@automateyournetwork
基本情報
An MCP Server for pyATS (experimental)
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"pyats": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"PYATS_TESTBED_PATH",
"-v",
"/absolute/path/to/testbed/folder:/app",
"pyats-mcp-server"
],
"env": {
"PYATS_TESTBED_PATH": "/app/testbed.yaml"
}
}
}
}List all devices in the testbed
Fuzzy-search devices by name or alias
Run a validated show command; returns parsed JSON or raw output
Run a show command across multiple devices concurrently
Execute a ping from a network device
Run a command on a Linux host
Apply configuration commands with safety guardrails
Apply configuration across multiple devices concurrently
Apply config and return a before/after diff
Roll back to the last saved configuration snapshot
Snapshot CPU, memory, interfaces, and routing state
Retrieve CDP/LLDP neighbors
Find which interface owns a given IP address
Execute a sandboxed pyATS test script
Retrieve the in-memory operation log
pyATS MCP Server wraps Cisco pyATS and Genie, letting AI agents (Claude, LangGraph, etc.) run show commands, apply configuration, and query network state over STDIO using JSON-RPC 2.0. It communicates solely via STDIN/STDOUT with no HTTP ports or REST endpoints.
Clone the repository, install dependencies (pip install -r requirements.txt), copy .env.example to .env, edit the environment file with device credentials and testbed path, then run python3 pyats_mcp_server.py. Alternatively, build and run via Docker, passing the .env file and mounting the testbed YAML.
reload, erase, delete, etc..env — never in source code or testbed fileIt supports Cisco IOS XE, IOS XR, NX‑OS, IOS, Arista EOS, Juniper Junos, Palo Alto PAN‑OS, Linux, and Windows, set via `{DEVICENAME}_OS` in `.env`. A `generic` OS option lets Unicon autodetect on first connect.
Show commands are validated against dangerous pipes, redirects, and keywords. Config commands are checked for `reload`, `erase`, `write erase`, `delete`, and `format`. Dynamic tests run in a sandbox that bans `os`, `sys`, `subprocess` and other risky imports.
Credentials are never stored in the testbed YAML or source code. All device‑specific credentials (username, password, enable password) are defined in the `.env` file using a `{DEVICENAME}_{FIELD}` naming convention and referenced in the testbed via `%ENV{}` substitution.
The server requires Python 3 and the packages listed in `requirements.txt`. It can be run locally or inside a Docker container built from the provided `Dockerfile`.
All communication uses STDIN/STDOUT and JSON‑RPC 2.0. There are no HTTP ports or REST endpoints, making it suitable for MCP clients like Claude and LangGraph.
A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!
DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct
Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
コメント