Skip to main content
Glama

Control Plane

by io.cpln

Create a Policy

create_policy

Create a new policy with target kind, optional target scopes (targetAll/targetLinks/targetQuery), and principal bindings (addPermissions plus at least one principal list — one without the other is an error). Target scopes may be combined; targetAll wins because target="all" applies the policy to every resource. Recommended reading before first use: get_cpln_skill("access-control") — 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.
nameYesResource name (lowercase kebab-case, starts with a letter, 2-64 chars). Names are IMMUTABLE — renaming = delete + recreate (loses URL, DNS, policy links).
tagsNoOptional tags for the policy (behave like Kubernetes labels for selectors and compliance).
addUsersNoUser links to add (e.g., ["//user/alice"])
addGroupsNoGroup links to add
targetAllNoSet to true to target all resources of the kind. Pick the target scope that matches intent (combining scopes is legal; target=all wins).
targetKindYesTarget resource kind (e.g., "secret", "workload", "identity"). Only the kinds listed by get_permissions have meaningful permission schemas — confirm permission names there before binding.
descriptionNoPolicy description
targetLinksNoTarget resource links (e.g., ["//secret/my-secret"]). GVC-scoped kinds (workload/identity/volumeset/dbcluster) need the gvc segment: //gvc/GVC/workload/NAME. Pick the target scope that matches intent (combining scopes is legal; target=all wins).
targetQueryNoDynamically target resources matching a query (e.g. all secrets tagged env=prod). Pick the target scope that matches intent (combining scopes is legal; target=all wins).
addIdentitiesNoIdentity links to add (e.g., ["//gvc/my-gvc/identity/my-identity"]). Identities are GVC-scoped — the gvc segment is required.
addPermissionsNoPermissions to grant (e.g., ["reveal", "use"]). For the full list run get_permissions. Secret values need `reveal`, not `read`.
addServiceAccountsNoService account links to add (e.g., ["//serviceaccount/sa-1"])

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

A4.5/5.0
Behavior4/5

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

The description adds meaningful behavioral context beyond the annotations: combining target scopes is legal, targetAll wins because target='all' applies to every resource, and addPermissions without a principal list is an-error. It also recommends get_cpln_skill('access-control') as the runbook before first use, which helps the agent anticipate prerequisite knowledge.

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?

The description is three focused sentences: it fronts the primary purpose, then concisely covers high-risk constraints, and ends with a useful, specialized reference to get_cpln_skill. No redundant text fills the description.

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?

Given 13 parameters, nested targetQuery, another output schema, and nested objects, this description is strong because it efficiently highlights the most decision-heavy parts, points to get_cpln_skill for runbook context, and points to get_permissions for valid permission names. The generous schema coverage and output schema make additional detail unnecessary.

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

Parameters4/5

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

Although the schema already covers 100% of the parameter descriptions, the description adds relationship-level semantics by grouping addPermissions with principal lists and explaining the mutual requirement. It also clarifies targetAll's precedence over other target scopes, which is not immediately obvious by reading the schema alone.

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 'Create a new policy' and specifies the core elements: target kind, target scopes, and principal bindings. This clearly distinguishes it from sibling update_policy and other resource-creation tools by naming both the verb, resource, and key scope.

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

Usage Guidelines4/5

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

The description gives clear field guidance for when to use this tool and explains key constraints: target scopes may combine, targetAll wins, and principal bindings require addPermissions plus at least one principal list. It does not explicitly contrast using create_policy versus update_policy, but the 'Create a new policy' action and sibling context make that implied.

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