ClawHub

add.tools

v0.1.0

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

⭐ 0· 236·0 current·0 all-time
by@simmmel·duplicate of @simmmel/add-tools

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for simmmel/addtools.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "add.tools" (simmmel/addtools) from ClawHub.
Skill page: https://clawhub.ai/simmmel/addtools
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install addtools

ClawHub CLI

Package manager switcher

npx clawhub@latest install addtools
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name/description (a search engine for agent-discoverable tools/APIs) align with the SKILL.md examples, which are simple curl calls against add.tools endpoints. There are no unrelated env vars, binaries, or config paths requested.
✓
Instruction Scope
SKILL.md only instructs the agent to issue HTTP GET/POST requests to add.tools (search and feedback endpoints) and to use content negotiation for JSON; it does not instruct reading local files, accessing unrelated environment variables, or transmitting data to other endpoints.
✓
Install Mechanism
There is no install spec and no code files. Because this is instruction-only the skill does not write to disk or pull remote packages.
✓
Credentials
The skill declares no environment variables, no credentials, and no config paths — appropriate for a read/search-only integration with a public web API.
✓
Persistence & Privilege
The skill uses platform defaults (not always:true) and does not request elevated or persistent system privileges. Autonomous invocation is allowed by default but not combined with other red flags.
Assessment
This skill is low-risk in terms of local access because it only documents how to call add.tools web endpoints and asks for no secrets or installs. However, it will cause your agent to send queries to an external service (https://add.tools). Do not include sensitive or secret information in search queries or feedback posts. If you want extra caution, verify the add.tools website and GitHub repo listed in SKILL.md before installing, and consider restricting autonomous agent access if you prefer manual approval of outbound network calls.

Like a lobster shell, security has layers — review code before you run it.

latestvk971dw9rvnzh8wx98cexmt0db1834f0y
236downloads
0stars
1versions
Updated 1mo ago
v0.1.0
MIT-0
@simmmel
latest
Download

add.tools

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

Comments

Loading comments...