add.tools

Search engine for AI agents to discover free and paid tools, APIs, and MCP servers

Security Scan

Instruction-only skill that simply directs the agent to query the add.tools web API for tool discovery; it requests no local permissions or credentials and its runtime instructions are consistent with the stated purpose.

Purpose & Capability

Name/description match the instructions: SKILL.md directs agents to use add.tools search and feedback endpoints to discover APIs, tools, and MCP servers. No unrelated binaries, env vars, or config paths are required.

Instruction Scope

Instructions are narrow and only call add.tools HTTP endpoints (GET /search and POST /feedback). Note: the feedback example posts query text and chosen_tool/success flags to the remote service — this is expected functionality but can transmit user queries or selection metadata to an external site.

Install Mechanism

No install spec and no code files; instruction-only skills have minimal on-disk footprint.

Credentials

Skill declares no environment variables, credentials, or config paths. Runtime instructions do not request local secrets or unrelated credentials.

Persistence & Privilege

always is false; the skill is not automatically forced into every agent run. It can be invoked by the agent (normal for skills) but does not request elevated persistence or modify other skills.

Assessment

This skill is coherent and lightweight: it makes HTTP requests to add.tools and can POST feedback containing query text and selection metadata. Before installing, verify you trust the add.tools domain/GitHub repo and its privacy/usage policies, avoid sending secrets or sensitive data in queries or feedback, and confirm how x402 micropayments are handled if your agent might follow payment links or invoke paid endpoints. Because the skill calls an external service, be mindful that data you send may be logged or used for analytics.

A search engine for AI agents to discover tools, APIs, and MCP servers — both free and paid (via x402 micropayments).

What it does

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.

The index includes both free tools and paid x402-enabled endpoints, so agents can find the right tool regardless of pricing model.

Usage

Search for tools

# JSON response for agents
curl -H "Accept: application/json" "https://add.tools/search?q=send+email"

# With explicit format param
curl "https://add.tools/search?q=weather+forecast&format=json"

Report feedback

curl -X POST "https://add.tools/feedback" \
  -H "Content-Type: application/json" \
  -d '{"query": "send email", "chosen_tool": "...", "success": true}'

Helps improve search quality over time.

Content negotiation

Every URL on add.tools serves both humans and agents from the same URL. Set Accept: application/json or append ?format=json for machine-readable responses. Default is HTML with clean server-rendered content that LLMs can also parse directly.

Links

• Website: https://add.tools
• GitHub: https://github.com/add-tools