Skip to main content

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 and explicitly select the keyword-only test embedder (no downloads):

uvx citadeldb-mcp --db memory.cdl --embedder mock

For the best recall (recommended - this is the benchmark config): pull the semantic embedder and the cross-encoder reranker once, then enable both:

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

e5-large + ms-marco-minilm is the highest-recall setup and the exact config behind the memory benchmark numbers. 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):

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

Tools (over a synchronous, hand-rolled 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 listing of a kind (no embedding)
  • mem_edges - 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 / mem_remember_batch - store atoms with payload, importance, TTL, immutability
  • mem_update - replace a stored atom's payload in place (preserves id, edges, and embedding)
  • mem_link - connect atoms with a typed edge
  • mem_evolve - recompute an atom's neighbor links and score
  • mem_evict - selective forgetting by policy (cryptographic erasure on encrypted regions)
  • mem_forget - forget atoms by id and return a verifiable erasure receipt (cryptographic erasure on encrypted regions; skips immutable atoms unless forced)

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.

Every server invocation must select an embedder. Use --embedder mock only when keyword-only recall is intentional. The (CPU) Candle embedder is compiled into the default build; models are fetched only on explicit pull, never automatically. e5-large + the ms-marco-minilm reranker (shown above) is the recommended, highest-recall setup.

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

Release files for citadeldb-mcp 2.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for citadeldb-mcp 2.1.0
File Size Uploaded
citadeldb_mcp-2.1.0.tar.gz 1.6 MB Details

Built distributions (wheels)

Table of built distributions (wheels) for citadeldb-mcp 2.1.0
File
citadeldb_mcp-2.1.0-py3-none-win_amd64.whl Python 3 none Windows x86-64 Details
citadeldb_mcp-2.1.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl Python 3 none Linux glibc 2.17+ x86-64 Details
citadeldb_mcp-2.1.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl Python 3 none Linux glibc 2.17+ ARM64 Details
citadeldb_mcp-2.1.0-py3-none-macosx_11_0_arm64.whl Python 3 none macOS 11.0+ ARM64 Details
citadeldb_mcp-2.1.0-py3-none-macosx_10_12_x86_64.whl Python 3 none macOS 10.12+ x86-64 Details

Total release size: 41.2 MB

Release files / citadeldb_mcp-2.1.0.tar.gz

Download URL citadeldb_mcp-2.1.0.tar.gz
Size 1.6 MB
Tags Source
SHA-256 checksum
How to use checksums
321a584bd308caf21c85a233147651df1f0072c5d0d0a92dbc6af80c3435add7
BLAKE2b-256 checksum
How to use checksums
d75d2568846553af4035c76b89372ae22ab59b64054795f8e29040bb172c0944
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 30, 2026.

Transparency log

Release files / citadeldb_mcp-2.1.0-py3-none-win_amd64.whl

Download URL citadeldb_mcp-2.1.0-py3-none-win_amd64.whl
Size 8.5 MB
Tags Python 3 Windows x86-64
SHA-256 checksum
How to use checksums
50dac39c2ab4f1500973b85ff13cb843d92b90cfe28051e52972425a5c45bf94
BLAKE2b-256 checksum
How to use checksums
03998dbd0c0e5009b275d21e209a4765965cd134fbe0d13239c041605a9de19a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 30, 2026.

Transparency log

Release files / citadeldb_mcp-2.1.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Download URL citadeldb_mcp-2.1.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Size 8.2 MB
Tags Linux glibc 2.17+ x86-64 Python 3
SHA-256 checksum
How to use checksums
7fbe09113e3784ae0daf3ad03bdd3b2da8279368c18603eea5035e100d8554d3
BLAKE2b-256 checksum
How to use checksums
2b1efda6d6ef9a9ea7a334dd6268a2f701199991a098f2f439778ad49361a139
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 30, 2026.

Transparency log

Release files / citadeldb_mcp-2.1.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl

Download URL citadeldb_mcp-2.1.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
Size 7.6 MB
Tags Linux glibc 2.17+ ARM64 Python 3
SHA-256 checksum
How to use checksums
29fa43814472179b3feba7775e6a0ac1eac8deb626c91991a11e9b003177f5fd
BLAKE2b-256 checksum
How to use checksums
8d101c7240e12349a1afe8ffc85fe80195a81bdfa66b5c66d536f3b66c109339
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 30, 2026.

Transparency log

Release files / citadeldb_mcp-2.1.0-py3-none-macosx_11_0_arm64.whl

Download URL citadeldb_mcp-2.1.0-py3-none-macosx_11_0_arm64.whl
Size 7.3 MB
Tags Python 3 macOS 11.0+ ARM64
SHA-256 checksum
How to use checksums
446c8ccbdd8a420dbe5809d1c6111b24f2a9c1a273088a1e96b72ed17d71b0a0
BLAKE2b-256 checksum
How to use checksums
f88c9cdb258a21a6a8d448e093d6b1c03f3efc39e34f7a69a3bd318240e838e8
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 30, 2026.

Transparency log

Release files / citadeldb_mcp-2.1.0-py3-none-macosx_10_12_x86_64.whl

Download URL citadeldb_mcp-2.1.0-py3-none-macosx_10_12_x86_64.whl
Size 8.0 MB
Tags Python 3 macOS 10.12+ x86-64
SHA-256 checksum
How to use checksums
876e5a788bc96f612dbb511e1232a40020b1a93f2120327d0cf73bc9c4cd28ad
BLAKE2b-256 checksum
How to use checksums
4f3ee5f75c1f81f90058be2e1a7da53c7706d3e9f9bd7393ba51f406ed466906
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 30, 2026.

Transparency log

Release history Release notifications | RSS feed

2.6.1

6 release files

2.6.0

6 release files

2.5.0

6 release files

2.4.0

6 release files

2.3.0

6 release files

2.2.0

6 release files

This release

2.1.0 This release

6 release files

2.0.0

6 release files

1.15.0

6 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page