ToolTrust
A8/100
Smithery

evan-follis-u0ll-preflight

mcpsmithery

@Smithery

Check if your MCP server is ready to publish on the MCP Registry, Smithery, or npm. Preflight validates your server's actual artifacts — `server.json`, `package.json`, `smithery.yaml` — against the documented requirements of each directory. Every finding includes the evidence found, the directory rule it maps to, and the exact fix. ## What it checks - **MCP Registry** — server.json schema, name format, packages/remotes config, transport type, npm mcpName ownership, PyPI README marker - **Smithery** — Streamable HTTP transport, public HTTPS endpoint, server-card presence - **npm** — name, version, entry point (bin/main) Each finding is tagged with evidence level (`verified_from_artifact` or `inferred`), rule type (`hard_requirement`, `directory_convention`, or `heuristic`), and a source URL linking to the directory documentation. ## How to use Call `check_publish_readiness` with raw artifact contents (all fields optional): - `manifest` — your server.json - `package_json` — your package.json - `smithery_yaml` — your smithery.yaml - `pyproject_toml` — your pyproject.toml - `readme` — your README - `target_directories` — optional array of `mcp_registry`, `smithery`, `npm` Returns a verdict (`checks_pass`, `fixable`, or `not_ready`), per-directory readiness, and evidence-backed findings with concrete fixes. Zero dependencies. No LLM calls. No authentication. No PII collection.

By Smithery | 2 findings | Scanned 5/31/2026 | tooltrust-scanner/v0.3.13

1 Medium1 Info

Risk Summary

Safe With Normal Controls

Excessive Permissions is the main signal, but overall risk remains within an acceptable range.

Potential impact: The agent may gain overly broad access to files, network, databases, or execution capabilities.

Recommended action: No high-risk findings were detected in this scan, but you should still apply least-privilege defaults and rescan after changes.

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

Security Findings (2)

  • MediumAS-002

    ⚠️Excessive Permissions

    check_publish_readiness:tool declares fs permission

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

  • InfoAS-014

    ℹ️Dependency Inventory Unavailable

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

    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 evan-follis-u0ll-preflight"

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 A](https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-directory/main/docs/badges/grade-a.svg)](https://github.com/AgentSafe-AI/tooltrust-directory)