truth-anchor-agent
An MCP server that provides fact-checking capabilities and truth anchoring for AI agents using verified data sources.
README
⚓️ Truth Anchor Agent
Truth Anchor Agent is an MCP (Model Context Protocol) server that provides a verifiable grounding layer for AI agents. It verifies URL status and content accessibility, gated by on-chain USDC micro-payments on Base via the x402 protocol.
The Problem: AI agents often reference dead links or hallucinate sources. The Solution: A trustless, pay-per-verification service that requires agents to commit a micro-payment before confirming a source's validity.
🛠 Model Context Protocol (MCP) Integration
This server exposes a verify tool that any MCP-compliant LLM (Claude Desktop, ChatGPT, IDEs) can use autonomously.
Registration in Claude Desktop
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"truth-anchor": {
"command": "npx",
"args": ["-y", "truth-anchor-agent"],
"env": {
"MY_WALLET_ADDRESS": "0x367B9193D4F9cb4877Ca58E6F3ce944d761d8009"
}
}
}
}
💳 The x402 Flow
The agent implements the HTTP 402 Payment Required standard, enabling seamless AI-to-AI economic transactions.
- Request: Agent calls
/verifywith a URL. - Challenge: Server returns
402 Payment Requiredwith payment instructions. - Payment: Agent executes a 0.005 USDC transfer on Base Mainnet.
- Verification: Agent retries with the transaction hash in the
X-402-Payment-Tokenheader. - Truth: Server validates the hash on-chain (preventing replays) and returns the status.
⚡️ API Reference
POST /verify
Verifies a URL's status. Requires a valid Base transaction hash.
Headers:
| Header | Description |
|---|---|
X-402-Payment-Token |
The transaction hash of the 0.005 USDC payment on Base |
Request Body:
{ "url": "https://base.org" }
Success Response (200 OK):
{
"url": "https://base.org",
"is_live": true,
"status_code": 200,
"payment_verified": true
}
🏗 Tech Stack
- FastAPI — High-performance Python API framework.
- Web3.py — Real-time on-chain verification (Base RPC).
- SQLite — Replay attack prevention and transaction indexing.
- Fly.io — Global edge deployment.
- Base — L2 Ethereum for fast, low-cost USDC payments.
🛠 Local Development
# 1. Clone and Install
git clone https://github.com/cristiano-c1/truth-anchor-agent
cd truth-anchor-agent
pip install -r requirements.txt
# 2. Configure
echo "MY_WALLET_ADDRESS=0x367B9193D4F9cb4877Ca58E6F3ce944d761d8009" > .env
# 3. Run
uvicorn main:app --reload
📜 License
Distributed under the MIT License. See LICENSE for more information.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.