Skills/PyPI/sibyl-memory-mcp

sibyl-memory-mcp@0.4.1

VERIFIED· install only

Publisher claims: "MCP server for Sibyl Memory Plugin: wraps the local SQLite + FTS5 memory engine and exposes it to MCP-compatible agents (Claude Code, Codex, Cursor, Continue, anything that speaks MCP)." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher sibyl-labs · publishing for 180 daysInstalls 276Last detonated 2d ago
$claude mcp add sibyl-memory-mcp -- uvx sibyl-memory-mcp
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
SIBYL_CREDENTIALSConfiguration, not credentials: SIBYL_MEMORY_DB
Where it talks to
no vendor host named in the codeAlso sibyllabs.org, claude.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names sibyllabs.org, claude.com as well as its own vendor. The guard injects SIBYL_CREDENTIALS only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx sibyl-memory-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-12 and scored it 90/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionsibyl_memory_mcp/server.py:235 · File type combined with upload action — agent may exfiltrate local data files# or credentials.json appeared / disappeared (post-init / post-logout),Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File permission modification commandsibyl_memory_mcp/server.py:278 · File permission modification command — agent changes file ownership/permissions# ignored when the dir already exists, so chmod belt-and-suspenders to coverFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

Cost to the agent

Instructions loaded
≈85 tok
1 file · 4 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

No advisories in OSV for sibyl-memory-mcp@0.4.1 as of 2d ago. This is the package itself, not its dependencies.