secret-paste
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| request_secretA | Ask the user for an API key or other secret via a native password dialog (pinentry, zenity, kdialog, or a macOS dialog), falling back to a local browser page. The value is stored directly to the chosen target (.env in the working directory, the OS keychain, or 1Password) and never enters the conversation. Afterwards, reference it indirectly (e.g. process.env.NAME); never ask the user to paste secrets in chat. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
There is only one tool, so there is no possibility of misselection or overlap. Its purpose (securely obtain and store a secret without exposing it in chat) is unmistakable.
The single name request_secret follows a clear verb_noun convention and is self-descriptive. With one tool there is nothing to be inconsistent with.
The server is narrowly scoped to secret ingestion, so one tool is defensible, but it sits at the thin end of the range. A secret-management surface usually warrants at least a companion tool for checking, rotating, or removing stored secrets.
Writing a secret to .env, keychain, or 1Password is covered, but the lifecycle is a dead end: there is no way to verify a secret already exists, rotate it, or delete it. Agents must guess or re-prompt the user, which risks redundant dialogs and stale credentials.