Hypermnesia MCP Server
hypermnesia-mcp
PyPI
v4.19.1
Published by cdeust — 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.
Scientifically-grounded memory system based on computational neuroscience research
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 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 1 = 99. 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 |
|---|---|
| −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 12
medium Dynamic module load from a non-literal (mcp_server/doctor_mcp.py)MTC-SRC-005
In the server's implementation (`mcp_server/doctor_mcp.py:577`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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: __import__(mod) except ImportError as exc: missing.append(mod) e
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 mcp_server/doctor_mcp.py
low Shell/command execution in packaging/dev tooling (benchmarks/_repro.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`benchmarks/_repro.py:47`): 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: result = subprocess.run( ["git", "rev-parse", "HEAD"], capture_output=True,
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 benchmarks/_repro.py
low Shell/command execution in packaging/dev tooling (benchmarks/lib/ablation_runner.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`benchmarks/lib/ablation_runner.py:175`): 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: out = subprocess.check_output( ["git", "rev-parse", "HEAD"], cwd=_ROOT, stderr=subprocess.
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 benchmarks/lib/ablation_runner.py
low Shell/command execution in packaging/dev tooling (benchmarks/lib/blend_weight_sweep.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`benchmarks/lib/blend_weight_sweep.py:212`): 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: .monotonic() proc = subprocess.run( cmd, env=env, cwd=str(REPO_ROOT), capture_output
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 benchmarks/lib/blend_weight_sweep.py
low Shell/command execution in packaging/dev tooling (benchmarks/lib/cross_benchmark_runner.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`benchmarks/lib/cross_benchmark_runner.py:89`): 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: time.time() proc = subprocess.run( [sys.executable, "-m", DRIVER_MODULE, benchmark, data_path, str(limit)],
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 benchmarks/lib/cross_benchmark_runner.py
low Shell/command execution in packaging/dev tooling (benchmarks/lib/db_snapshot.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`benchmarks/lib/db_snapshot.py:282`): 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: ath), db_url] res = subprocess.run(cmd, capture_output=True, text=True) if res.returncode != 0: raise Ru
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 benchmarks/lib/db_snapshot.py
low Shell/command execution in packaging/dev tooling (benchmarks/lib/decay_sweep_runner.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`benchmarks/lib/decay_sweep_runner.py:218`): 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: sha = subprocess.run( ["git", "rev-parse", "HEAD"], cwd=REPO_ROOT,
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 benchmarks/lib/decay_sweep_runner.py
low Shell/command execution in packaging/dev tooling (benchmarks/lib/disk_space_snapshot.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`benchmarks/lib/disk_space_snapshot.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: try: out = subprocess.run( ["docker", "info", "--format", "{{.DockerRootDir}}"], ca
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 benchmarks/lib/disk_space_snapshot.py
low Shell/command execution in packaging/dev tooling (benchmarks/lib/machine_load_snapshot.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`benchmarks/lib/machine_load_snapshot.py:37`): 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: return subprocess.run( cmd, capture_output=True, text=True, timeout=10, check=False, env=en
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 benchmarks/lib/machine_load_snapshot.py
low Shell/command execution in packaging/dev tooling (benchmarks/lib/run_e1_v3_lme.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`benchmarks/lib/run_e1_v3_lme.py:60`): 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: sha() -> str: out = subprocess.run( ["git", "rev-parse", "HEAD"], capture_output=True, text=True, cwd=_ROOT
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 benchmarks/lib/run_e1_v3_lme.py
low Shell/command execution in packaging/dev tooling (benchmarks/lib/run_e1_v3_locomo.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`benchmarks/lib/run_e1_v3_locomo.py:158`): 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: sha() -> str: out = subprocess.run( ["git", "rev-parse", "HEAD"], capture_output=True, text=True, cwd=_ROOT
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 benchmarks/lib/run_e1_v3_locomo.py
low Dynamic module load from a non-literal in packaging/dev tooling (benchmarks/lib/ablation_runner.py)MTC-SRC-005
In a packaging/dev/install script (shipped, but not the server runtime) (`benchmarks/lib/ablation_runner.py:100`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: in specs: mod = __import__(module_path, fromlist=[attr]) original = getattr(mod, attr) saved.app
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 benchmarks/lib/ablation_runner.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 5
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 |
|---|---|---|---|---|
v4.19.1 latest |
A 99/100 | 12 | 1.13.0 | 2026-09-04 |
v4.18.0 |
A 99/100 | 12 | 1.13.0 | 2026-08-27 |
v4.17.2 |
A 99/100 | 12 | 1.13.0 | 2026-08-25 |
v4.16.0 |
A 93/100 | 12 | 1.12.1 | 2026-07-27 |
v4.15.0 |
A 93/100 | 12 | 1.9.0 | 2026-07-23 |
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 hypermnesia-mcp --online --registry pypiMore in Data Science & ML
MCP server for 2s.io — 575+ pay-per-call tools for AI agents — ground-truth data, AI gateway, and agent infra (storage, locks, queues, watchers). x402 USDC on Base/Solana, no API keys, upto usage billing, free trials.
ArXiv preprints + Google Scholar papers, with citation counts in one query.
Add MCP servers to your favorite coding agents with a single command.
Help agents automatically write and test stories for your UI components
Model Context Protocol server for AI-Archive platform - enables AI agents to discover, submit, and review research papers
MCP server for Semantic Scholar research workflows with stdio and Streamable HTTP transports.