florian-weavely
mcpsmitheryWeavely is an AI-native form builder. This MCP server exposes 13 tools that cover the entire form-building lifecycle: create forms, add and update 25+ element types (text, rating, matrix, file upload, signature, and more), configure conditional logic, set themes, manage multi-step pages, and publish — all from natural language. The AI builds incrementally while a live preview URL updates in real time. When you're done, a single publish_form call returns an editor link to claim full ownership on the Weavely platform. No authentication required. After publishing, connect your form to Google Sheets, Zapier, n8n, HubSpot, Notion, and more.
By Smithery | 32 findings | Scanned 5/21/2026 | tooltrust-scanner/v0.3.12
Risk Summary
Needs ApprovalExcessive Permissions plus Dep Visibility raises enough risk that this tool should not be auto-trusted.
Potential impact: The agent may gain overly broad access to files, network, databases, or execution capabilities.
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 (32)
tool declares network permission
create_formadd_elementset_logicpublish_formtool declares exec permission
add_elementupdate_elementFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
tool declares fs permission
create_formadd_elementupdate_elementremove_elementremove_pageFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
set_logic:tool name "set_logic" implies local write operation but only remote/network-class permissions were detected
Fix: Ensure tool names, descriptions, and permission declarations are internally consistent. Use explicit naming conventions that fully reflect actual capabilities.
tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration
create_formadd_elementupdate_elementset_logicpublish_formFix: 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.
input schema exposes 26 properties (threshold: 10)
add_elementtool declares http permission
set_logicFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.
create_formget_form_summaryadd_elementupdate_elementremove_elementreorder_elementsadd_pageremove_pagereorder_pagesset_themeset_settingsset_logicpublish_formFix: 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 florian-weavely"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.
[](https://github.com/AgentSafe-AI/tooltrust-directory)