# offprompt (npm · offprompt)

Ask the human for API keys in a browser page and write them to .env. The model only sees key names.

- Trust score: 89/100 (high trust)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- npm · `offprompt`: 89/100 (this document), [markdown](https://verifymcp.io/servers/offprompt-offprompt/offprompt.md), [page](https://verifymcp.io/servers/offprompt-offprompt/offprompt)

## Channel facts

- Registry: `npm`
- Package: `offprompt`
- Version: `0.3.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-04.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to offprompt/offprompt).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 4 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 60/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1817 tokens (~605/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 70/100
  - Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the offprompt MCP server?

offprompt runs locally as an npm package, launched with npx -y offprompt. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add offprompt-offprompt -- npx -y offprompt
```

### Cursor

```json
{
  "mcpServers": {
    "offprompt-offprompt": {
      "command": "npx",
      "args": [
        "-y",
        "offprompt"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "offprompt-offprompt": {
      "command": "npx",
      "args": [
        "-y",
        "offprompt"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add offprompt-offprompt -- npx -y offprompt
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "offprompt-offprompt": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "offprompt"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add offprompt-offprompt --command npx --arg -y --arg offprompt
```

### Hermes

```yaml
mcp_servers:
  offprompt-offprompt:
    command: "npx"
    args: ["-y", "offprompt"]
```

### Netclaw

```json
{
  "McpServers": {
    "offprompt-offprompt": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "offprompt"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add offprompt-offprompt -t stdio -c npx -a -y offprompt
```

### Other

```json
{
  "mcpServers": {
    "offprompt-offprompt": {
      "command": "npx",
      "args": [
        "-y",
        "offprompt"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 89, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 88, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 87, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-31 (score 72, −14)

- [security regression] Malware scan: pass → unverified
- [functional] Package version: 0.3.0 → 0.3.1

### 2026-10-29 (score 86, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 85, 0)

- [security regression] Stability: 0.43 → unverified
- [security regression] Tool safety: pass → unverified
- [functional regression] Schema quality: 505 → 583
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] Package version: 0.2.0 → 0.3.0

### 2026-10-27 (score 85, 0)

- [functional] Package version: 0.1.3 → 0.2.0

### 2026-10-26 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (3)

### `collect_secret` (~1323 tokens)

Collect a secret from the human

Get the values a task needs — API keys, tokens, connection strings, settings — written
where the project reads them, typed by the human or generated by offprompt. Call this instead of asking the user to paste
a secret into the conversation.

Each entry in `secrets` is one key, and says how its value comes to be:
\- `generate: {}` — a random value, 32 bytes of base64url unless set, made on the user's page (or by offprompt when no
  page opens); the user may paste one they already use instead. You never see it. For AUTH_SECRET, JWT_SECRET,
  SESSION_SECRET and encryption keys. A key that is already set is kept as it is.
\- `provider` — a key the human gets from a provider, such as `provider: "stripe"` for STRIPE_SECRET_KEY. The page
  shows the provider's logo and links to where the key is made.
\- `format` — a value of a known kind that no one provider issues, such as `format: "postgres_url"` for DATABASE_URL.
  The page links to providers where the human can create one.
\- none of these — any other value, taken as plain text. A provider's key is still recognised by its usual name.
Set `secret: false` on a value that is not secret, such as MAX_RETRIES, and the page shows it in the clear.

Give an entry a `link` when you know where its value is made, so the human lands on the right page:
\- Some provider keys are made on a page that belongs to one account, organisation or project. Give that one's name or ID
  as parameters, such as `link: { "project": "abcdefghijklmnopqrst" }` for a Supabase key, and the page's "Get it"
  opens it. The `link` field lists the keys that take them and where a project keeps each value: read it from there
  rather than guessing. A parameter that is missing or does not fit leaves "Get it" on the key's usual page.
\- A key no provider issues, such as an internal tool's token, takes the https address where it is made. The page shows it
  as your suggestion, apart from offprompt's own links, and asks the human to confirm its host before it opens. A…

Input parameters:

- `reason` (string, required): Why the values are needed, written for the human and shown on the page as your claim. Markdown is rendered: bold, italics, code, lists, quotes. Links show their address as text and are not clickable.
- `sandbox` (boolean): true only when your environment tells you that you run in a cloud sandbox, a container or a remote VM, where a browser would open on a screen the user cannot see. Not a temporary folder or a run nobo…
- `secrets` (array, required): Every key you need, in one request. The human fills them on one page and can paste them all at once.
- `sink` (required): Where the values are written. Fixed now and not re-read from the page.

