经 AI Skill Hub 精选评估,开源MCP工具:个人知识库 获评「推荐使用」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.5 分,适合有一定技术背景的用户使用。
Personal knowledge base with hybrid search and read/write access for AI agents,提供了一个开源的MCP工具,支持个人知识库的创建和管理,具有混合搜索和读写访问权限的AI代理。
开源MCP工具:个人知识库 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
Personal knowledge base with hybrid search and read/write access for AI agents,提供了一个开源的MCP工具,支持个人知识库的创建和管理,具有混合搜索和读写访问权限的AI代理。
开源MCP工具:个人知识库 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/fstamatelopoulos/cerefox
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"--mcp--------": {
"command": "npx",
"args": ["-y", "cerefox"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 开源MCP工具:个人知识库 执行以下任务... Claude: [自动调用 开源MCP工具:个人知识库 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"__mcp________": {
"command": "npx",
"args": ["-y", "cerefox"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<p align="center"> <img src="web/static/cerefox_logo.jpg" alt="Cerefox" width="160"> </p>
| Feature | Details |
|---|---|
| **Hybrid search** | Combines full-text (BM25) + semantic (vector) search with a configurable alpha weight |
| **Metadata-filtered search** | JSONB containment filter (@>) on document metadata; server-side, GIN-indexed; composable with project filter and all search modes; available across all access paths (MCP, CLI, web UI, GPT Actions) |
| **Metadata search** | Standalone metadata-only search (no text query needed); find documents by key-value criteria, project, and date range; optional content inclusion with byte budget; dedicated MCP tool, CLI command, and web UI page |
| **Project discovery** | cerefox_list_projects MCP tool for agents to discover available projects; all search results include human-readable project_names alongside UUIDs |
| **Heading-aware chunking** | Greedy section accumulation — H1/H2/H3 sections accumulate until MAX_CHUNK_CHARS; heading breadcrumb preserved per chunk |
| **Cloud embeddings** | OpenAI text-embedding-3-small (768-dim) via API — or swap to Fireworks AI |
| **Remote MCP endpoint** | cerefox-mcp Supabase Edge Function — MCP Streamable HTTP; connect Claude Desktop, Claude Code, or Cursor with just a URL and anon key; no Python install needed |
| **Local MCP server** | cerefox mcp stdio server -- local alternative with zero Edge Function usage, lower latency, and offline support; requires Python + uv + local clone |
| **Web UI** | React + TypeScript SPA (Mantine UI) at /app/; FastAPI JSON API backend; Markdown viewer, search with 4 modes, document editing, project management |
| **Multi-format ingest** | .md, .txt, .pdf (pypdf), .docx (python-docx) |
| **Batch ingest** | cerefox ingest-dir recurses directories |
| **Deduplication** | SHA-256 content hash; re-ingesting the same file is a no-op |
| **Backup and restore** | JSON snapshots, optional git commit |
| **Small-to-big retrieval** | cerefox_context_expand RPC returns chunk neighbours for richer context |
| **Audit log** | Immutable, append-only log of all write operations (create, update, delete, status change). Author attribution with author_type ('user' or 'agent'). Browsable via web UI, queryable via MCP tool and Edge Function |
| **Review status** | Schema-level review_status on documents (approved / pending_review). Auto-transitions based on author_type. Filterable on search |
| **Version governance** | Version archival (protect specific versions from cleanup), configurable retention (CEREFOX_VERSION_CLEANUP_ENABLED), version diff viewer |
| **Usage tracking** | Opt-in logging of all operations (reads and writes) across all access paths. Tracks operation type, access path (remote-mcp, local-mcp, edge-function, webapp, cli), requestor identity, query text, and result count. Controlled via cerefox config-set usage_tracking_enabled true/false -- no redeploy needed |
| **Analytics dashboard** | /app/analytics -- 7 interactive charts: calls per day, access path breakdown, top documents, top readers, operations donut, reader word cloud, and reader-to-document access pattern visualization (HEB). Date range + project + path filters. CSV export. |
---
Full walkthrough: docs/guides/quickstart.md -- zero to first ingested document and connected agent in 15 minutes. Upgrading? If you are upgrading from a previous version, see the Upgrading Guide for migration steps.
git clone https://github.com/fstamatelopoulos/cerefox.git
cd cerefox
uv sync
uv run python scripts/db_deploy.py
Edge Functions handle server-side embedding so AI agents never need a local model. Requires the Supabase CLI.
npx supabase functions deploy cerefox-search
npx supabase functions deploy cerefox-ingest
npx supabase functions deploy cerefox-mcp
Set your OpenAI key as a Supabase secret (used by the functions at runtime):
npx supabase secrets set OPENAI_API_KEY=sk-...your-key...
cp .env.example .env
Open .env and fill in these values:
| Variable | Where to find it |
|---|---|
CEREFOX_SUPABASE_URL | Supabase → Project Settings → API → Project URL |
CEREFOX_SUPABASE_KEY | Supabase → Project Settings → API Keys → **Secret key** (sb_secret_…). Legacy service_role JWT also works. |
CEREFOX_DATABASE_URL | Supabase → Project Settings → Database → **Connection pooling → Session Pooler** (port 5432). See notes below. |
OPENAI_API_KEY | [platform.openai.com/api-keys](https://platform.openai.com/api-keys) |
CEREFOX_SUPABASE_ANON_KEY (only for Edge Functions / MCP / GPT Actions) | Supabase → Project Settings → API Keys → **Legacy → anon** (JWT, eyJ…). The new sb_publishable_… does **not** work for Edge Function Bearer auth. See [docs/guides/setup-supabase.md → Supabase API keys (2026)](docs/guides/setup-supabase.md#supabase-api-keys-2026). |
CEREFOX_DATABASE_URL notes: - Use the Session Pooler (port 5432), not the Transaction Pooler (6543, no DDL) or the Direct Connection (IPv6-only on free tier). - The Session Pooler may not be a first-class option in the new "Connect" dialog; either find it under Connection pooling, or take the Transaction Pooler URI and change :6543 → :5432. - The username must include your project ref: postgres.your-project-ref — not just postgres. Without the suffix Supabase returns "Tenant or user not found". - Append ?sslmode=require to enforce TLS. - Full reference: docs/guides/setup-supabase.md → Connection pooling (2026).
该项目提供了一个开源的MCP工具,支持个人知识库的创建和管理,具有混合搜索和读写访问权限的AI代理,值得关注。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
AI Skill Hub 点评:开源MCP工具:个人知识库 的核心功能完整,质量良好。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | cerefox |
| 原始描述 | 开源MCP工具:Personal knowledge base with hybrid search and read/write access for AI agents。⭐9 · Python |
| Topics | ai-knowledge-basehybrid-searchmcppgvectorpython |
| GitHub | https://github.com/fstamatelopoulos/cerefox |
| License | Apache-2.0 |
| 语言 | Python |
收录时间:2026-05-25 · 更新时间:2026-05-30 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端