GenPark Concurrency Semaphore Guard

io.github.alphaparkincPublished by GitHub account alphaparkincv1.0.1Updated Oct 26, 2026

In-memory concurrency leaky-bucket and fair semaphore guard protecting downstream LLM APIs from rate

VerifiedSTDIODesktop onlyDeveloper ToolsAI & ML

Overview

AI-generated overview

A local MCP server that guards downstream LLM APIs with an in-memory leaky-bucket and fair semaphore to prevent rate-limit saturation.

What you can do
  • Provides an in-memory concurrency guard combining a leaky bucket with a fair semaphore.
  • Throttles and queues calls so downstream LLM APIs are not saturated by rate limits.
  • Runs as a local MCP server that agents and desktop clients can connect to.
  • Can also be used directly as a Python library in agent workflows.
When to use it
Worth adding when several agents or tools share the same LLM API quota and you want a local, dependency-free way to cap concurrency and smooth request bursts.
Requirements
Runs as a local process on the user's machine, started with the Python interpreter (standard library only, no third-party runtime dependencies). Desktop only; no authentication, environment variables or headers declared.
Before you install
The guard is in-memory, so limits apply only within one running process and are not shared across machines or restarts. No tools, credentials or data-handling details are documented, so review the package before installing.

Installation

In SourceWeft

  1. Open GenPark Concurrency Semaphore Guard in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

GenPark Concurrency Semaphore Guard

[License: MIT] [Python Standard Library] [Model Context Protocol] [GenPark]

In-memory concurrency leaky-bucket and fair semaphore guard protecting downstream LLM APIs from rate-limit saturation.

Part of the GenPark AI Agent Skills Ecosystem.

🌟 Key Features

  • 100% Python Standard Library: Zero third-party runtime dependencies.
  • MCP Native: Plugs directly into Claude Desktop, Cursor, LobeChat, and autonomous agent DAGs.
  • Production Resilience: Strict schema conformance, zero data loss, enterprise hardened.

🚀 Installation & Usage

Run as an MCP server:

bash
python mcp_server.py

Use directly as a library:

python
from client import *

See example_usage.py for comprehensive integration demonstrations.

📄 License

MIT License. Maintained by GenPark AI.

Source: README.md at commit 49d56b8

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.1LatestOct 20, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.