1. Conduid
  2. Agents
  3. AI Assistant With MCP Server And Tools Using Langchain And Groq.
MCP server · Agents

AI Assistant With MCP Server And Tools Using Langchain And Groq.

by · github.com/kshitija852/AI-Assistant-with-MCP-server-and-tools-using-langchain-and-groq.
Unclaimed last commit 6 months ago agents
InstallView source
30Low

Scored 6 months ago · breakdown

About AI Assistant With MCP Server And Tools Using Langchain And Groq.

AI Assistant With MCP Server And Tools Using Langchain And Groq. is an MCP server published by kshitija852 in the Agents category.

Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.

Install

From source
git clone https://github.com/kshitija852/AI-Assistant-with-MCP-server-and-tools-using-langchain-and-groq.

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about AI Assistant With MCP Server And Tools Using Langchain And Groq.

Powered by Claude · Grounded in docs

I know everything about AI Assistant With MCP Server And Tools Using Langchain And Groq.. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ✓README presentThe repository ships documentation.

5 checks have not been run yet.

README

AI Assistant with MCP, LangChain, and Groq

A small terminal chat app that connects a Groq LLM to multiple MCP (Model Context Protocol) servers through mcp-use and LangChain. You type natural language; the agent picks tools (browser automation, search, etc.) and runs them for you.

Features

  • Multi-server MCP — Configured via browser_mcp.json (Playwright browser, Airbnb, DuckDuckGo search).
  • Groq — Fast inference via langchain-groq (ChatGroq).
  • Conversation memory — MCPAgent keeps context across turns until you clear it.
  • Robust tool calls — Custom middleware strips null optional arguments so strict MCP servers (e.g. Playwright) do not reject JSON null for optional string fields.
  • Browser search hints — System instructions steer the model toward reliable patterns (e.g. Google: navigate to https://www.google.com/search?q=... instead of typing into ambiguous homepage refs).

Requirements

Requirement Notes
Python 3.13+ (see pyproject.toml)
uv Used to create the venv and run the app
Node.js npx must work; MCP servers in this project start via npx
Groq API key Groq Console

Quick start

  1. Clone the repository (use the exact URL from your GitHub repo page).

  2. Install dependencies

    cd mcpdemos
uv sync

  3. Create a .env file in the project root (this file is gitignored):

    GROQ_API_KEY=your_groq_api_key_here

  4. Run the chat loop

    uv run app.py

    First run may download MCP packages through npx; allow network access.

Usage

  • Type your request at the You: prompt (e.g. open a site, search, or combine steps).
  • exit, quit, or bye — Leave the app.
  • clear, clear history, or reset — Clear the agent’s conversation memory.

Configuration

browser_mcp.json

Defines MCP servers in the standard mcpServers shape. This project includes:

Server Purpose
playwright @playwright/mcp — browser navigate, click, type, snapshot, etc.
airbnb @openbnb/mcp-server-airbnb
duckduckgo-search duckduckgo-mcp-server

You can add/remove servers or change args; restart the app after edits.

app.py (knobs you might change)

  • config_file — Path to the MCP JSON config (default: browser_mcp.json).
  • ChatGroq — model, max_tokens, temperature.
  • MCPAgent — max_steps, memory_enabled, additional_instructions (browser/search behavior).

Project layout

Path Role
app.py Async chat loop, MCP client, middleware, agent setup
browser_mcp.json MCP server definitions
main.py Minimal entry stub (primary demo is app.py)
pyproject.toml / uv.lock Dependencies and lockfile

Troubleshooting

  • Repository not found (git) — Confirm the remote URL matches your GitHub repo slug exactly (including any trailing . in the repo name if you created it that way).
  • 429 from Groq — Rate limit; wait and retry or check Groq rate limits.
  • Playwright / browser errors — Ensure Node and npx work; first run may install @playwright/mcp. For Google searches, the app is tuned to prefer direct search?q= URLs to avoid filling non-input elements.
  • Telemetry — mcp-use may log anonymized telemetry; set MCP_USE_ANONYMIZED_TELEMETRY=false in the environment if you want it off.

License

Specify your license here (e.g. MIT) or add a LICENSE file.

README copy captured when this server was indexed; it may lag the repository. The original is authoritative.

Questions

About AI Assistant With MCP Server And Tools Using Langchain And Groq.

How do I install AI Assistant With MCP Server And Tools Using Langchain And Groq.?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is AI Assistant With MCP Server And Tools Using Langchain And Groq. safe to use with an AI agent?

Its trust score is 30 out of 100 (low). It passes 1 of the 1 static security checks run so far. It has no ConduID identity yet, so agent calls to it are not receipted.

Is AI Assistant With MCP Server And Tools Using Langchain And Groq. still maintained?

The last commit was 6 months ago. That's long enough that you should check whether the maintainer is responding to issues before depending on it.