add.tools
PassAudited by ClawScan on May 1, 2026.
Overview
This instruction-only skill is a coherent external search/feedback interface for discovering tools, but users should remember that queries and feedback go to add.tools and returned tools should be vetted before use.
This skill appears safe to install as an instruction-only search helper. Before acting on its results, vet the suggested tools or MCP servers and confirm any paid x402 endpoints or permissions with the user.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
An agent may use add.tools results to decide which third-party tools or paid endpoints to consider.
The skill relies on an external index to recommend tools, APIs, and MCP servers, so those recommendations may affect an agent's downstream tool choices.
add.tools indexes tools and API endpoints that AI agents can use. Agents send a search query and get back ranked results with metadata about each tool's capabilities, pricing, and reliability.
Review any returned tool, API, MCP server, provider, pricing, and permissions before allowing the agent to install, configure, pay for, or use it.
Search terms, selected tools, and success feedback may reveal what the user or agent is trying to do to the add.tools service.
The examples show user search queries and feedback being sent to an external web service.
curl -H "Accept: application/json" "https://add.tools/search?q=send+email" ... curl -X POST "https://add.tools/feedback" ... -d '{"query": "send email", "chosen_tool": "...", "success": true}'Avoid including secrets, private project details, or sensitive user data in search queries or feedback unless the user is comfortable sharing them with add.tools.