Skip to main content
Glama
Sign In

Ankra

by ai.ankra
OverviewDiscussionsAdmin

Elevate cluster access

elevate_cluster_access
Destructive

Break-glass: give yourself - the caller, never anyone else - time-boxed Kubernetes access to one cluster (the twin of ankra cluster access elevate). Needs kube_access.elevate or kube_access.manage, and is always held to the organisation access policy's self-elevation bounds, whoever calls it: it must expire within the policy's elevated lifetime, carry a reason when the policy requires one, and stay under the role ceiling. Only your own elevation is re-timed by a repeat. Always have the user confirm the cluster, role, lifetime and reason first.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "role": "<role>"
    },
    "name": "elevate_cluster_access"
  }
}

Input Schema

NameRequiredDescriptionDefault
roleYesKubernetes role the grant carries; must not exceed the organisation access policy's max_grant_role (get_cluster_access_policy).
scopeNocluster (default) for the whole cluster, namespace for one namespace.
reasonNoWhy the access is needed. The organisation access policy may require it for elevated roles (require_reason_from_role).
namespaceNoThe namespace, required with scope namespace and refused otherwise (a DNS-1123 label).
cluster_idNoUUID of the cluster. Optional when a cluster is selected.
expires_atNoWhen the grant ends, an RFC 3339 timestamp at least a minute ahead. Give this or expires_in.
expires_inNoHow long the grant lasts: whole days (7d) or a duration (30m, 4h, 1h30m), at least 1m. Give this or expires_at.
cluster_nameNoExact name of the cluster. Optional when a cluster is selected.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Goes well past the annotations: it discloses the permission requirements, that the grant is always bounded by the organisation access policy (lifetime ceiling, required reason, max role), and that a repeat call re-times the existing elevation rather than stacking a second one — important given idempotentHint=false. That last detail is exactly the kind of behavior an agent cannot infer from destructiveHint/readOnlyHint alone.

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?

One front-loaded paragraph that opens with the 'Break-glass' framing and then layers permissions, policy bounds and the confirmation step. Every clause carries information — no filler, no restatement of the title.

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

Completeness4/5

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

For an 8-parameter privileged mutation with no output schema, it covers permissions, policy limits, repeat-call behavior and the human-confirmation requirement. It does not say what the response contains (grant id, expiry, kubeconfig retrieval) or how this interacts with an already-existing elevation of a different role, which an agent would want before calling.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds real cross-parameter meaning: expires_at/expires_in must fall inside the policy's elevated lifetime, role must stay under the role ceiling, and reason becomes mandatory at a policy-defined threshold. It does not restate the expires_at vs expires_in exclusivity, but that is already in the schema.

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?

States a specific verb and resource ('give yourself ... time-boxed Kubernetes access to one cluster') and pins the scope tightly with 'the caller, never anyone else'. It also maps itself to the CLI equivalent (`ankra cluster access elevate`), which makes it immediately distinguishable from grant_cluster_access and revoke_cluster_access.

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?

Use context is clear: break-glass self-elevation, gated on kube_access.elevate or kube_access.manage, plus an explicit operational rule to have the user confirm cluster, role, lifetime and reason before calling. It stops short of naming the sibling tools (grant_cluster_access for others, revoke_cluster_access to end it) as explicit alternatives, so the routing is implied rather than spelled out.

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

All Ankra toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources