try_fastmcp

Created By
iAbdelRahima year ago
chat with a llm having access to a mcp server.
Overview

what is try_fastmcp?

try_fastmcp is a Python application that creates an MCP server using the FastMCP library and interacts with the OpenAI API to facilitate chat functionalities.

how to use try_fastmcp?

To use try_fastmcp, clone the repository, set up a virtual environment, install the dependencies, and run the MCP server and client using the provided commands.

key features of try_fastmcp?

  • Retrieves public datasets from data.gouv.ci catalog.
  • Fetches news articles based on user queries.
  • Performs basic arithmetic operations (add, subtract, multiply, divide).
  • Calculates advanced mathematical functions (power, square root, cube root, factorial, logarithm, trigonometric functions).
  • Provides personalized greetings.

use cases of try_fastmcp?

  1. Chatting with an AI that can perform calculations and fetch data.
  2. Educational tool for learning basic and advanced math operations.
  3. Research tool for accessing public datasets and news articles.

FAQ from try_fastmcp?

  • What are the prerequisites for using try_fastmcp?

You need Python 3.6 or higher and an OpenAI API key.

  • Is there a graphical interface for the client?

Yes, the client can be run using Streamlit, which provides a web interface.

  • Can I customize the greetings?

Yes, you can personalize the greeting by using the greeting://{name} resource.

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