Fused MCP Agents: Setting up MCP Servers for Data

Created By
fusedioa year ago
Fused MCP Agents: Setting up MCP Servers for Data Scientists
Overview

What is Fused MCP?

Fused MCP is a project designed to set up MCP servers for data scientists, allowing them to connect Claude and other LLMs to APIs and executable code seamlessly.

How to use Fused MCP?

To use Fused MCP, clone the repository from GitHub, install the necessary dependencies, and follow the instructions in the provided Jupyter notebook to set up the MCP server with Claude's Desktop App or a local client.

Key features of Fused MCP?

  • Easy setup of MCP servers for data scientists.
  • Compatibility with Claude's Desktop App and local clients.
  • Step-by-step guidance through a Jupyter notebook.

Use cases of Fused MCP?

  1. Connecting LLMs to APIs for enhanced data processing.
  2. Running Python code directly from a local environment.
  3. Facilitating data science workflows with integrated tools.

FAQ from Fused MCP?

  • Do I need a Fused account to use this?

No, you can run everything locally without a Fused account.

  • What are the system requirements?

You need Python 3.11 and the latest Claude Desktop app installed on MacOS or Windows.

  • Can I use this on Linux?

Yes, there is a local client available for Linux users.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
fusedio
Star
24
Language
Jupyter Notebook
License
MIT license

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

29 minutes ago