Skip to main content
Glama

Control Plane

by io.cpln

Build an Image from a Git Repository

build_image
Destructive

Build a container image on Control Plane from a GitHub or GitLab repository and push it to the org's private registry. No Docker daemon is involved: the service clones the repo, detects how to build it (Dockerfile when present), and always produces linux/amd64. Returns a buildId to read with get_image_build — the build keeps running after this call returns. ONLY repositories work here. To build a LOCAL FOLDER, tell the user to run cpln image build --remote --dir PATH --name NAME:TAG in their terminal — this server has no access to their filesystem. Building an existing NAME:TAG replaces that image. A private repository needs a one-time browser authorization per org; this tool returns the link when that is missing. Recommended reading before first use: get_cpln_skill("image") — the runbook for this tool family (read once per session).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
orgYesOrganization slug (lowercase kebab-case). NEVER guess — if the user has not named one, ask. On org-not-found, stop and ask; do not retry variants.
tagYesTag for this build, e.g. "v1.2.0". Required — there is no default. Building an EXISTING tag REPLACES it, and any workload on that tag with dynamic-tag support redeploys onto the new image. Prefer a fresh tag.
nameYesImage name WITHOUT the tag, e.g. "my-app". The result is referenced in a workload as //image/NAME:TAG.
branchNoBranch to build. Omit for the repository's default branch.
noCacheNoRebuild every step, ignoring cached layers. Slower — only when a cached layer is suspect.
repoUrlYesHTTPS URL of the repository to build, e.g. "https://github.com/acme/api". GitHub and GitLab only. SSH remotes and URLs with embedded credentials are rejected. A private repo needs a one-time browser authorization per org, which this tool returns a link for.
connectNonceNoOnly when retrying after the user authorized the git provider: echo this tool's previous `connectNonce` verbatim.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
okYesWhether the call succeeded.
dataNoThe full machine-readable result — list rows, the resource object, query results. Read THIS, not just the summary.
summaryYesOne-line summary of the result.
nextStepsNoRecommended follow-up actions for this task, in order.

TDQS

A4.7/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds substantial behavioral context beyond the annotations: no Docker daemon involved, always produces linux/amd64, returns a buildId with the build running asynchronously, building an existing NAME:TAG replaces it, and private repos need one-time browser authorization. This complements the destructiveHint/openWorldHint annotations without contradicting them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Each sentence adds distinct information: action, no-docker, async, overwrite semantics, auth, local-folder alternative, and recommended reading. No fluff; the structure is logical and front-loaded with the core purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex, destructive, asynchronous tool with 7 parameters and an output schema, the description covers all key user-need areas: what it does, how it works, side effects, failure/alternative paths (local folder), and prerequisite reading. The existence of an output schema reduces the need to describe return values, and this description still mentions buildId.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with detailed per-parameter descriptions, so the description is not required to compensate. It provides general build context (e.g., 'detects how to build it') but does not add parameter-specific meaning beyond what the schema already states for each field.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Build a container image on Control Plane from a GitHub or GitLab repository and push it to the org's private registry.' It clearly distinguishes from siblings like get_image_build by stating this is the build action and even clarifies 'ONLY repositories work here.'

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when not to use this tool: 'To build a LOCAL FOLDER, tell the user to run `cpln image build --remote --dir PATH --name NAME:TAG`... this server has no access to their filesystem.' It also directs the user to get_cpln_skill('image') for runbook guidance and explains the private-repo auth flow.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Control Plane toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0
Disambiguation5/5

Every tool targets a distinct resource/action pair (e.g., get_resource vs get_resource_schema, list_deployments vs list_workload_replicas) and descriptions clearly differentiate purposes. No two tools appear to do the same thing.

Naming Consistency5/5

All tools follow a verb_noun snake_case pattern (create_gvc, update_workload, list_resources, query_metrics) with consistent verbs. The few imperative verbs (browse, build, mount) still maintain the same verb-first structure.

Tool Count1/5

With 55 tools, this server far exceeds the typical well-scoped 3-15 tool range. While each tool appears purposeful, the sheer number creates selection overhead and falls into the extreme 50+ category on the rubric.

Completeness4/5

The surface covers nearly the full Control Plane lifecycle: CRUD for GVC, workload, identity, policy, volumeset, and domain, plus observability, templates, image builds, and Terraform. Minor gaps include referenced but missing configure_workload_* tools and no secret creation/deletion (by design).

Resources