Bundles four live agent services into MCP tools: real-time weather via OpenMeteo, GitHub repo search, currency conversion through open.er-api.com, and Solana wallet trust scoring against mainnet-beta RPC. The interesting bit is the architecture pattern. Instead of wrapping APIs directly, each tool hits a backend agent service that can be swapped or upgraded without touching the MCP interface. The trust scoring tool reads on-chain signals to vet unknown wallets before you delegate tasks or payments. Runs via npx or as a public HTTP endpoint with streamable transport. No API keys required for any of the four tools. Self-host with Node or Docker if you want to run your own instance.
A Model Context Protocol server that bundles 4 real-world agent capabilities as MCP tools. Each tool calls a live backend agent service — making agent-to-agent collaboration invisible to the LLM using the tools.
| Tool | Description | Backend |
|---|---|---|
agent_weather | Real-time weather + 3-day forecast for any city | OpenMeteo (free, no API key) |
agent_code_search | GitHub repository search by topic or description | GitHub Search API |
agent_currency | Currency conversion & exchange rates | open.er-api.com (free, no API key) |
agent_trust_score | Solana wallet trust scoring (on-chain signals) | Solana mainnet-beta RPC |
Most MCP tools are wrappers around single APIs. This server demonstrates a different pattern: agents as tools. Each tool is backed by a running agent service that can be upgraded independently without changing the MCP interface.
The trust scoring tool is particularly useful before delegating tasks or micropayments to unknown agent wallets — a key primitive in the emerging agent economy.
Add to your claude_desktop_config.json or MCP config:
{
"mcpServers": {
"openclaw-agent-tools": {
"command": "npx",
"args": ["-y", "openclaw-agent-tools"]
}
}
}
The server also runs as a public HTTP endpoint supporting the MCP Streamable HTTP transport:
POST http://178.104.131.84:8087/mcp
Accept: application/json, text/event-stream
Content-Type: application/json
{
"jsonrpc": "2.0",
"method": "tools/call",
"id": "1",
"params": {
"name": "agent_weather",
"arguments": {"query": "Amsterdam"}
}
}
{
"jsonrpc": "2.0",
"method": "tools/call",
"id": "2",
"params": {
"name": "agent_trust_score",
"arguments": {"wallet_address": "9WzDXwBbmkg8ZTbNMqUxvQRAyrZzDsGYdLVL9zYtAWWM"}
}
}
git clone https://github.com/baronsengir007/openclaw-agent-tools
cd openclaw-agent-tools
npm install
node server.js --http # HTTP mode on port 3000
# or
node server.js --stdio # stdio mode for Claude Desktop
docker build -t openclaw-agent-tools .
docker run -d -p 3000:3000 openclaw-agent-tools
MIT — OpenClaw Research
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent