meshcore-marketplace
Discover and call paid AI agents from the MeshCore marketplace. Find specialized agents for weather, data analysis, summarization, and more — with automatic billing.
Packaged view
This page reorganizes the original catalog entry around fit, installability, and workflow context first. The original raw source lives below.
Install command
npx @skill-hub/cli install openclaw-skills-meshcore-marketplace
Repository
Skill path: skills/anegash/meshcore-marketplace
Discover and call paid AI agents from the MeshCore marketplace. Find specialized agents for weather, data analysis, summarization, and more — with automatic billing.
Open repositoryBest for
Primary workflow: Analyze Data & AI.
Technical facets: Full Stack, Data / AI.
Target audience: everyone.
License: Unknown.
Original source
Catalog source: SkillHub Club.
Repository owner: openclaw.
This is still a mirrored public skill entry. Review the repository before installing into production workflows.
What it helps with
- Install meshcore-marketplace into Claude Code, Codex CLI, Gemini CLI, or OpenCode workflows
- Review https://github.com/openclaw/skills before adding meshcore-marketplace to shared team environments
- Use meshcore-marketplace for development workflows
Works across
Favorites: 0.
Sub-skills: 0.
Aggregator: No.
Original source / Raw SKILL.md
---
name: meshcore-marketplace
description: Discover and call paid AI agents from the MeshCore marketplace. Find specialized agents for weather, data analysis, summarization, and more — with automatic billing.
version: 1.0.0
user-invocable: true
metadata:
openclaw:
requires:
env:
- MESHCORE_API_TOKEN
bins:
- curl
- jq
primaryEnv: MESHCORE_API_TOKEN
emoji: "globe_with_meridians"
homepage: https://meshcore.ai
---
# MeshCore Marketplace Skill
You have access to the MeshCore AI agent marketplace — a platform where developers publish AI agents and others can discover and pay to use them.
## API Base URL
All API calls go to: `https://api.meshcore.ai`
## Available Actions
### 1. Search for agents
Use semantic search to find agents by what they do:
```bash
curl -s "https://api.meshcore.ai/public/agents/search?query=SEARCH_TERM&limit=5" | jq '.[] | {name, description, pricingType, pricePerCall, id}'
```
Replace `SEARCH_TERM` with what the user is looking for (e.g., "weather", "summarize text", "currency exchange").
### 2. List all agents
Browse all available agents:
```bash
curl -s "https://api.meshcore.ai/public/agents" | jq '.[] | {name, description, pricingType, pricePerCall, id}'
```
### 3. Get agent details
Get full information about a specific agent:
```bash
curl -s "https://api.meshcore.ai/public/AGENT_ID" | jq
```
### 4. Call an agent
Call an agent through the MeshCore gateway:
**For FREE agents (no auth needed):**
```bash
curl -s -X POST "https://api.meshcore.ai/gateway/call/AGENT_ID" \
-H "Content-Type: application/json" \
-d 'JSON_PAYLOAD'
```
**For PAID agents (auth required):**
```bash
curl -s -X POST "https://api.meshcore.ai/gateway/call/AGENT_ID" \
-H "Authorization: Bearer $MESHCORE_API_TOKEN" \
-H "Content-Type: application/json" \
-d 'JSON_PAYLOAD'
```
### 5. Check wallet balance
```bash
curl -s "https://api.meshcore.ai/wallet/balance" \
-H "Authorization: Bearer $MESHCORE_API_TOKEN" | jq
```
## Important Rules
1. **Always show pricing before calling a paid agent.** Tell the user: "This agent costs $X per call. Shall I proceed?"
2. **Wait for user confirmation before calling any paid agent.** Never call a paid agent without explicit approval.
3. **Free agents can be called without asking.** If `pricingType` is `FREE`, just call it.
4. **Show results clearly.** Format the agent's response in a readable way.
5. **If search returns no results**, suggest the user try different terms or browse all agents.
## Example Workflows
**User: "Find me a weather agent"**
1. Search: `curl -s "https://api.meshcore.ai/public/agents/search?query=weather&limit=3"`
2. Show results with name, description, and pricing
3. Ask: "Would you like me to call the Weather Agent?"
4. If yes and it's free: call it directly
5. Show the weather data
**User: "Summarize this text: [long text]"**
1. Search: `curl -s "https://api.meshcore.ai/public/agents/search?query=text+summarizer&limit=3"`
2. Show results: "I found a Text Summarizer agent. It costs $0.01 per call. Want me to use it?"
3. Wait for confirmation
4. Call with auth: `curl -s -X POST ... -H "Authorization: Bearer $MESHCORE_API_TOKEN"`
5. Show the summary
---
## Skill Companion Files
> Additional files collected from the skill directory layout.
### README.md
```markdown
# MeshCore + OpenClaw: Getting Started
MeshCore is a marketplace where AI agents are bought and sold. Developers publish specialized agents (weather, summarization, scraping), set pricing, and earn money when others use them. Think of it as npm for AI agents, but with built-in billing.
This guide gets you from zero to calling your first marketplace agent in under 5 minutes.
## 1. Install the MeshCore Skill
```bash
clawhub install meshcore-marketplace
```
## 2. Set Up Your API Token
1. Sign up at [meshcore.ai](https://meshcore.ai)
2. Go to Dashboard → API Keys
3. Create a new API key
4. Add to your environment:
```bash
export MESHCORE_API_TOKEN="your-token-here"
```
> **Note:** Free agents work without a token. You only need a token for paid agents and wallet features.
## 3. Try It
Open your OpenClaw agent and try these commands:
- **"Search the marketplace for weather agents"** — Discovers available weather agents
- **"Call the weather agent for Tokyo"** — Gets live weather data
- **"What agents are available on MeshCore?"** — Lists the full marketplace
- **"Find an agent that can summarize text"** — Semantic search
- **"Check my MeshCore wallet balance"** — See your credits
## 4. For Skill Builders: Monetize Your Skills
Already built a useful agent or skill? Turn it into a paid API on MeshCore:
```bash
# Install the MeshCore CLI
npm install -g @meshcore/cli
# Log in
mesh auth login
# Register your agent
mesh agent create \
--name "My Agent" \
--description "What it does" \
--endpoint "https://my-agent.example.com/run" \
--pricing-type PER_CALL \
--price-per-call 0.01
# That's it. You earn $0.009 every time someone calls your agent.
```
**Pricing is up to you.** MeshCore takes a 10% platform fee. You keep 90%.
## 5. Alternative: MCP Server
If you prefer MCP tools over the skill interface:
```bash
npx @meshcore/mcp-server
```
Add to your `openclaw.json`:
```json
{
"mcpServers": {
"meshcore": {
"command": "npx",
"args": ["@meshcore/mcp-server"],
"env": {
"MESHCORE_API_TOKEN": "your-token-here"
}
}
}
}
```
## Support
- Website: [meshcore.ai](https://meshcore.ai)
- Docs: [meshcore.ai/docs](https://meshcore.ai/docs)
- Discord: [discord.gg/8GksNwCAC3](https://discord.gg/8GksNwCAC3)
- Twitter: [@meshcore_ai](https://twitter.com/meshcore_ai)
```
### _meta.json
```json
{
"owner": "anegash",
"slug": "meshcore-marketplace",
"displayName": "MeshCore Marketplace",
"latest": {
"version": "1.0.0",
"publishedAt": 1772298137125,
"commit": "https://github.com/openclaw/skills/commit/d00f1ae4cd65d572639e4ba102f33f21fb7c2ced"
},
"history": []
}
```