Rubber Duck MCP Server

Created By
francoisjosephlacroixa year ago
A rubber duck MCP server for your LLM coding agent
Overview

what is Rubber Duck MCP Server?

Rubber Duck MCP Server is a Model Context Protocol (MCP) server designed to provide a rubber duck debugging tool for Large Language Models (LLMs). It allows LLMs to explain their code to a "rubber duck" without expecting any response, aiding in organizing thoughts and debugging effectively.

how to use Rubber Duck MCP Server?

To use the Rubber Duck MCP Server, connect to it through the MCP protocol. Install it using the FastMCP CLI with the command: fastmcp install src/server.py. This will integrate the rubber-duck tool into your LLM environment.

key features of Rubber Duck MCP Server?

  • Silent Rubber Duck: A classic debugging companion that listens without responding.
  • Squeaky Rubber Duck: An interactive rubber duck that squeaks when squeezed, adding a fun element to debugging.

use cases of Rubber Duck MCP Server?

  1. Debugging complex code issues by explaining them to the rubber duck.
  2. Walking through implementation logic to clarify thought processes.
  3. Organizing thoughts during development to enhance productivity.
  4. Adding a playful aspect to debugging with the squeaky feature.

FAQ from Rubber Duck MCP Server?

  • Can I use Rubber Duck MCP Server with any LLM?

Yes! It is designed to work with any LLM that supports the MCP protocol.

  • Is there any cost associated with using the Rubber Duck MCP Server?

No, it is open-source and free to use under the MIT License.

  • What are the system requirements?

You need Python 3.10 or higher and the uv package manager along with the fastmcp package.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
francoisjosephlacroix
Star
0
Language
Python
License
-

Recommend Servers

View All
Scratchpad Mcp
@MikePressure

scratchpad-mcp is an MCP server that gives AI agents persistent, token-efficient storage. It solves a specific waste problem: agents constantly re-read files they've already seen, re-summarize documents they've already processed, and re-load context they've already understood. Every one of those round-trips burns tokens for no new information. This server fixes that with eight tools designed around how agents actually work: Versioned writes. write_file automatically versions every write and keeps the 10 most recent versions per file. Storage is append-only on success and atomic on failure partial writes can't corrupt state. Structured diffs. read_file accepts a since_version parameter and returns a JSON line-diff against that prior version instead of the full content. Agents that have already seen v1 can ask "what changed in v3?" and get a small structured payload they can reason about, not the entire file again. Append-only logs. append_log and read_log give agents an event-stream they can replay. Cursor-based pagination (since_entry + last_entry_id + has_more) means an agent can checkpoint where it left off and resume cheaply. On-demand summaries. summarize_file calls Claude Haiku to summarize files over ~2000 estimated tokens. Summaries are cached per file version, so repeat calls on an unchanged file cost nothing. The threshold is enforced server-side you can't accidentally pay to summarize something small. Per-agent isolation. Every operation is scoped by an agent_id parameter, so one server instance can serve many agents without leaking state between them. Storage limits. 1 MB per file write, 64 KB per log entry, 1000 files / 100k log entries / 100 MB total per agent sane multi-tenant guardrails out of the box. Backed by a single SQLite file (Postgres migration is on the roadmap). All SQL is parameterized, paths are validated against a strict allowlist, and the security model is documented honestly it's safe for one-user-per-process deployments today, and the V2 plan derives agent_id from the caller's API key for true multi-tenancy. Build agents that remember what they've already seen.

12 hours ago