ToolTrust
C25/100
Smithery

rationalbloks-rationalbloks

mcpsmithery

@Smithery

By providing a simple JSON configuration file to describe your data structure, the system generates for you: โ€ข ๐—™๐—ฎ๐˜€๐˜๐—”๐—ฃ๐—œ ๐—•๐—ฎ๐—ฐ๐—ธ๐—ฒ๐—ป๐—ฑ: A full CRUD API implementation based on your JSON schema. โ€ข ๐—ฃ๐—ผ๐˜€๐˜๐—ด๐—ฟ๐—ฒ๐—ฆ๐—ค๐—Ÿ ๐——๐—ฎ๐˜๐—ฎ๐—ฏ๐—ฎ๐˜€๐—ฒ: Production-ready, with an Alembic migration system built-in (fully trackable by Git). โ€ข ๐—ฆ๐—ฒ๐—ฐ๐˜‚๐—ฟ๐—ถ๐˜๐˜†: Production-ready JWT authentication built-in. โ€ข ๐—–๐—น๐—ผ๐˜‚๐—ฑ ๐—œ๐—ป๐—ณ๐—ฟ๐—ฎ๐˜€๐˜๐—ฟ๐˜‚๐—ฐ๐˜๐˜‚๐—ฟ๐—ฒ: Fully managed and production-ready with built-in staging and production environments.

By Smithery | 28 findings | Scanned 4/17/2026 | tooltrust-scanner/v0.3.8

2 High6 Medium2 Low18 Info

Risk Summary

Needs Approval

Dep Visibility plus Excessive Permissions raises enough risk that this tool should not be auto-trusted.

Potential impact: This finding indicates the tool should be reviewed before it is trusted.

Recommended action: Keep this tool behind manual approval and avoid unattended runs until the risky capabilities are narrowed or removed.

Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.

Security Findings (28)

  • HighAS-002

    โš ๏ธExcessive Permissions ร—2

    tool declares network permission

    list_projects

    tool declares exec permission

    create_project

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

  • MediumAS-002

    โš ๏ธExcessive Permissions ร—6

    tool declares fs permission

    create_projectupdate_schemadelete_project

    tool declares db permission

    update_schemadelete_project

    tool declares env permission

    rollback_project

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

  • LowAS-011

    โ„น๏ธMissing Rate-Limit / Timeout ร—2

    tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration

    list_projectscreate_project

    Fix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.

  • InfoAS-014

    โ„น๏ธDependency Inventory Unavailable ร—18

    Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.

    list_projectsget_projectget_schemaget_user_infoget_job_statusget_project_infoget_version_historyget_template_schemasget_subscription_statusget_project_usageget_schema_at_versioncreate_projectupdate_schemadeploy_stagingdeploy_productiondelete_projectrollback_projectrename_project

    Fix: Review and remediate the identified issue.

Scan this tool yourself

Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.

Install once, then scan any MCP server:

$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash
$ tooltrust-scanner scan --server "npx -y rationalbloks-rationalbloks"

Adjust the package name if your npm registry name differs from the tool ID. View source

Add badge to your README

Copy this Markdown to show your ToolTrust grade on GitHub.

[![ToolTrust Grade C](https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-directory/main/docs/badges/grade-c.svg)](https://github.com/AgentSafe-AI/tooltrust-directory)