Skip to main content
Glama
This connector has been deprecated

Replaced by Control Plane.

This listing has been renamed. Control Plane is now listed as com.controlplane/mcp.

It is the same server at the same endpoint (https://mcp.cpln.io/mcp), so existing connections keep working. Please use the new listing going forward.

Create a Secret

create_secret
Idempotent

Create an org-scoped secret whose values never pass through this chat. With values "generate", Control Plane fills dictionary keys or an opaque payload with random values now. With values "user", returns a Console link prefilled with the name, type, keys, and defaults for keys whose values are not secret, where the user types the rest. No input accepts a secret value and no result contains one. Databases through add_database get their credentials without this tool. A workload reads a key as cpln://secret/NAME.KEY; deploy_app grants the access, grant_workload_secret_access does it for an existing workload.

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": {
      "name": "<name>",
      "type": "<type>",
      "values": "<values>"
    },
    "name": "create_secret"
  }
}

Input Schema

NameRequiredDescriptionDefault
orgNoOrganization slug.
keysNoDictionary key names. Required to generate a dictionary. For "user", prefills the Console form with these keys.
nameYesName for the new org-scoped secret. Pass the name only; names are immutable.
typeYesSecret type. Generated values support "dictionary" (one value per key) and "opaque" (one payload).
lengthNoGenerated value length in characters (default 32). Only with values "generate".
valuesYesWho supplies the values. "generate": Control Plane fills them with random values now and nobody sees them, for values nobody needs to know (database passwords, signing and session keys, internal tokens). "user": returns a Console link where the user types them, for values only the user has (third-party keys, existing credentials, certificates). Nothing is created in "user" mode until the user saves the form.
charsetNoGenerated value alphabet (default "alphanumeric", which is safe in connection strings). Only with values "generate".
defaultsNoOnly with values "user" and a dictionary: starting values the form fills in for some of keys, which the user can change before saving. Only values that are not secret, such as a host, port, username, region, or mode.
descriptionNoOptional description shown on the secret.

Output Schema

NameRequiredDescriptionDefault
okYes
dataNoThe full result. Read this, not only the summary.
detailsNo
summaryYes
nextStepsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / defaults
      Added value: +{
      +  "additionalProperties": {
      +    "type": "string"
      +  },
      +  "description": "Only with values \"user\" and a dictionary: starting values the form fills in for some of keys, which the user can change before saving. Only values that are not secret, such as a host, port, username, region, or mode.",
      +  "propertyNames": {
      +    "pattern": "^[-._a-zA-Z0-9]+$"
      +  },
      +  "type": "object"
      +}
  2. Added

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false; the description adds the critical non-obvious behaviors: no input accepts a secret value, no result contains one, and in 'user' mode nothing is created until the user saves the Console form. It also documents the cpln://secret/NAME.KEY read path, which annotations cannot convey. Minor gap: it doesn't restate that create is idempotent by name.

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

Conciseness4/5

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

Front-loaded with the core constraint and organized as mode-by-mode explanation, then access-control follow-ups. Dense long sentences (e.g., the 'user' sentence packs mode, link contents, and save requirement), but nothing is filler.

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?

With 9 parameters, 3 required, nested 'defaults', and an output schema present, the definition covers the security model, both modes, the Console-link return, and the access-granting siblings - everything needed to call it correctly without guessing.

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; the description goes beyond it by explaining the semantics of the 'values' enum at the mode level and clarifying that databases are handled elsewhere (relevant to 'type'). It adds less for length, charset, defaults and description, which the schema already fully documents.

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 (create an org-scoped secret) plus its defining constraint that values never pass through the chat. Distinguishes itself from add_database, rotate_secret, deploy_app, and grant_workload_secret_access by name, so an agent can route without inspecting schemas.

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 splits the two modes: 'generate' for values nobody needs to know, 'user' for values only the user has, and states neither creates the secret value here. Also names the exclusions ('Databases through add_database get their credentials without this tool') and the follow-up tools for granting access.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.