hypermnesia-mcp-viz@3.3.0
VERIFIED· not startedPublisher claims: "Visualization and graph MCP server for Cortex — neural graph, methodology map, workflow graph, and trace UI extracted from the Cortex memory engine" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
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
DATABASE_URLConfiguration, not credentials: CI_OS, CLAUDE_PLUGIN_DATA, CLAUDE_PLUGIN_ROOT, GITHUB_REF_NAME, GITHUB_REF_TYPE, PYTHONPATH- Where it talks to
- no vendor host named in the codeAlso esm.sh — 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
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names esm.sh as well as its own vendor. The guard injects DATABASE_URL only into requests to the host you bind (and its subdomains) and refuses the rest.
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 (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-11 and scored it 80/100 (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 · 2 scenarios · 0 deviationsStatic findings
in, so a mid-install kill never leaves a shadowing husk. Retries withFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Load order is load-bearing (ui/shared/README.md): surface-toggle.js stamps data-surface="paper" before first paint, then ds.css resolves the token contract for Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.…ncy rule and the file count per layer, the structural invariant that no `import mcp_server.*` is permitted anywhere in cortex_viz/, the read contract per data source, the browser directory map, the four trust boundaries in order of exposur…Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Brain is a separate 3D WebGL surface (its own page), not an in-page tab — data-nav navigates instead of swapping the active view.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.<summary><strong>More options</strong> (Clone, manual run)</summary> **Clone + run from source:** ```bash git clone https://github.com/cdeust/cortex-viz.git && Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…east privilege: Cortex's memory tables are never written and the ban on `import mcp_server.*` keeps the separation structural; workflow tokens are permissions: read-all by default and widened per job only where a job must write. Fail-safe …Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.… run -m pytest && uv run --no-sync coverage xml -o coverage-py.xml && npm ci && npx vitest run --coverage --coverage.reporter=cobertura && python3 scripts/merge_cobertura…Fix: Pin versions and sources; vendor anything fetched at install time.proc = subprocess.run(base, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.done = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.event, output = Path(tmp) / "event.json", Path(tmp) / "output"Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.console.log(`[equivalence] PASS — ${results[0].file} and ${results[1].file} produce byte-identical output buffers.`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.done = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
No advisories in OSV for hypermnesia-mcp-viz@3.3.0 as of 3d ago. This is the package itself, not its dependencies.