PyATS MCP vs Kibi MCP
A side-by-side look at the PyATS MCP and Kibi MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose PyATS MCP for coding agents work over a hosted endpoint; choose Kibi MCP for coding agents as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose PyATS MCP when
- You need dedicated capabilities in the Coding Agents domain.
- You prefer a remote HTTP/SSE transport.
- Its auth model fits you: other.
- You have the keys it needs:
PYATS_TESTBED_PATH, PYATS_MCP_ARTIFACTS_DIR, PYATS_MCP_KEEP_ARTIFACTS, PYATS_MCP_TESTBED_CACHE_TTL, PYATS_MCP_CONN_CACHE_TTL, PYATS_MCP_OP_LOG_MAX, PYATS_MCP_TRANSPORT_MODE, PYATS_MCP_HTTP_HOST. - You want tools like
pyats_list_devices, pyats_search_devices, pyats_run_show_command.
Choose Kibi MCP when
- You need dedicated capabilities in the Coding Agents domain.
- You prefer a local stdio subprocess transport.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Coding Agents | Coding Agents |
| Quality signal | 60/100 · Good | 48/100 · Fair |
| Install command | Confirmed | Confirmed |
| Transport | Remote HTTP/SSE | Local subprocess (stdio) |
| Auth | other | Not declared |
| Pricing | Free | Not declared |
| Required env vars | 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_HOST | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 89 | 10 |
| Directory activity | 4 views 0 installs 0 upvotes | 0 views 0 installs 0 upvotes |
| Tools | 26 | Not listed |
| Full listing | View PyATS MCP | View Kibi MCP |
Tools & capabilities
PyATS MCP tools 26
pyats_list_devicesList all devices in the testbedpyats_search_devicesFuzzy-search devices by name or aliaspyats_run_show_commandRun a validated show command; returns parsed JSON or raw outputpyats_run_show_command_multiRun a show command across multiple devices concurrently (thread pool)pyats_pcall_show_commandSame, but one OS process per device (`pyats.async_.pcall`) instead of a shared thread poolpyats_show_running_configRetrieve the full running configuration (raw text)pyats_show_loggingRetrieve device system logs via `show loggingpyats_ping_from_network_deviceExecute a ping from a network devicepyats_run_linux_commandRun a command on a Linux hostpyats_configure_deviceApply configuration commands with safety guardrailspyats_configure_devices_multiApply configuration across multiple devices concurrently (thread pool)pyats_pcall_configure_devicesSame, but one OS process per device- +14 more on the listing page
Kibi MCP tools
No tool names declared yet. Check the project README from the listing page.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
PyATS MCP
{
"mcpServers": {
"automateyournetwork-pyats-mcp": {
"url": "http://localhost:8080/mcp"
}
}
}
Kibi MCP
{
"mcpServers": {
"kibi-mcp": {
"command": "npx",
"args": [
"-y",
"--no-install",
"kibi-mcp"
]
}
}
}
Frequently asked questions
PyATS MCP is categorized under Coding Agents and uses a remote HTTP/SSE transport. Kibi MCP belongs to Coding Agents and uses a local stdio subprocess. Pick PyATS MCP for coding agents work and Kibi MCP for coding agents.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
PyATS MCP is listed as free. Auth: other. Kibi MCP has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add automateyournetwork-pyats-mcp and kibi-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, PyATS MCP has a quality signal of 60/100 (Good) with 4 views, 0 installs and 89 GitHub stars. Kibi MCP has 48/100 (Fair) with 0 views, 0 installs and 10 GitHub stars.