🔍 🤖 🌐 Ollama Chat with MCP

Created By
redbuildinga year ago
This app demonstrates use of MCP server and client in a local model chat via Ollama that incorporates web search via Serper.
Overview

What is Ollama Chat with MCP?

Ollama Chat with MCP is a demonstration application that integrates local language models with real-time web search capabilities using the Model Context Protocol (MCP).

How to use Ollama Chat with MCP?

To use the application, clone the repository, install the required dependencies, set up your Serper.dev API key, and run either the web interface or the terminal client to start chatting and searching.

Key features of Ollama Chat with MCP?

  • Web-enhanced chat with real-time search results
  • Local model execution using Ollama
  • Integration of MCP for enhanced capabilities
  • Dual interfaces: terminal CLI and web-based GUI
  • Structured formatting of search results
  • Conversation memory to maintain context

Use cases of Ollama Chat with MCP?

  1. Engaging in informative conversations with real-time data
  2. Conducting research with integrated web search
  3. Utilizing local models for personalized interactions

FAQ from Ollama Chat with MCP?

  • Can I use my own language model?

Yes! You can customize the model used in the application.

  • Is there a cost to use the Serper.dev API?

There is a free tier available for the Serper.dev API.

  • What programming language is this project built with?

The project is built using Python.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
redbuilding
Star
0
Language
Python
License
MIT license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago