Skip to main content

sibyl-memory-mcp

MCP server for Sibyl Memory Plugin. Exposes the local SQLite + FTS5 memory engine to any MCP-compatible agent: Claude Code, Codex CLI, Cursor, Continue, anything that speaks Model Context Protocol.

Install

pip install sibyl-memory-mcp

You also need an activated Sibyl Memory account. If you haven't already:

sibyl init

This creates ~/.sibyl-memory/credentials.json (server-issued, HMAC-signed) and a local SQLite database at ~/.sibyl-memory/memory.db. The MCP server reads both automatically.

Add to Claude Code

Edit ~/.claude/settings.json (global) or .mcp.json (project-local):

{
  "mcpServers": {
    "sibyl-memory": {
      "command": "sibyl-memory-mcp"
    }
  }
}

Restart Claude Code. The 8 memory tools (prefixed memory_*) become available immediately.

Add to Codex CLI

Edit ~/.codex/config.toml:

[[mcp_servers]]
name = "sibyl-memory"
command = "sibyl-memory-mcp"

Restart Codex.

Run with Docker

A first-party image is provided at the repo root (Dockerfile, docker-compose.yml, .dockerignore). The image is non-root, runs on a pinned slim Python base, and bakes in no secrets. Memory lives on a mounted volume so it survives container recreation.

The MCP server speaks stdio, not HTTP. It is not a daemon you leave running. Run it attached to an MCP client's stdin, or via docker compose run.

Build:

docker build -t sibyl-memory-mcp:local .

First, activate on the host so the mounted volume carries your credentials:

sibyl init

Run attached, mounting your host ~/.sibyl-memory for memory.db and credentials.json:

docker run -i --rm \
  -v "$HOME/.sibyl-memory:/home/app/.sibyl-memory" \
  sibyl-memory-mcp:local

Note the -i (keep STDIN open) and the absence of -t (no TTY): the MCP client drives stdin programmatically.

Wire it into Claude Code by pointing the command at the container:

{
  "mcpServers": {
    "sibyl-memory": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-v", "/absolute/path/to/your/.sibyl-memory:/home/app/.sibyl-memory",
        "sibyl-memory-mcp:local"
      ]
    }
  }
}

Using Compose (note run, not up, because it is a stdio server):

docker compose run --rm sibyl-memory-mcp

Environment overrides (SIBYL_MEMORY_DB, SIBYL_CREDENTIALS, SIBYL_TENANT_ID) are passed through when set on the host. No secret is ever written into the image or the compose file. Credentials arrive only through the mounted volume.

Tools exposed

Tool What it does
memory_remember Store an entity by (category, name)
memory_recall Read an entity by exact key
memory_search FTS5 search across all entities
memory_list List entities in a category
memory_forget Archive an entity (recoverable)
memory_set_state Write a HOT-tier state doc
memory_get_state Read a HOT-tier state doc
memory_record_event Append a COLD-tier journal event

Full docs at docs.sibyllabs.org/memory/integrations.

Environment overrides

Var Default What it overrides
SIBYL_MEMORY_DB ~/.sibyl-memory/memory.db Local SQLite path
SIBYL_CREDENTIALS ~/.sibyl-memory/credentials.json Credentials file path

Tier behavior

  • Free tier: 8 tools work. Hard-capped at 2 MB of local storage. Writes that would push past the cap return CAP_EXCEEDED with an upgrade_url. Self-learning and memory-check-up tools are not exposed on free tier.
  • Paid tiers (Sync / Stake / Lifetime / Enterprise): cap removed. All tools enabled.

The cap-gate runs against the server-authoritative tier (verified via HMAC-signed credentials): the MCP server can't bypass it by editing the local file.

License

MIT: same as the rest of the sibyl-memory-* family.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

sibyl_memory_mcp-0.1.14.tar.gz (26.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

sibyl_memory_mcp-0.1.14-py3-none-any.whl (16.7 kB view details)

Uploaded Python 3

File details

Details for the file sibyl_memory_mcp-0.1.14.tar.gz.

File metadata

  • Download URL: sibyl_memory_mcp-0.1.14.tar.gz
  • Upload date:
  • Size: 26.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.12.3

File hashes

Hashes for sibyl_memory_mcp-0.1.14.tar.gz
Algorithm Hash digest
SHA256 6468dd5ac34643d6f15bccdcb77f590a5f4c3dfa848008a674697bf9ed4c3dbd
MD5 d1c4c87001417c8e7234eca040c2d77d
BLAKE2b-256 faf47f4fa13b2ca8cc334fdbb890c6218bd3f04b3da4bbbcf5c0639d1eb96ecf

See more details on using hashes here.

File details

Details for the file sibyl_memory_mcp-0.1.14-py3-none-any.whl.

File metadata

File hashes

Hashes for sibyl_memory_mcp-0.1.14-py3-none-any.whl
Algorithm Hash digest
SHA256 2e32099d30c7f7abf47a62fb9b19e8cb6cefa8cfaa2b6741b244af3dcb4c8ad3
MD5 060376e37319503fa3b480651431d78e
BLAKE2b-256 64d25e291331dd2e6da520eb1bf020c56c119784969df9b5b86ba659c4cbfe4c

See more details on using hashes here.

Release history Release notifications | RSS feed

This release

0.1.14 This release

2 files

0.1.13

1 file

0.1.12

1 file

0.1.11

1 file

0.1.10

1 file

0.1.9

2 files

0.1.8

1 file

0.1.7

1 file

0.1.6

1 file

0.1.5

2 files

0.1.4

2 files

0.1.3

2 files

0.1.2

2 files

0.1.1

2 files

0.1.0

2 files

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page