MCP server

MCP tools and permissions

This reference lists Plous's agent tools. For a guided setup, use plous-debug or the assistant panel.

Available tools

Standalone setup names its server   plous_debug  . The panel normally uses   plous  , with a suffix in Codex if needed. The built-in agent uses the same tool implementations.

Task

Tools

Results

Inspect objects

  kubernetes_resources_read  ,   helm_releases_read  ,   argo_resources_read  ,   flux_resources_read

Resources, releases, controller status

Read Helm configuration

  helm_configuration_read

Filtered values, manifests, hooks

Read logs

  kubernetes_logs_read

Pod or workload log excerpts

Run diagnostics

  kubernetes_exec_run  ,   kubernetes_diagnostic_run

Explicitly enabled commands or temporary tests

Read usage

  kubernetes_usage_read

Current Pod, Node, or workload usage and budgets

Compare Helm revisions

  helm_diff_read

Differences between stored revisions

Read app records

  workspace_read  ,   history_read

Workspace and Activity data, saved messages and evidence

Open Plous views

  ui_read  ,   kubernetes_show  ,   helm_show  ,   history_show

Current view information and navigation results. Panel sessions only.

  _read   tools return information.   _show   tools open a view.   _run   tools can change cluster or application state.

Argument rules:

  •   kubernetes_logs_read  ,   kubernetes_usage_read  , and   helm_diff_read   take no   operation   argument.

  •   kubernetes_show   accepts   view=resource  ,   list  , or   logs  .

  • Other show tools take no   view   argument.   helm_show   opens revision comparisons, not release lists.

  • For Helm comparisons,   revision   is the after revision and   compare_revision   is the before revision.

Calls include a purpose and use the session's connection identity. Supplying another identity does not grant access. Integration-owned schemas validate arguments before execution. See the tool registry and history implementation.

Monitor evidence

All integrations use the same selected cluster. Their statuses describe different things. A Helm release record or controller's Ready condition does not prove current Pod health.

Tool

Important limits

  kubernetes_usage_read

Reads current metrics without opening a chart. Reports times, missing measurements, and completeness. Cannot recover unsaved chart history.

  kubernetes_logs_read

Requires a Pod or supported workload and an explicit container. Reads at most 16 Pods, 500 lines per Pod, and 64 KiB combined. Reports failed or skipped Pods.

  helm_diff_read

An explicit comparison needs two distinct positive stored revisions. Otherwise it compares with the predecessor. Revision 1 uses an empty baseline.

Workload logs follow controller ownership and check Pod identities before and after collection. Excerpts are not complete log history.

See the Kubernetes, Helm, Argo CD, and Flux guides for integration details.

Historical evidence

History contains results that were saved. It is not a continuous archive of resource contents. A current read cannot recover a value that was never recorded.

Search matches identify candidate records, not resource counts. Counts and comparisons report incomplete or unknown inputs.

Active diagnostics

Enable these through diagnostic setup. Both require a purpose, the selected Kubernetes   connection_id  , and its default   namespace  .

Tool

Required inputs

Behavior

  kubernetes_exec_run

Pod   name  , exact   uid  ,   container  , and   command   argument array

One command in an existing container. No added shell, stdin, or TTY.

  kubernetes_diagnostic_run

`test=http

dns

  timeout_seconds   defaults to 30 and accepts 1–120. Output is limited to 64 KiB. Temporary cleanup can take another 10 seconds.

HTTP targets need a full HTTP(S) URL without embedded credentials. Tests do not follow redirects or retry.

Plous records requests before running them and saves results before returning them. A transport or storage failure must not cause an automatic retry of an operation that may already have changed state.

Scope and delivery

A session keeps the cluster it started with. Reads may use any namespace allowed by those Kubernetes credentials. Diagnostic operations stay in the configured default namespace.

General chat and history-only views have no live cluster tools. To change a standalone target, reconnect. To change the panel's target, close and reopen its session.

Plous validates and serializes calls, then saves results before delivery. Fatal storage, history, or target errors disable further tool access. A native CLI remains open so you can inspect the error.

Native sessions have no Plous-imposed process deadline or session-wide tool-call cap. The CLI manages model calls and spending. Built-in agent budgets are described in Configuration.

MCP connection details

Mode

Transport

Configuration

Standalone

Newline-delimited stdin/stdout, with no listening port

Inside Plous

Temporary loopback HTTP endpoint with a per-session bearer token

Automatic. Ends when the native session closes.

Do not copy the panel's endpoint or token into global client settings.

The local MCP connection does not make model inference local. Cluster data can go to the CLI's configured provider.

Plous view tools preserve focus and edits. They return   opened  ,   blocked  , or   failed   and do not send keystrokes or write resources. Their navigation results are stored separately from searchable cluster evidence.

See AI implementation for the adapter and tool contracts.

Protocol behavior

Property

Support

Protocol

JSON-RPC 2.0, one request per message

Authentication

Panel HTTP uses a fresh bearer token and rejects Origin headers. Stdio uses subprocess pipes.

Initialization

Protocol version   2025-03-26  , tools capability

Requests

  initialize  ,   ping  ,   tools/list  ,   tools/call

Notifications

  notifications/initialized  , plus cancellation of a matching active request

Discovery

Tool descriptions, schemas, and read/diagnostic annotations

Results

Text content. View tools return navigation results.

Other features

No resources or prompt templates

Request IDs must be strings or integers. A tool-call ID cannot be reused in the same session. Inspect tool content for errors even when transport succeeds.

Unsupported methods return JSON-RPC errors. After a fatal tool failure, later calls receive a closed-session response.

Schemas use an object root with operation-specific constraints under   dependentSchemas  . See the bridge, launch configuration, and client checks for implementation details.

View source

Plous · Open source · Early development

Search Plous docs

Search the documentation.

Documentation versions