Yggdrasil Memory (VonderVuflya) MCP Server
yggdrasil-memory
PyPI
v0.15.0
Published by vondervuflya — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
One shared, durable memory for all your AI coding agents — MCP, local-first, zero-dependency.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 1.2 = 99. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −1.2 | Hardcoded JSON Web Token in test/example/packaging MTC-SRC-008 | exfiltration |
2. Client adoption risk — 99 − 7 = 92. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 11
high Shell/command execution in server code (yggdrasil/cli.py)MTC-SRC-002
In the server's implementation (`yggdrasil/cli.py:166`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: return 1 return subprocess.call(["bash", str(INSTALL_SH), cmd, *rest]) return 2 def _runtime_check(check,
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server yggdrasil/cli.py
high Shell/command execution in server code (yggdrasil/hooks/ygg_session_start.py)MTC-SRC-002
In the server's implementation (`yggdrasil/hooks/ygg_session_start.py:127`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try: top = subprocess.run(["git", "-C", cwd, "rev-parse", "--show-toplevel"],
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server yggdrasil/hooks/ygg_session_start.py
high Shell/command execution in server code (yggdrasil/hooks/ygg_stop.py)MTC-SRC-002
In the server's implementation (`yggdrasil/hooks/ygg_stop.py:26`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try: top = subprocess.run(["git", "-C", cwd, "rev-parse", "--show-toplevel"],
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server yggdrasil/hooks/ygg_stop.py
high Shell/command execution in server code (yggdrasil/service.py)MTC-SRC-002
In the server's implementation (`yggdrasil/service.py:165`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ion"] = True proc = subprocess.Popen(argv, **kwargs) # noqa: S603 try: PIDFILE.write_text(str(proc.pid)
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server yggdrasil/service.py
high Shell/command execution in server code (yggdrasil/ygg_cross_agent_demo.py)MTC-SRC-002
In the server's implementation (`yggdrasil/ygg_cross_agent_demo.py:54`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: + "\n" completed = subprocess.run([sys.executable, str(MCP)], input=stdin, cwd=ROOT, env=env, text=True, capture_ou
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server yggdrasil/ygg_cross_agent_demo.py
high Shell/command execution in server code (yggdrasil/ygg_dense_gate.py)MTC-SRC-002
In the server's implementation (`yggdrasil/ygg_dense_gate.py:64`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: SER_ID) completed = subprocess.run( [ str(YGG), "remember", "--project",
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server yggdrasil/ygg_dense_gate.py
high Shell/command execution in server code (yggdrasil/ygg_governance_gate.py)MTC-SRC-002
In the server's implementation (`yggdrasil/ygg_governance_gate.py:48`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rocess[str]: return subprocess.run(args, cwd=ROOT, env=env, text=True, capture_output=True, timeout=90, check=False)
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server yggdrasil/ygg_governance_gate.py
high Shell/command execution in server code (yggdrasil/ygg_import_claude_memory.py)MTC-SRC-002
In the server's implementation (`yggdrasil/ygg_import_claude_memory.py:76`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rocess[str]: return subprocess.run([sys.executable, str(YGG), *args], cwd=ROOT, env=env, text=True, capture_output=T
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server yggdrasil/ygg_import_claude_memory.py
high Shell/command execution in server code (yggdrasil/ygg_providers.py)MTC-SRC-002
In the server's implementation (`yggdrasil/ygg_providers.py:205`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: bprocess return subprocess.run([lms, "unload", model], capture_output=True, timeou
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server yggdrasil/ygg_providers.py
high Shell/command execution in server code (yggdrasil/ygg_quality_gate.py)MTC-SRC-002
In the server's implementation (`yggdrasil/ygg_quality_gate.py:36`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: EMO_USER_ID) return subprocess.run(args, cwd=ROOT, env=env, text=True, capture_output=True, check=check) def healt
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server yggdrasil/ygg_quality_gate.py
low Hardcoded JSON Web Token in test/example/packaging (tests/test_ygg_memory_server.py)MTC-SRC-008
A hardcoded JSON Web Token (an embedded JSON Web Token (often an example or expired token)) appears in `tests/test_ygg_memory_server.py:250`. Verify whether this is a real credential; if so, remove and rotate it.
Evidence: JSON Web Token: eyJh…(redacted)
Fix: Remove the secret, rotate it, and load credentials from the environment or a secret store.
Location: server tests/test_ygg_memory_server.py
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Versions 2
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.15.0 latest |
A 92/100 | 11 | 1.13.0 | 2026-08-25 |
v0.13.2 |
A 92/100 | 11 | 1.12.1 | 2026-07-27 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan yggdrasil-memory --online --registry pypiOther implementations of Yggdrasil Memory 1
Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →
More in Databases
Security scan results for the A5sql MCP server.
Expose AgentsKit tools as an MCP server — use them from Claude Desktop, Cursor, Windsurf, or any MCP host.
MCP server for Aiven cloud data platform - manage PostgreSQL, Kafka, and other services
MCP Server for All-Inkl.com hosting via KAS API
Structured aquarium, marine, terrarium and paludarium data for AI agents.
MCP server that gives your AI agent real vehicle data — specs, representative images, federal recalls, owner complaints, service bulletins, defect investigations, and OBD-II DTC reference — from the CarVector API.