息提炼为浓缩的、可搜索的知识——以向量嵌入的形式存储在 DuckDB 中,并通过自然语言检索。可通过 stdio 在本地运行,也可作为托管 HTTP 服务运行,并支持 GitHub OAuth 供团队访问。
Distillery 实现了最高价值的转化——从噪声到信号——并使其成为整个团队都能使用的工具。
Related MCP server: Rememberizer MCP Server
技能
Distillery 提供 15 个 Claude Code 斜杠命令:
技能 | 用途 | 示例 |
| 捕获会话知识并检测重复 |
|
| 带来源追溯的语义搜索 |
|
| 多条目综合并附引用 |
|
| 对比内部知识与环境情报,提供方向性评估 |
|
| 存储 URL 并自动生成摘要 |
|
| 会议记录,支持追加更新 |
|
| 分类条目并处理审核队列 |
|
| 管理监控的订阅源 |
|
| 环境订阅摘要及来源建议 |
|
| 调整订阅相关性阈值 |
|
| 基于内部条目的团队活动摘要 |
|
| 将 GitHub issues/PR 同步到知识库 |
|
| 深度上下文构建器,支持关系遍历 |
|
| 带指标的团队知识仪表盘 |
|
| MCP 连接与配置的入门向导 |
|
快速开始
第 1 步:安装插件
claude plugin marketplace add norrietaylor/distillery
claude plugin install distillery这将安装全部 15 个技能。插件不会自动配置 MCP 服务器——请运行 /setup(见下文)来添加一个。推荐的配置通过 uvx --from 'distillery-mcp[fastembed]>=0.6.0' distillery-mcp 本地运行——在您的机器上构建一个私有的、自包含的知识库,使用设备端 fastembed 嵌入(无需 API 密钥)。需要 Python 3.11+ 和 uv(安装:curl -LsSf https://astral.sh/uv/install.sh | sh)。
第 2 步(可选):改用 Jina 或 OpenAI
默认的 fastembed 提供程序可离线运行,无需 API 密钥。如果您更愿意使用托管的嵌入服务,请设置 DISTILLERY_EMBEDDING_PROVIDER 并提供相应的 API 密钥:
# Jina (free tier at jina.ai)
export DISTILLERY_EMBEDDING_PROVIDER=jina
export JINA_API_KEY=jina_...
# Or OpenAI
export DISTILLERY_EMBEDDING_PROVIDER=openai
export OPENAI_API_KEY=sk-...uvx 会从您的 shell 环境中继承这些变量。完整的提供程序配置块(包括用于 fastembed 模型选择的选项 C)请参阅 distillery.yaml.example。
重启 Claude Code 并运行入门向导:
/setup试用托管演示(可选)
想在本地不安装任何东西的情况下进行评估?将托管演示配置为 distillery-mcp.fly.dev 而不是本地服务器:
claude mcp add distillery --scope user --transport http --url https://distillery-mcp.fly.dev/mcp演示服务器:
distillery-mcp.fly.dev仅用于评估。请勿存储敏感或机密数据。
完整的配置选项请参阅本地设置指南,或部署您自己的实例供团队使用。
开发
uv pip install -e ".[dev]"
# or
pip install -e ".[dev]"
pytest # run tests
mypy --strict src/distillery/ # type check
ruff check src/ tests/ # lint完整指南请参阅贡献指南。
许可证
Apache 2.0 — 详情请参阅 LICENSE。
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables AI systems to remember interactions, understand document context through semantic search, and intelligently route requests with persistent memory and quality-scored content synthesis.
- AlicenseNot gradedqualityDmaintenanceEnables semantic search and retrieval of personal and team knowledge from connected sources like Slack, Gmail, Google Drive, and Dropbox, with the ability to save new information for future recall.Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables semantic search and retrieval of information from personal and team knowledge repositories including Slack, Gmail, Dropbox, Google Drive, and uploaded files. Allows storing new information for future recall through AI-powered search.Apache 2.0
- AlicenseAqualityDmaintenanceEnables AI assistants to search, browse, and save to a semantic knowledge graph with vector search and hierarchical organization.51MIT
Related MCP Connectors
Your company's brain for AI agents. Cited, permission-aware knowledge across every system.
Shared, permission-aware company context for AI agents, with provenance, approvals and audit.
End-to-end agent-managed company brain. Docs, diagrams, plans, Knowledge Graph. Lean & affordable.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/norrietaylor/distillery'
If you have feedback or need assistance with the MCP directory API, please join our Discord server