Claude Desktop
Desktop · Freemium · Proprietary
Anthropic's official Claude AI desktop application. Supports MCP servers to extend functionality.
WindowsMacOS
pyATS_MCP
automateyournetwork/pyATS_MCP
Cisco pyATS and Genie already know how to talk to a network — parsing show commands, pushing configuration, learning feature state, running declarative tests. What they didn't have was a way for an AI agent to drive any of it directly.
Install
npx -y mcp-remote http://localhost:8080/mcp --transport http-onlyClient configuration
{
"mcpServers": {
"pyats": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"http://localhost:8080/mcp",
"--transport",
"http-only"
]
}
}
}Environment variables
PYATS_TESTBED_PATHPYATS_MCP_ARTIFACTS_DIRPYATS_MCP_KEEP_ARTIFACTSPYATS_MCP_TESTBED_CACHE_TTLPYATS_MCP_CONN_CACHE_TTLPYATS_MCP_OP_LOG_MAXPYATS_MCP_TRANSPORT_MODEPYATS_MCP_HTTP_HOSTPYATS_MCP_HTTP_PORTXPRESSO_URLXPRESSO_API_TOKENXPRESSO_GROUP- GitHub stars
- 16
- Author
- @automateyournetwork
- Category
- Monitoring, Developer Tools
- License
- MIT
- Updated
- Oct 6, 2026
About pyATS_MCP
This server closes that gap: it wraps pyATS/Genie as a set of structured, guarded MCP tools that an agent like Claude can call against a real testbed, over the Model Context Protocol's current Streamable HTTP transport.
Point an agent at it and it can look up a device, run and parse a show command, apply configuration with a rollback point, learn and diff a feature's state before and after a change, fan a command out across a fleet — one thread pool or one process per device — run a declarative Blitz or Robot Framework test, or call a device's REST/RESTCONF API directly. Every risky path is guarded before it reaches a device, and every call lands in an…
Tools (26)
pyats_list_devices
List all devices in the testbed
pyats_search_devices
Fuzzy-search devices by name or alias
pyats_run_show_command
Run a validated show command; returns parsed JSON or raw output
pyats_run_show_command_multi
Run a show command across multiple devices concurrently (thread pool)
pyats_pcall_show_command
Same, but one OS process per device (pyats.async_.pcall) instead of a shared thread pool
pyats_show_running_config
Retrieve the full running configuration (raw text)
pyats_show_logging
Retrieve device system logs via show logging
pyats_ping_from_network_device
Execute a ping from a network device
pyats_run_linux_command
Run a command on a Linux host
pyats_configure_device
Apply configuration commands with safety guardrails
pyats_configure_devices_multi
Apply configuration across multiple devices concurrently (thread pool)
pyats_pcall_configure_devices
Same, but one OS process per device
pyats_configure_with_diff
Apply config and return a before/after diff
pyats_rollback_config
Roll back to the last saved configuration snapshot
pyats_device_health
Snapshot CPU, memory, interfaces, and routing state
pyats_get_neighbors
Retrieve CDP/LLDP neighbors
pyats_find_interface_by_ip
Find which interface owns a given IP address
pyats_learn_feature
Genie device.learn() for a whole feature (interface, ospf, bgp, …), optionally saved as a named snapshot
pyats_diff_learned_snapshots
Diff two snapshots saved by pyats_learn_feature
pyats_clean_device
Genie Clean (Kleenex), restricted to non-destructive connect+execute_command stages; dry_run=True by default
pyats_run_blitz
Run a declarative pyATS Blitz YAML test
pyats_run_robot
Run a Robot Framework suite using the pyats.robot/genie.libs.robot keyword libraries
pyats_run_dynamic_test
Execute a sandboxed pyATS AEtest script
pyats_rest_request
Generic REST/RESTCONF/NX-API call via pyATS's rest.connector (a separate connection type from CLI/SSH)
pyats_xpresso_request
Authenticated call to Cisco XPresso's REST API v2 (test requests, jobs, testbeds, images, …)
pyats_get_operation_log
Retrieve the in-memory operation log
Details on this page are taken from the project's README. Open README
Supported clients
Clients mentioned in this server's README:
VS Code GitHub Copilot
Desktop · Freemium · MIT
VS Code integrates MCP with GitHub Copilot through agent mode, allowing direct interaction with MCP-provided tools in your agentic coding workflow. Configure servers in Claude Desktop, workspace, or user settings, with guided MCP installation and secure handling of secrets in input variables to avoid leaking hardcoded keys.
Related MCP servers
2344
comet-ml/opik
Opik is the open-source LLM observability and evaluation platform for AI agent tracing, LLM evaluation, prompt management, and production monitoring. Built by Comet. Apache-2.0 licensed, free to self-host the full platform, with 20,000+ GitHub stars.
MCP Grafana
grafana/mcp-grafana
A Model Context Protocol (MCP) server for Grafana.
Vite Plugin Vue MCP
webfansplz/vite-plugin-vue-mcp
Vite plugin that enables a MCP server for your Vue app to provide information about the component tree, state, routes, and pinia tree and state.
api200
API-200/api200
API 200 is all-in-one gateway for managing third-party APIs efficiently. Integrate third-party APIs or setup MCP server in minutes with auto-generated code, docs, auth, caching and error handling – so you can focus on what really matters.
WireMCP (Wireshark)
0xkoda/wiremcp
WireMCP is a Model Context Protocol (MCP) server designed to empower Large Language Models (LLMs) with real-time network traffic analysis capabilities.
gospy
monsterxx03/gospy
A tool for inspecting and analyzing running Go processes, including goroutine states, memory statistics, and binary information.