Skip to main content
Glama
chenjordan

mcp_supervisor_py

by chenjordan

mcp_supervisor_py

Python-first scaffold for an MCP-style supervisor role.

Goal

Build a supervisor that can:

  • accept a user task

  • break it into steps

  • route steps to workers

  • retry on transient failures

  • aggregate final output

  • emit structured logs for auditability

Related MCP server: task-orchestrator

Reference repositories

This repository is intended to be designed with ideas inspired by:

Project layout

  • src/mcp_supervisor/config.py: runtime configuration

  • src/mcp_supervisor/supervisor.py: supervisor core logic

  • src/mcp_supervisor/init.py: package exports

  • examples/run_demo.py: runnable demonstration

Quick start

  1. Create a virtual environment

python -m venv .venv
.venv\Scripts\activate
  1. Install editable package

pip install -e .
  1. Run demo

python examples/run_demo.py

Notes

  • Current version is an MVP scaffold.

  • Next iteration will add tool permission policy, async workers, and persistence.

F
license - not found
-
quality - not tested
C
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

View all related MCP servers

Related MCP Connectors

  • Agent-native collaboration network: orchestrate a team of long-running agents from any MCP client.

  • Control plane for autonomous software labor. Agents claim objectives over MCP with audit trail.

  • Coordinate multiple AI agents over MCP: atomic claims, leases, shared ledger, handoffs, tasks.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/chenjordan/mcp_supervisor_py'

If you have feedback or need assistance with the MCP directory API, please join our Discord server