Secret Store

Request access

request_access

Ask the user for access this token does not have: another environment (production, for example), an extra scope, keys outside the token's allow-list, or protected items. Nothing is granted by calling this: it returns an approveUrl the user must open to approve (with a second factor) or deny. Ask for the narrowest thing that does the job. A client that speaks MCP tasks (protocol 2025-11-25) may call it as a task and poll tasks/get until the user decides.

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": {
      "project": "<project>",
      "scopes": "<scopes>",
      "reason": "<reason>"
    },
    "name": "request_access"
  }
}

Input Schema

Name	Required	Description	Default
`keys`	No	Only these secret keys (default: every key). Prefer naming them
`reason`	Yes	One sentence the user will read: what you are doing and why you need this
`scopes`	Yes	Scopes needed, e.g. ["secrets:read"]
`project`	Yes	Project slug or id
`duration`	No	once = a single tool call; or a window of 15m, 1h or 8h. The user can change it	once
`environment`	No	Environment slug or id. Leave out only when the whole project is needed (saved logins and project files hang off the project)
`include_protected`	No	Also open protected items (default false). The user can only open what they are on the unlock list for

Output Schema

Name	Required	Description
`next`	Yes
`asked`	Yes
`status`	Yes
`request`	Yes
`answerBy`	Yes	ISO 8601 timestamp
`approveUrl`	Yes	Show this to the user; they decide there

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.7/5.0

Behavior5/5

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

Annotations only declare that this is a non-destructive, non-idempotent, non-read-only call; the description adds the crucial behavior that nothing is granted on invocation and an approveUrl must be opened by the user with a second factor, who may deny. It also discloses the async task path (tasks/get polling under protocol 2025-11-25), which is exactly the kind of context annotations cannot carry.

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?

Four sentences, front-loaded with what the tool does, then the critical 'nothing is granted' consequence, then the narrowest-ask rule, then the async note. Every sentence changes how an agent would call the tool; no 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?

For a 7-parameter, 3-required mutation with an output schema, the description covers the trigger, the consent flow, denial, the approval artifact, and the task-polling mode. Return-shape detail is correctly left to the output schema, and nothing an agent needs before calling is missing.

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 a governing least-privilege principle that shapes how scopes, keys, and duration should be chosen, and clarifies that requested keys are ones outside the token's allow-list. That is real decision guidance beyond the field descriptions, though it does not annotate individual parameters.

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 ('Ask the user for access this token does not have') and then enumerates the exact request kinds: another environment, an extra scope, keys outside the allow-list, protected items. That enumeration lets an agent tell this apart from read-side siblings like check_keys or whoami without opening a schema.

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?

Gives a clear trigger (the token lacks the access needed) and an explicit selection rule for how much to ask for ('Ask for the narrowest thing that does the job'), plus a parameter-level rule to omit environment only when the whole project is needed. It does not say to first verify existing access with a sibling or name check_access_request as the status-check alternative, so it stops short of full when/when-not routing.

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

All Secret Store tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?