MCP SSE Client Python

Created By
zanetworkera year ago
Simple MCP Client for remote MCP Servers 🌐
Overview

What is MCP SSE Client Python?

MCP SSE Client Python is a Python client designed for interacting with Model Context Protocol (MCP) endpoints using Server-Sent Events (SSE). It provides a simple interface for connecting to MCP servers and invoking tools interactively.

How to use MCP SSE Client Python?

To use the MCP SSE Client, clone the repository, install the package, and run the interactive Streamlit app to test the tools available on the MCP endpoint.

Key features of MCP SSE Client Python?

  • Connects to MCP endpoints via Server-Sent Events.
  • Allows discovery and invocation of tools with parameters.
  • Integrates with various LLMs (OpenAI, Anthropic, Ollama) for AI-driven tool selection.
  • Provides a command-line interface for interactive testing.
  • Includes a user-friendly Streamlit app for testing tools interactively.

Use cases of MCP SSE Client Python?

  1. Connecting to and interacting with various MCP tools.
  2. Using AI to select the appropriate tool based on natural language queries.
  3. Testing tools interactively through a Streamlit UI.

FAQ from MCP SSE Client Python?

  • What programming language is used?

The client is written in Python.

  • What are the requirements?

Requires Python 3.7+, along with specific libraries like requests, sseclient-py, and streamlit.

  • Is there a graphical interface?

Yes, the Streamlit app provides a graphical interface for testing tools.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
zanetworker
Star
0
Language
Python
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.

37 minutes ago