Skip to main content

MCP (Model Context Protocol) server for Joblet job orchestration system

Project description

Joblet MCP Server

MCP server for Joblet job orchestration - enables AI assistants to manage distributed computing jobs through the Joblet platform.

Quick Start

# Install (SDK mode - recommended)
pip install joblet-mcp-server[sdk]

# Configure (~/.rnx/rnx-config.yml)
mkdir -p ~/.rnx
cp sample_config.yaml ~/.rnx/rnx-config.yml
# Edit with your Joblet server credentials

# Run (SDK mode)
joblet-mcp-server

Features

  • Jobs - Run, monitor, and manage compute jobs
  • Workflows - Orchestrate multi-job pipelines
  • Storage - Create and manage persistent volumes
  • Networks - Configure isolated networks
  • Monitoring - Real-time metrics and GPU status

Implementation Modes

The MCP server provides two implementations for communicating with Joblet:

1. SDK Mode (Recommended)

Command: joblet-mcp-server

Uses joblet-sdk-python for direct gRPC communication with the Joblet server.

Advantages:

  • Better performance (direct gRPC, no subprocess overhead)
  • Type safety and error handling
  • Automatic connection management
  • Streams data efficiently

Requirements:

  • Install with SDK: pip install joblet-mcp-server[sdk]
  • Requires joblet-sdk-python >= 2.0.0 (proto v2.3.0+)

2. CLI Mode (Alternative)

Command: joblet-mcp-server-cli

Uses subprocess calls to the rnx CLI binary.

Advantages:

  • Works without Python SDK
  • Uses existing CLI tools
  • Simpler deployment if rnx already installed

Requirements:

  • Install without SDK: pip install joblet-mcp-server
  • Requires rnx binary in PATH or specify with --rnx-binary
  • Configure via ~/.rnx/rnx-config.yml

Usage:

# Use rnx from PATH
joblet-mcp-server-cli

# Specify custom rnx binary location
joblet-mcp-server-cli --rnx-binary /path/to/rnx

Configuration

Create ~/.rnx/rnx-config.yml:

version: "3.0"
nodes:
  default:
    address: "joblet-server.com:50051"
    cert: |
      -----BEGIN CERTIFICATE-----
      # Your client certificate
      -----END CERTIFICATE-----
    key: |
      -----BEGIN PRIVATE KEY-----
      # Your private key
      -----END PRIVATE KEY-----
    ca: |
      -----BEGIN CERTIFICATE-----
      # Your CA certificate
      -----END CERTIFICATE-----

Requirements

Common Requirements

  • Python 3.10+
  • Joblet server with TLS certificates
  • Configuration file at ~/.rnx/rnx-config.yml

SDK Mode (Recommended)

  • joblet-sdk-python >= 2.0.0 (installed automatically with [sdk] extra)
  • Direct gRPC communication (port 50051)

CLI Mode (Alternative)

  • rnx binary installed and in PATH
  • No Python SDK required

Documentation

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

joblet_mcp_server-1.1.3.tar.gz (17.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

joblet_mcp_server-1.1.3-py3-none-any.whl (16.2 kB view details)

Uploaded Python 3

File details

Details for the file joblet_mcp_server-1.1.3.tar.gz.

File metadata

  • Download URL: joblet_mcp_server-1.1.3.tar.gz
  • Upload date:
  • Size: 17.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for joblet_mcp_server-1.1.3.tar.gz
Algorithm Hash digest
SHA256 34ab33609fe7e8b238bc15411b0c5b9e2fb6e92ae950a608372497f3685376d5
MD5 f946ae231d0f5f4bd6b1a22419877735
BLAKE2b-256 5a1057f6297381f38e143457a49e8530ccf828f7c3c5cbcc1bfd00d38c6f25b1

See more details on using hashes here.

Provenance

The following attestation bundles were made for joblet_mcp_server-1.1.3.tar.gz:

Publisher: release.yml on ehsaniara/joblet-mcp-server

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file joblet_mcp_server-1.1.3-py3-none-any.whl.

File metadata

File hashes

Hashes for joblet_mcp_server-1.1.3-py3-none-any.whl
Algorithm Hash digest
SHA256 429c8a3c6518a5be2e6159827ca010aa389ae8281f343bedf4eefa1b84021373
MD5 f2ab9d48741d3e9816c6408528152f66
BLAKE2b-256 99ca4147df5356a9b190588eb6007c0ed95390748bc68d92ef1aa664f52dbe6e

See more details on using hashes here.

Provenance

The following attestation bundles were made for joblet_mcp_server-1.1.3-py3-none-any.whl:

Publisher: release.yml on ehsaniara/joblet-mcp-server

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page