financedeveloper-tools

Fluora MCP

fluora-ai

by fluora-ai

Fluora MCP: AI agent marketplace for pay-per-use blockchain services — discover and auto-pay with USDC on Base, with sec

Enables AI agents to discover and pay for monetized services such as PDF processing and DeFi operations using USDC on the Base blockchain. It provides automatic payment processing and secure local wallet management for seamless integration with MCP-compatible clients.

github stars

0

0 commentsdiscussion

Both formats append explainx.ai attribution and the canonical URL for this MCP server listing.

Automatic payment processingSecure local wallet managementBase blockchain integration

best for

  • / AI agents needing paid external services
  • / DeFi application development
  • / Automated document processing workflows
  • / Blockchain-based service marketplaces

capabilities

  • / Discover monetized AI services
  • / Process USDC payments on Base blockchain
  • / Manage local cryptocurrency wallets
  • / Access PDF processing services
  • / Execute DeFi operations
  • / Handle automatic payment transactions

what it does

Enables AI agents to automatically discover, purchase, and use paid services like PDF processing and DeFi operations using USDC payments on the Base blockchain.

about

Fluora MCP is an official MCP server published by fluora-ai that provides AI assistants with tools and capabilities via the Model Context Protocol. Fluora MCP: AI agent marketplace for pay-per-use blockchain services — discover and auto-pay with USDC on Base, with sec It is categorized under finance, developer tools.

how to install

You can install Fluora MCP in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.

license

MIT

Fluora MCP is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.

readme

🌟 Fluora MCP - Monetized AI Agent Services

npm version License: MIT

Transform your AI agents into revenue-generating businesses with seamless blockchain payments.

Fluora MCP enables AI agents to discover, access, and pay for monetized services across the web. Built on blockchain technology with automatic payment processing using USDC on Base network.

🚀 Quick Start

Claude Desktop

Edit your Claude Desktop config file:

  • Mac: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "fluora-registry": {
      "command": "npx",
      "args": ["fluora-mcp"],
      "env": {
        "ENABLE_REQUEST_ELICITATION": "true",
        "ELICITATION_THRESHOLD": "0.01"
      }
    }
  }
}

VS Code (Cline/Continue Extension)

Add to your VS Code MCP settings:

{
  "mcpServers": {
    "fluora-registry": {
      "command": "npx",
      "args": ["fluora-mcp"],
      "env": {
        "ENABLE_REQUEST_ELICITATION": "true",
        "ELICITATION_THRESHOLD": "0.01"
      }
    }
  }
}

Note: Exact location depends on your MCP extension (Cline vs Continue).

🦞 OpenClaw Integration

Install from GitHub for best compatibility:

# Clone and build
git clone https://github.com/fluora-ai/fluora-mcp.git
cd fluora-mcp
npm install
npm run build

# Add to mcporter
mcporter config add fluora --command "node /path/to/fluora-mcp/build/index.js"

# Verify installation

mcporter list fluora
mcporter call fluora.exploreServices category=PDF

OpenClaw users: The MCP server will be automatically available to your agent after adding it to mcporter.

🎬 What Happens After Install

When you first run fluora-mcp:

  1. ✅ A wallet is automatically generated at ~/.fluora/wallets.json
  2. ✅ The MCP server starts and loads the services on the fluora registry
  3. ✅ Your wallet addresses are ready:

   - Testnet (Base Sepolia): Check ~/.fluora/wallets.json    - Mainnet (Base): Check ~/.fluora/wallets.json

⚠️ IMPORTANT: Backup your wallet!

# Backup your wallet file (contains private keys)
cp ~/.fluora/wallets.json ~/fluora-wallet-backup.json

Next Steps:

  1. Fund your wallet (see Funding Your Wallet below)
  2. Restart Claude Desktop/VS Code to load the MCP server
  3. Ask your AI: "What services are available on Fluora?"

💰 Funding Your Wallet

To use paid services, you need USDC in your wallet.

For Production (Mainnet)

  1. Get your mainnet address:    bash    cat ~/.fluora/wallets.json | grep -A 1 MAINNET   

  2. Transfer USDC on Base network    - Recommended: Transfer $1 to start    - Network: Base (not Ethereum mainnet!)    - Token: USDC

💡 Tip: Most services cost $0.001-0.02 per call, so $1 goes a long way!

