MCP Risk

Scan report

ai.toolprint/hypertool-mcp

This page reports an automated security scan of ai.toolprint/hypertool-mcp (npm), scanned 2026-07-28. It rates trust (provenance, transport, known vulnerabilities, instruction integrity) as grade C and capability risk (what the tools can do) separately at critical. It does not certify the server is safe to connect; it reports what could be checked from outside.

npm, scanned 2026-07-28, tool surface via package-source

C 79/100 Capability risk: Critical permalink

The grade rates trust: provenance, transport, known vulnerabilities and instruction integrity. Capability risk rates what the tools can do and is reported, not penalised – a server built to run shell commands is doing its job (Policy §2.4).

Automated checks

StatusCheckPolicyResult
PASS Listed on the official MCP registry §1.1
Listed on registry.modelcontextprotocol.io as ai.toolprint/hypertool-mcp. 1 finding
  • Registry entry: ai.toolprint/hypertool-mcp ↗
PASS Source repository is public and maintained §1.2
Active repository with a license. 5 findings
  • Repository ↗
  • Last push: 279 days ago
  • Stars: 155
  • License: NOASSERTION
  • Security policy (SECURITY.md): absent
WARN Published package is consistent and attested §1.3
Minor integrity gaps: no npm provenance attestation. 6 findings
  • Package: @toolprint/hypertool-mcp@0.0.45 ↗
  • Ecosystem: npm
  • Age: 375 days
  • Weekly downloads: 598
  • Repo field matches source repo: true
  • Build-provenance attestation: absent
PASS Tool surface is inspectable and proportionate §2.1–§2.4
Package source scanned. Capabilities detected: filesystem, process-execution, credential-access, network-egress. Reported as capability risk (§2.4); whether each is essential to the server's stated purpose is §2.3 and remains a manual judgement. 25 findings
  • filesystem (filesystem write/delete): dist/commands/persona/add.js
  • filesystem (fs module import): dist/commands/persona/add.js
  • filesystem (fs module import): dist/config/appConfig.js
  • filesystem (fs module import): dist/persona/cache.js
  • filesystem (filesystem write/delete): dist/extensions/discovery.js
  • filesystem (fs module import): dist/extensions/discovery.js
  • filesystem (fs module import): dist/commands/steps/exampleConfigs.js
  • filesystem (fs module import): dist/config/extensionConfig.js
  • filesystem (fs module import): dist/commands/extensions/install.js
  • filesystem (filesystem write/delete): dist/test-utils/lightweight.js
  • filesystem (fs module import): dist/dxt/loader.js
  • filesystem (fs module import): dist/dxt/manifest.js
  • filesystem (fs module import): dist/config/mcpConfigFileLoader.js
  • process-execution (child process execution): dist/utils/output.js
  • process-execution (child process module import): dist/utils/output.js
  • filesystem (fs module import): dist/persona/scanner.js
  • filesystem (fs module import): dist/server.js
  • credential-access (credential/env access): dist/server.js
  • process-execution (child process execution): dist/config-manager/cli/interactive/servers-menu.js
  • process-execution (child process module import): dist/config-manager/cli/interactive/servers-menu.js
  • filesystem (fs module import): dist/server/tools/config-tools/persona/validate-persona.js
  • filesystem (fs module import): dist/extensions/validation.js
  • filesystem (fs module import): dist/persona/validator.js
  • network-egress (http module import): dist/server/http-server.d.ts
  • Detected capabilities: filesystem, process-execution, credential-access, network-egress
INFO Transport & authentication §3

Local (stdio) server: runs with host-process privileges by design. Transport checks apply to remote servers; scrutiny shifts to §1/§2.
PASS No known vulnerabilities (OSV.dev) §4.1

No advisories on record for @toolprint/hypertool-mcp @0.0.45 (npm).
WARN Server-supplied instructions free of poisoning indicators §5.1–§5.4
2 suspicious indicator(s) found in server-supplied instructions, tool descriptions, or schemas. 2 findings
  • dist/config/flagRegistry.js (source literal): cross-tool shadowing: instead of showing all tool
  • dist/config/flagRegistry.d.ts (source literal): cross-tool shadowing: instead of showing all tool

Verify manually - the scoring model can’t judge these for you

  • §2.3 - Is the tool surface no broader than the server’s stated purpose requires?
  • §3.4 - For stdio servers: which environment credentials does it read, and are they scoped rather than org-wide tokens?
  • §6.1 - Cross this server’s capabilities with your already-connected servers: any read-capability × send-capability pairs need explicit sign-off.
  • §6.2 - Run the connecting agent with sandboxing and egress controls sized to the combined tool surface, not just this server’s.

Methodology: MCP Server Security Policy. Checks and scoring weights are open source. Unfamiliar term? See the glossary.