Citadel

dev.citadeldb由 citadeldb.dev 发布v2.7.0更新于 Oct 24, 2026

Encrypted-first embedded database with vector search and agent memory, exposed as MCP tools

已验证STDIO仅桌面数据库知识与记忆

概览

AI 生成的概览

Citadel 是一个本地 MCP 服务器,为助手提供持久化、加密的记忆,并支持向量、关键词、时效与重要性混合检索。

可以做什么
检索与查看记忆:混合检索、按类型游标列举、按精确 ID 批量获取、图边查询、查询画像与按类型摘要,以及从磁盘重新校验原子完整性。写入与维护记忆:存储单个原子或原子化批量写入(带幂等性)、原地替换内容、增删带类型的边、重算邻居链接与重要性。选择性遗忘:按策略淘汰、按 ID 遗忘并返回可验证的擦除凭据,可选原子化擦除派生原子。
适用场景
适合需要在本机跨会话保留长期记忆、且要求静态加密、语义召回和类型化图结构的助手。适用于需要存储、搜索、校验并选择性遗忘事实的智能体或 IDE 客户端。
运行要求
以本地 stdio 进程运行,可用 uvx 启动,或通过 pip、cargo 安装;仅支持桌面客户端。需要设置 CITADEL_KEY 环境变量作为数据库口令,指定数据库路径,并在每次启动时选择嵌入模型。语义召回需先显式拉取模型(推荐 e5-large 与 ms-marco-minilm);模型不会自动下载。
安装前请注意
CITADEL_KEY 中的口令用于解锁加密数据库,需妥善保护口令及保存它的客户端配置。工具会写入、更新、建立链接并擦除记忆;遗忘不可撤销,且擦除不会吊销明文导出或早前备份、快照中保留的密钥。明文区域模式会关闭逐原子加密与加密擦除。自定义模型目录会绕过托管缓存的校验。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Citadel,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

citadeldb-mcp

mcp-name: dev.citadeldb/mcp

Model Context Protocol (MCP) server for the Citadel encrypted memory engine. Gives any MCP client (Claude Desktop, an IDE, an agent) persistent, encrypted memory.

Memory lives in a local citadeldb-mem region: AES-256 encrypted at rest, per-atom sealed and HMAC-authenticated, recalled through a hybrid vector + keyword + recency + importance fusion over a PRISM approximate nearest-neighbor index, connected by a typed edge graph, and forgotten by destroying keys (cryptographic erasure).

Install

Run it with no install. For semantic recall, pull the recommended embedder and cross-encoder reranker once, then enable both:

sh
uvx citadeldb-mcp pull e5-largeuvx citadeldb-mcp pull ms-marco-minilm

The pull commands do not open a vault. Before serving, set CITADEL_KEY to the vault passphrase (export CITADEL_KEY="your-passphrase" on macOS/Linux or $env:CITADEL_KEY = "your-passphrase" in PowerShell), then run:

sh
uvx citadeldb-mcp --db memory.cdl --embedder e5-large --reranker ms-marco-minilm

e5-large + ms-marco-minilm is the recommended semantic-recall setup. See the memory benchmarks for measured configurations. Models are never downloaded automatically.

Built-in pulls use release-pinned Hugging Face revisions. Each complete snapshot is verified against compiled sizes and SHA-256 digests, then stored with a BLAKE3 manifest under <models-dir>/<name>/<revision>/. A flat cache created by an earlier CitadelDB release is not trusted; run pull again to create the pinned snapshot. --model-dir and --reranker-dir remain explicit bring-your-own-artifact paths and bypass the managed-cache manifest. Citadel treats those directories as user-trusted and does not attest their contents.

Or install the command with pip install citadeldb-mcp or cargo install citadeldb-mcp, then wire it into Claude Desktop (claude_desktop_config.json):

json
{  "mcpServers": {    "citadel": {      "command": "citadeldb-mcp",      "args": ["--db", "/absolute/path/to/memory.cdl", "--embedder", "e5-large", "--reranker", "ms-marco-minilm"],      "env": { "CITADEL_KEY": "your-passphrase" }    }  }}

The server supports stateless MCP 2026-07-28 discovery and per-request metadata, plus the initialize-based 2025-11-25 and 2025-06-18 revisions for existing clients.

Tools (over a bounded, cancellable JSON-RPC 2.0 stdio transport):

  • mem_recall - hybrid retrieval (vector + keyword + recency + importance); filter by kind/payload, expand along the memory graph, override fusion weights, and optionally attach provenance (derived_from), per-hit integrity verdicts (attest), and resource_links to each hit
  • mem_fetch - deterministic cursor-based listing of a kind (no embedding)
  • mem_get - bounded exact-id batch retrieval in request order, with missing atoms marked explicitly
  • mem_edges - cursor-based typed graph introspection
  • mem_profile - what the memory knows about a query: recall plus its graph neighborhood
  • mem_summarize - per-kind digest of a region
  • mem_verify - re-authenticate atoms off disk: per-atom integrity verdict (authentic / tampered / key_erased / missing / plaintext_unattested)
  • mem_remember - store one atom with optional provenance and retry-safe idempotency
  • mem_remember_batch - atomically store an ordered batch; every entry carries a distinct idempotency key, and a changed reuse rejects the whole batch
  • mem_update - replace a stored atom's payload in place (preserves id, edges, and embedding)
  • mem_link / mem_unlink - add or remove one exact typed edge
  • mem_evolve - recompute an atom's neighbor links and stored importance
  • mem_evict - selective forgetting by policy (cryptographic erasure on encrypted regions)
  • mem_forget - forget atoms by id and return a verifiable erasure receipt; optionally erase their region-local derived_from closure atomically (cryptographic erasure on encrypted regions; immutable atoms require the protected-erasure opt-in)

The citadeldb-mcp binary reads the passphrase from CITADEL_KEY and serves one region (encrypted by default); only protocol messages go to stdout, diagnostics to stderr. --region-mode plaintext disables per-atom encryption and cryptographic erasure for that region; the database remains encrypted at rest. Erasure does not revoke plaintext exports or keys retained in pre-erasure backups or snapshots.

Every server invocation must select an embedder. The CPU Candle embedder is compiled into the standalone server's default build, including the citadeldb-mcp Python package; it is not included in the default citadeldb library wheel. Models are fetched only on explicit pull.

Embedder pull names: e5-large (recommended), e5-large-v2, bge-small, bge-base, bge-large, minilm. Reranker: ms-marco-minilm. Or point --model-dir at a compatible local checkpoint for the selected catalog pipeline, and build with --features cuda-embed to run on an NVIDIA GPU.

This crate is part of the Citadel workspace.

License

Apache-2.0

来源:crates/citadel-mcp/README.md,提交 fa786b2

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

4
  1. v2.7.0最新Sep 28, 2026
  2. v2.6.1Sep 25, 2026
  3. v2.6.0Sep 24, 2026
  4. v2.5.0Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分