✨ What You Get

  • 🔍 Service Discovery: Access 76+ monetized services (Browse All)

  - PDF Generation & Conversion   - DeFi Data & Analytics (Solana, Base)   - Web Scraping & Screenshots   - AI Research & Analysis

  • IG/Twitter Scraping   - And more...

  • 💳 Auto Payments: Seamless USDC transactions on Base blockchain

  • 🤖 AI Integration: Works with Claude Desktop, VS Code, OpenClaw, and any MCP client

  • 🔐 Secure Wallets: Auto-generated private keys stored locally

  • 📊 Real-time: Live service status, pricing, and availability

🎯 Core Features

Service Discovery


# Ask your AI agent:

"What PDF services are available via Fluora?"
"Show me DeFi operations under $1 on Fluora"
"Take a screenshot of <website URL> using Fluora "

Automatic Payments

  • USDC on Base: Testnet (Sepolia) and Mainnet support
  • Auto-signing: Transactions signed automatically
  • Instant settlement: Real-time payment verification
  • Secure storage: Private keys never leave your machine

Developer Experience

  • MCP Standard: Full Model Context Protocol compatibility
  • Multiple Transports: STDIO and Server-Sent Events (SSE)
  • Rich Logging: Winston-based logging with configurable levels
  • Error Handling: Graceful degradation and detailed reporting

🛠 Configuration

Environment Variables


MCP_TRANSPORT=stdio              		# stdio | sse
FLUORA_API_URL=https://api.fluora.ai/api # For local development
LOG_LEVEL=INFO                   		# DEBUG | INFO | WARN | ERROR
ENABLE_UNSAFE_DIRECT_ACCESS=false		# CAUTION! Only for development intent
ENABLE_REQUEST_ELICITATION=true			# Usage control over services

Where to put env vars:

  • Claude Desktop: Set in your shell profile (~/.zshrc or ~/.bashrc)
  • VS Code: Use extension settings or .env file
  • OpenClaw: Set in your shell or OpenClaw config

Wallet Setup

Wallets auto-generate at ~/.fluora/wallets.json:

{
  "USDC_BASE_SEPOLIA": {
    "privateKey": "0x...",
    "address": "0x..."
  },
  "USDC_BASE_MAINNET": {
    "privateKey": "0x...",
    "address": "0x..."
  }
}

🔧 Troubleshooting

Server Not Starting

# Check if wallet exists
ls -la ~/.fluora/wallets.json
# Check logs
tail -f ~/.fluora/fluora-mcp.log

"No Funds" Error

  • Check your wallet balance on Base Sepolia/Mainnet
  • Most services cost $0.001-0.02
  • Fund with testnet USDC first to test

Claude Desktop Not Seeing Tools

  1. Verify config: cat ~/Library/Application\ Support/Claude/claude_desktop_config.json
  2. Restart Claude Desktop completely (quit and reopen)
  3. Check Developer Tools (Cmd+Option+I on Mac) for errors

Services Not Loading

# Test server directly
npx fluora-mcp

# Should show: "Request elicitation for MCP services (Human-In-The-Loop for purchase), ENABLED"
# Should list 76+ services

Deprecation Warnings

These warnings are non-critical but will be addressed in future updates.

🔐 Security

  • Local Storage: Private keys stored locally, never transmitted
  • Blockchain Native: All payments verified on-chain
  • X402 Protocol: Standardized payment verification
  • No Data Retention: Service data not stored or logged
  • ⚠️ BACKUP YOUR WALLET: Losing ~/.fluora/wallets.json = losing funds

🤝 Support

📄 License

MIT License - Built with ❤️ for the AI economy


Ready to monetize your AI services?

npm install -g fluora-mcp && fluora-mcp

FAQ

What is the Fluora MCP MCP server?
Fluora MCP is a Model Context Protocol (MCP) server profile on explainx.ai. MCP lets AI hosts (e.g. Claude Desktop, Cursor) call tools and resources through a standard interface; this page summarizes categories, install hints, and community ratings.
How do MCP servers relate to agent skills?
Skills are reusable instruction packages (often SKILL.md); MCP servers expose live capabilities. Teams frequently combine both—skills for workflows, MCP for APIs and data. See explainx.ai/skills and explainx.ai/mcp-servers for parallel directories.
How are reviews shown for Fluora MCP?
This profile displays 41 aggregated ratings (sample rows for discoverability plus signed-in user reviews). Average score is about 4.6 out of 5—verify behavior in your own environment before production use.

