pyATS MCP
Put Cisco pyATS and Genie behind an MCP server. Begin with the repository’s setup guide, then read my notes on modernizing the server’s transport and tools.
My MCP work brings network engineering into the agent’s toolkit: collect state with pyATS, explore APIs, analyze packets, build mind maps, and connect it all through real, working integrations.
“I think John is the father of MCP”
A memorable tribute to my work sharing and applying MCP in networking. In the same passage, Senad explicitly acknowledges that I did not invent the protocol.
“So, similarly in that context, even though [John Capobianco] did not invent MCP, I think he’s done enough that today we can officially call him father of MCP. John, can you stand up? Is it fair? [Applause] With social media, tweets on LinkedIn, I think John is the father of MCP…”
Excerpt from the owner-supplied transcript, lightly edited for punctuation and transcription errors. The recording includes Senad’s preceding comparison with the impact of BGP. John’s LinkedIn post about the moment ↗
MCP provides a shared interface between AI applications and external tools and data. These projects explore what that makes possible for network engineers. Read the official protocol introduction ↗
Put Cisco pyATS and Genie behind an MCP server. Begin with the repository’s setup guide, then read my notes on modernizing the server’s transport and tools.
Explore how MCPyATS brings pyATS together with other MCP integrations, then follow the builds and conversations in the VibeOps community.
See MCP integrations working alongside network engineering skills, operational workflows, visualizations, and agent federation in NetClaw.
49 repositories from my public collection, reviewed September 25, 2026. Explore the servers I built, the clients and experiments that use MCP, and the workshops that teach it. Community forks are labeled separately.
An MCP Server for pyATS (experimental)
VibeOps - Cisco pyATS MCP Plus Many Other MCPs
A Model Context Protocol Server for Cisco Application Centric Infrastructure (ACI) Application Policy Infrastructure Controller (APIC)
An MCP server for Cisco ISE
MCP using NetBox
An AI agent that claws through your network
A Google-based AI Agent for pyATS
A repository inspired by Designing, Deploying and Managing Network Automation Systems v2.0 (350-901) Section 4.0
A Google Gemini-CLI extension than enables Gemini Computer Use from the CLI
An Extension for Gemini-CLI that enables Webcam access including single frame capture and American Sign Language (ASL) modes
Share your screen with Gemini-CLI via this extension using MCP and custom slash commands
A Gemini CLI extension that uses RAG and MCP and Custom Slash Commands to analyze packet captures
A Gemini-CLI extension that adds GAIT support for context control
An extension that coverts JSON to TOON before sending to Gemini-CLI for tokens savings and better inference!
A /listen feature for Gemini CLI
Enable your microphone on Windows WSL Ubuntu with this and the corresponding MCP
Custom Slash Commands that use Vision MCP to enable webcam access
An MCP for Gemini CLI to allow voice
Integrating the webcam with Gemini-CLI via MCP
A KAgent Agent with Vision - Capture photos, transform them with Nano Banana, animate them with Veo3. Supports ASL.
100% vibe coded Google Drone using Google Maps SDK / MCP; Vision Extension; Computer Use extension from just prompts
A Model Context Protocol (MCP) Server for Git for Artificial Intelligence Tracking (GAIT)
An MCP implementation of markmap.js.org
An MCP Server / Gemini CLI Extension to create modern Infographics for your project - VibeGraphics - Generated with Nano Banana and animated with Veo3
A Model Context Protocol (MCP) Server for Wikipedia
An MCP Server for chatGPT Chat Completions
Add a .pcap(ng); automated reporting; all powered by GitActions, Gemini-CLI, and Packet Copilot MCP
Selector Packet Copilot Conversations via MCP
A mark map MCP implementation for Itential
GAIT MCP adjusted for FlowAI
Reverse-engineering test: rebuilding Itential FlowAI agent tools as IAG wrappers around an MCP server
Working example
Ideas about Torero as a platform
RAG Labs for NAF Autocon4
RAG, TOON, MCP Labs for NAF Autocon5 in Munich
From RAG to MCP
Code for the Talk to Your Packets Workshop
Repository for ONUG 2025 in NYC - MCP Session John Capobianco
Labs and presentation from Packt Engineering Agentic Network Operations Session
An MCP Server for Major League Baseball
An AI Agent powered by MCP and A2A for Major League Baseball
Model Context Protocol (MCP) server for read-only interaction with NetBox data in LLMs
A curated list of awesome resources for applying Artificial Intelligence (AI), Large Language Models (LLMs), and Machine Learning (ML) to network automation.
