Advertise
MCP.so
Sign In

Agent MCP Server

@Zeppelinpp

Repository

Basic information

Category

AI & Agents

License

MIT license

Transports

stdio

Author

Zeppelinpp

About Agent MCP Server

local mcp server-client agent

Agent MCP Server config

No standard config provided

This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.

Repository

Agent MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Agent-MCP?

Agent-MCP is a local MCP server-client agent that provides a web search MCP server using Google SerpAPI and a client capable of calling both local MCP servers and external MCP services from the Smithery platform. It is designed for developers who want to integrate web search and tool-use capabilities into AI agents using the Model Context Protocol, with an OpenAI-compatible API interface.

How to use Agent-MCP?

Configure the MCP server by specifying the command and arguments (e.g., python with the server script path) when creating MCPServerStdio. The client is set up with an OpenAI-compatible endpoint and can invoke planning and researcher agents via Runner.run_streamed(). The example in the README uses a planning agent that hands off to a research agent using the MCP server.

Key features of Agent-MCP

  • Local web search MCP server using Google SerpAPI
  • MCP client compatible with OpenAI API format
  • Supports both local MCP servers and external Smithery services
  • Integrates planning and researcher agents for deep research workflows
  • Tested with Qwen2.5 and DeepSeek-V3 models

Use cases of Agent-MCP

  • Performing web research with AI agents using natural language queries
  • Building a multi-step research workflow with planning and tool-use
  • Integrating web search capabilities into custom AI pipelines via MCP
  • Testing different LLMs (Qwen, DeepSeek) with MCP tool calls

Frequently asked questions

1

What API does the MCP server use for web search?

It uses Google SerpAPI as the search API.

2

How does the MCP client differ from the original Anthropic client?

The

Comments

More AI & Agents MCP servers

FLORA

FLORA is a remote MCP server available at https://agents.flora.ai. The FLORA MCP lets users generate, organize, and iterate on visual assets — hero images, moodboards, lifestyle shots, promo graphics — directly from a co

OpenZiti / LLM-Gateway

openziti

NetFoundry LLM Gateway is an OpenAI-compatible API proxy that routes requests across multiple LLM providers using zero-trust networking. Zero trust LLM gateway. OpenAI-compatible proxy with semantic routing and load bala

93

GoBuy - Product Trust

gobuy-ai

GoBuy gives AI agents marketplace-evidence trust scores. One call returns a 0–100 Evidence Score with observed/missing signals, freshness, and product context. Tools: • check_product_trust — inspect one Amazon, Walmart,

OpenZiti MCP Gateway

openziti

NetFoundry MCP Gateway enables secure, isolated access to Model Context Protocol (MCP) tools across distributed systems without exposing public endpoints. Zero trust gateway for MCP servers. Aggregate, filter, and secure

48

bsv.cx

Andy Rowe

Timestamp and verify evidence on-chain. Let your agent prove what it saw and when. bsv.cx gives an AI agent verifiable memory. Timestamp a hash of any output, archive a web page as it looked, or fetch a URL with a recei

Advertise