Use Cases

Extended AI Capabilities

Add new capabilities to Claude beyond text generation

Example

Access external data sources, execute code, interact with tools and services

Transform Claude from chatbot to action-taking agent

Context Enhancement

Provide Claude with access to relevant context and data

Example

Load project documentation, access knowledge bases, query databases

Get more accurate, context-aware responses

Workflow Automation

Automate multi-step workflows combining AI and external tools

Example

Research → Summarize → Create document → Send notification

Complete complex tasks end-to-end without manual steps

Implementation Guide

Prerequisites

  • Claude Desktop 0.7.0+ or Cursor IDE with MCP support
  • Basic understanding of MCP architecture and capabilities
  • Access credentials for integrated services (if required)
  • Willingness to experiment and iterate on configuration

Time Estimate

15-60 minutes depending on server complexity

Installation Steps

  1. 1.Install MCP server: npm install -g [package-name] or via GitHub
  2. 2.Add server configuration to ~/.claude/mcp.json
  3. 3.Provide required credentials and configuration
  4. 4.Restart Claude Desktop to load new server
  5. 5.Test basic functionality with simple prompts
  6. 6.Explore capabilities and experiment with use cases
  7. 7.Document successful patterns for reuse

Troubleshooting

  • MCP server not loading: Check config syntax, verify installation
  • Connection errors: Check network, firewall, credentials
  • Feature not working: Read server docs, check required parameters
  • Performance issues: Monitor resource usage, check for network latency
  • Conflicts with other servers: Check port assignments, namespace collisions

Best Practices

✓ Do

  • +Read server documentation thoroughly before setup
  • +Start with simple use cases to validate functionality
  • +Test in non-production environment first
  • +Monitor resource usage and performance
  • +Keep servers updated for bug fixes and new features
  • +Document configuration for team members
  • +Use environment variables for sensitive configuration

✗ Don't

  • Don't grant overly permissive access to MCP servers
  • Don't skip reading security considerations in docs
  • Don't expose sensitive data without proper controls
  • Don't run untrusted MCP servers without code review
  • Don't ignore error messages—investigate root cause

💡 Pro Tips

  • Combine multiple MCP servers for powerful workflows
  • Create custom MCP servers for your specific needs
  • Share successful configurations with team
  • Use MCP inspector for debugging
  • Join MCP community for tips and troubleshooting

Technical Details

Architecture

Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.

Protocols

  • Model Context Protocol (MCP)
  • JSON-RPC 2.0
  • stdio or HTTP transport

Compatibility

  • Claude Desktop
  • Cursor IDE
  • Custom MCP clients

When to Use This

✓ Use When

Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.

✗ Avoid When

Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.

Integration

  • Tool composition: Chain multiple MCP tools in workflows
  • Context augmentation: Provide AI with relevant external data
  • Action delegation: Let AI execute tasks on external systems
  • Bidirectional sync: Keep AI context and external systems in sync

Discussion

Product Hunt–style comments (not star reviews)
  • No comments yet — start the thread.

List & Promote Your MCP Server

Share your MCP server with the developer community

GET_STARTED →
MCP server reviews

Ratings

4.641 reviews
  • Chaitanya Patil· Dec 20, 2024

    We evaluated Fluora MCP against two servers with overlapping tools; this profile had the clearer scope statement.

  • Zaid Desai· Dec 16, 2024

    We wired Fluora MCP into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.

  • Carlos Agarwal· Dec 16, 2024

    Useful MCP listing: Fluora MCP is the kind of server we cite when onboarding engineers to host + tool permissions.

  • Piyush G· Nov 11, 2024

    Useful MCP listing: Fluora MCP is the kind of server we cite when onboarding engineers to host + tool permissions.

  • William Desai· Nov 7, 2024

    We evaluated Fluora MCP against two servers with overlapping tools; this profile had the clearer scope statement.

  • Carlos Nasser· Oct 26, 2024

    Fluora MCP is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.

  • Shikha Mishra· Oct 2, 2024

    Fluora MCP reduced integration guesswork — categories and install configs on the listing matched the upstream repo.

  • Camila Chen· Sep 25, 2024

    Strong directory entry: Fluora MCP surfaces stars and publisher context so we could sanity-check maintenance before adopting.

  • Carlos Patel· Sep 17, 2024

    We wired Fluora MCP into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.

  • Luis Perez· Sep 17, 2024

    According to our notes, Fluora MCP benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.

showing 1-10 of 41

1 / 5