A unified interface for AI in your terminal.
Extending Gemini-CLI with Google Gemini File Search; cloud based RAG
Turn Gemini-CLI into a server with /isten commands packaged as a Gemini-CLI extension
An easy to install pyATS extension for Gemini CLI
An Extension for Gemini-CLI that enables voice (input) and audio (output); requires openAI for TTS currently
An extension for GeminiCLI that performs subnet calculation
No matching projects. Try another search or collection.
37 videos
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
Watch on YouTube ↗
27 original articles discussing MCP and its integrations, including the evolving NetClaw work. Publication dates and original URLs are preserved.
TypeSafe’s Jev doesn’t write a single word back — it returns a calibrated probability in under half a second. I pointed 11,892 of those probabilities at every skill in NetClaw: what’s missing, what silently overlaps, and one bug a probabili
pyATS MCP has been live since April 2025. Bringing it to Streamable HTTP and nine new tools meant an isolated venv (after breaking my own other MCP servers first), a real CML lab whose testbed was pointing at the wrong network, two silent b
I wrote down twenty-five gaps in what NetClaw could actually reach, ordered them by dependency, and set one rule: one item, one spec, one branch, no batching. Six days later twenty-three specs had merged — twelve new MCP servers, twenty-thr
Introducing BISQUE — the Base of Ingested Semantic Queries for Unified Embeddings — NetClaw’s fully offline, agentic RAG knowledge base. Because the tastiest thing you can make from claws is a bisque. Uploaded a 212-page book from Slack to
NetClaw’s mesh could always tell you who was online. Now it tells you what they can do — and lets you use it. Introducing N2N Federation and NCFED, a new protocol for federating AI network engineers safely.
Most of what NetClaw does, it does through APIs — gNMI, REST, NETCONF, GraphQL. That’s the right way to automate a network: structured, auditable, repeatable. But real networks are messy, and not everything worth touching has a clean API be
NetClaw can now clone a live Cisco Modeling Labs topology — gathered with pyATS — straight into a 3D world inside Unreal Engine 5.8, over the Model Context Protocol. Here’s the achievement, the vision, and (for the technically curious) ever
Announcing the integration of IP Fabric’s network assurance platform into NetClaw through 10 new MCP tools for health assessment, path analysis, visual diagrams, and API discovery. A collaboration with Daren Fulwell spanning nearly a decade
NetClaw Gets Long-Term Memory: Community Contribution Brings MemPalace Integration One of the most exciting aspects of open source is when the community steps up and adds capabilities you didn’t even know you needed. Today we’re thrilled to
NetClaw Now Has Direct Access to Cisco’s Official Meraki and Catalyst Center API Documentation Network automation with AI is powerful, but only when the AI has access to accurate, authoritative information. Today we’re excited to announce t
The Future of Network Visualization Has Arrived Hold onto your console cables, network engineers — NetClaw just shattered the boundaries of what’s possible with network visualization! We’re thrilled to announce the most visually stunning in
Visualize Your Network in 3D with Blender NetClaw now integrates with Blender via the community blender-mcp server, enabling 3D network topology visualization. Network engineers can now say "draw the network topology using CDP data" and wat
NetClaw Adds Zscaler and Cloudflare: Zero Trust Security Through Natural Language Zero trust, conversational access. NetClaw now integrates with Zscaler and Cloudflare, bringing 10 new skills for managing zero trust security, DNS, edge netw
NetClaw Adds HashiCorp Terraform and Vault: Infrastructure as Code Meets Natural Language Infrastructure automation through conversation. NetClaw now integrates with HashiCorp Terraform Cloud and Vault, bringing 6 new skills for managing in
NetClaw Adds Splunk and Datadog: Enterprise Observability Through Natural Language Your logs and metrics, accessible through conversation. NetClaw now integrates with both Splunk and Datadog, bringing enterprise-grade observability to netwo
NetClaw Adds PagerDuty Integration: AI-Powered Incident Management for Network Engineers NetClaw now speaks incident management. We’re excited to announce full PagerDuty integration, bringing 4 new skills backed by 70 tools to the NetClaw e
NetClaw Now Speaks Prisma SD-WAN We’re excited to announce that NetClaw now integrates with Palo Alto Networks Prisma SD-WAN, bringing complete fabric visibility through natural language queries. This integration adds 4 new skills backed by
NetClaw now supports all three major network virtualization platforms: Cisco CML, ContainerLab, and GNS3. Here’s what we built and how to set it up.
