k8stools 0.1.0

Tools and an MCP server for building Kubernetes agents

Kubernetes Tools

This package provides a collection of functions to be used as tools for an Agent. They can be called directly as functions or placed behind an MCP server (included). Some use cases include:

• Chat with your kubernetes cluster via GitHub CoPilot or Cursor.
• Build agents to monitor your cluster or perform root cause analysis.
• Vibe-code a custom chat UI.
• Use in non-agentic automations.

Currently, the priority is on functions that do not modify the state of the cluster. We want to focus first on the monitoring / RCA use cases. When we do add tools to address other use cases, they will be kept separate from the read-only tools so you can still build "safe" agents. In general, our goal is to focus on quality over quantity -- providing well-documented and strongly typed tools. We believe that this is a critical in enabling agents to make effective use of tools, beyond simple demos.

These are built on top of the kubernetes Python API (https://github.com/kubernetes-client/python). There are three styles of tools provided here:

1. There are tools that mimic the output of kubectl commands (e.g. get_pod_summaries, which is equivalent to kubectl get pods). Strongly-typed Pydantic models are used for the return values of these tools.
2. There are tools that return strongly typed Pydantic models that attempt to match the associated Kubernetes client types (see https://github.com/kubernetes-client/python/tree/master/kubernetes/docs). Lesser used fields may be omitted from these models. An example of this case is get_pod_container_statuses.
3. In some cases we simply call to_dict() on the class returned by the API (defined in https://github.com/kubernetes-client/python/tree/master/kubernetes/client/models). The return type is dict[str,Any], but we document the fields in the function's docstring. get_pod_spec is an example of this type of tool.

Installation

Via pip:

pip install k8stools

Via uv:

uv add k8stools

Current tools

These are the tools we define:

• get_namespaces - get a list of namespaces, like kubectl get namespace
• get_pod_summaries- get a list of pods, likekubectl get pods`
• get_pod_container_statuses - return the status for each of the container in a pod
• get_pod_events - return the events for a pod
• get_pod_spec - retrieves the spec for a given pod
• get_logs_for_pod_and_container - retrieves logs from a pod and container

We also define a set of associated "print_" functions that are helpful in debugging:

• print_namespaces
• print_pod_summaries
• print_pod_container_statuses
• print_pod_events
• print_pod_spec

Using the tools

Directly use in an agent

The core tools are in k8stools.k8s_tools. Here's an example usage in an agent:

from pydantic_ai.agent import Agent
from k8stools.k8s_tools import TOOLS

agent = Agent(
        model="openai:gpt-4.1",
        system_prompt=SYSTEM_PROMPT,
        tools=TOOLS
)

result = agent.run_sync("What is the status of the pods in my cluster?")
print(result.output)

Using via MCP

The script k8s-mcp-server provides an MCP server for the same set of tools. Here are the command line arguments for the server:

usage: k8s-mcp-server [-h] [--transport {streamable-http,stdio}] [--host HOST] [--port PORT]
                      [--log-level {DEBUG,INFO,WARNING,ERROR,CRITICAL}] [--debug]

Run the MCP server.

options:
  -h, --help            show this help message and exit
  --transport {streamable-http,stdio}
                        Transport to use for MCP server [default: stdio]
  --host HOST           Hostname for HTTP service [default: 127.0.0.1]
  --port PORT           Port for HTTP service [default: 8000]
  --log-level {DEBUG,INFO,WARNING,ERROR,CRITICAL}
                        Log level [default: INFO]
  --debug               Enable debug mode [default: False]

Use MCP with the stdio transport

The stdio transport is best for use with local Coding Agents, like GitHub CoPilot or Cursor. It is the default, so you can run the k8s-mcp-server script without arguments. Here's an example mcp.json configuration:

{
   "servers": {
      "k8stools-stdio": {
         "command": "${workspaceFolder}/.venv/bin/k8s-mcp-server",
         "args": [
         ],
         "envFile": "${workspaceFolder}/.envrc"
      }
   }
}

This assumes the following:

1. The Python virtual environment is expected to be in .venv under the root of your VSCode workspace
2. You have installed the k8stools package into your workspace
3. The environment file .envrc contains any variables you need defined. In particular, you may need to set KUBECONFIG to point to your kubectl config file.

Use MCP with the streamable HTTP transport

The streamable http transport is enabled with the command line option --transport=streamable-http. It will start an HTTP server which listens on the specified address and port (defaulting to 127.0.0.1 and 8000, respectively). This transport is best for cases where you want remote access to your MCP server.

Here's a short example that starts the server and then does a sanity test using curl to get the tool information:

# start the server
 $ k8s-mcp-server --transport=streamable-http
[07/21/25 19:55:13] INFO     Starting with 6 tools on transport streamable-http           mcp_server.py:59
INFO:     Started server process [6649]
INFO:     Waiting for application startup.
INFO     StreamableHTTP session manager started         streamable_http_manager.py:111
INFO:     Application startup complete.
INFO:     Uvicorn running on http://127.0.0.1:8000 (Press CTRL+C to quit)

# Now, open another terminal window a test it
$ curl -v \
     -H "Content-Type: application/json" \
     -H "Accept: application/json, text/event-stream" \
     -d '{
           "jsonrpc": "2.0",
           "id": 1,
           "method": "tools/list",
           "params": {}
         }' \
     http://127.0.0.1:8000/mcp
*   Trying 127.0.0.1:8000...
* Connected to 127.0.0.1 (127.0.0.1) port 8000
> POST /mcp HTTP/1.1
> Host: 127.0.0.1:8000
> User-Agent: curl/8.7.1
> Content-Type: application/json
> Accept: application/json, text/event-stream
> Content-Length: 120
>
* upload completely sent off: 120 bytes
< HTTP/1.1 200 OK
< date: Tue, 22 Jul 2025 02:56:25 GMT
< server: uvicorn
< cache-control: no-cache, no-transform
< connection: keep-alive
< content-type: text/event-stream
< x-accel-buffering: no
< Transfer-Encoding: chunked
<
event: message
data: {"jsonrpc":"2.0","id":1,"result":{"tools":[.... long text elided ...]}}