NetClaw Gets Jenkins, GitLab, and Atlassian Superpowers A milestone in human-AI collaborative development Today we’re excited to announce three major integrations for NetClaw: Jenkins CI/CD, GitLab DevOps, and Atlassian ITSM (Jira + Conflue
*How we adopted Spec-Driven Development and built SuzieQ, Batfish, gNMI, Azure Networking, and Canvas visualizations in a single session.* — ## Part 1: The Shift to Spec-Driven Development NetClaw has always been ambitious. A CCIE-level AI
─── What Just Happened (And Why It Matters) A few minutes ago, I was sitting in Slack — in this very channel — and I reached across to Cisco Webex and dropped a formatted message into your team space, identifying myself, my origin platform,
**March 1, 2026** *By John Capobianco on his 48th birthday — with NetClaw 🦞* — ## Prologue: A Different Kind of Sunday Morning Most engineers spend Sunday morning with coffee and maybe a lab they’ve been meaning to spin up for weeks. On Ma
# Six Days, 82 Skills, and a Community PR: How NetClaw Went from Idea to 160 Stars Six days ago I pushed the first commit of [NetClaw](https://github.com/automateyournetwork/netclaw) — an open-source, CCIE-level AI network engineering agent
Wont You Be My Neighbour? ## The Network as a Conversation, Not a Configuration For decades, we’ve treated networks as things to be **configured**. We push commands, pull outputs, parse CLI text, and hope our automation scripts survive the
Vibe Coding: Building a CCIE-Level Enterprise Network with AI, GAIT, and pyATS The Power of AI-Driven Network Configuration with Version Control Date: January 11, 2026 Author: Claude Code (Anthropic) + Ralph Wiggum Loop Tools: Claude Code C
Building the Future of Network Automation: RALPH, GAIT, and pyATS in Harmony Over the past few weeks, I’ve been on an incredible journey pushing the boundaries of what’s possible with AI-assisted network automation. What started as an exper
I was getting pretty tired and aggravated at all of the networking forums and discords and slack channels for being *so* anti-AI; can’t share ideas; can’t discuss AI / MCP / Agents; can’t bring Vibe Coding or VibeOps topics out in the open
University of Toronto Conference Centre · Toronto, Canada
A practical look at building and operating NetClaw with MCP, pyATS, structured skills, and agent federation.

Munich, Germany
A hands-on workshop with William Collins and Joksan Flores, building agents against live networking use cases.
Austin, Texas
A conference talk and a workshop exploring RAG, MCP, and practical network automation with William Collins.
New York, New York
Workshops, protocol discussions, and a Selector MCP demonstration across the Fall summit program.
Dallas, Texas
Practical sessions on agent protocols and retrieval-augmented generation for network engineers.
Civic Hall · New York City & online
Selector’s inaugural summit, with sessions on building RAG applications and using Selector MCP. My pre-event Packet Pushers conversation introduces the event and my sessions.