Output parameters:

- `emoji` (string): A fingerprint of the values as the file holds them. The user's page shows the four it took from what they typed. Write them to the user as soon as the call returns, before your next tool call.
- `expires_in` (number)
- `file_keys` (array): Every key the file holds after the write, names only, so the file never needs opening.
- `kept` (array)
- `links` (array): What became of each link you gave: used as the key's "Get it" or shown as your suggestion, with the address the page opens, or dropped, with why.
- `names` (array)
- `note` (string)
- `request_id` (string)
- `sink` (object)
- `status` (string)
- `tell_user` (string): The line to write to the user as soon as the call returns, before your next tool call: "Fingerprint" and the four emoji their page shows.
- `url` (string): The page the user has to open, while the request is awaiting and the link is yours to pass on.
- `written_anyway` (array): Keys the user wrote although their values did not pass offprompt's checks: the provider may have changed the format, or the value may be wrong.

### `await_secret` (~172 tokens)

Wait for a secret to be written

Wait for a collect_secret request that came back still "awaiting" — which happens when
offprompt runs in a cloud sandbox, had no browser to open and handed you the page URL to pass on, or runs in a host that
ends a tool call before the human is done. Long-polls for up to 60 seconds, 50 in Cline, and returns
"written", "awaiting" or "expired". Call it again while the status is "awaiting", with no other work in between. When
you were given a link to pass on, an "awaiting" result carries it again: keep it in whatever you write to the user, or
ask them, until the values are written.

Input parameters:

- `request_id` (string, required): The request_id returned by collect_secret.

Output parameters:

- `emoji` (string): A fingerprint of the values as the file holds them. The user's page shows the four it took from what they typed. Write them to the user as soon as the call returns, before your next tool call.
- `file_keys` (array): Every key the file holds after the write, names only, so the file never needs opening.
- `kept` (array)
- `names` (array)
- `note` (string)
- `request_id` (string)
- `sink` (object)
- `status` (string)
- `tell_user` (string): The line to write to the user as soon as the call returns, before your next tool call: "Fingerprint" and the four emoji their page shows.
- `url` (string): The page the user has to open, while the request is awaiting and the link is yours to pass on.
- `written_anyway` (array): Keys the user wrote although their values did not pass offprompt's checks: the provider may have changed the format, or the value may be wrong.

### `cancel_secret` (~44 tokens)

Cancel a secret request

Close a collect_secret request that is no longer needed. Anything already typed on the
page is discarded.

Input parameters:

- `request_id` (string, required): The request_id returned by collect_secret.

Output parameters:

- `emoji` (string): A fingerprint of the values as the file holds them. The user's page shows the four it took from what they typed. Write them to the user as soon as the call returns, before your next tool call.
- `file_keys` (array): Every key the file holds after the write, names only, so the file never needs opening.
- `kept` (array)
- `names` (array)
- `note` (string)
- `request_id` (string)
- `sink` (object)
- `status` (string)
- `tell_user` (string): The line to write to the user as soon as the call returns, before your next tool call: "Fingerprint" and the four emoji their page shows.
- `url` (string): The page the user has to open, while the request is awaiting and the link is yours to pass on.
- `written_anyway` (array): Keys the user wrote although their values did not pass offprompt's checks: the provider may have changed the format, or the value may be wrong.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/offprompt-offprompt/offprompt#diagnostics

## Score history

- 2026-11-04: 89
- 2026-11-03: 88
- 2026-11-02: 88
- 2026-11-01: 87
- 2026-10-31: 72
- 2026-10-30: 86
- 2026-10-29: 86
- 2026-10-28: 85
- 2026-10-27: 85
- 2026-10-26: 85
- 2026-10-25: 84
- 2026-10-24: 84
- 2026-10-23: 83
- 2026-10-22: 83
- 2026-10-21: 82
- 2026-10-20: 82
- 2026-10-19: 81
- 2026-10-18: 81
- 2026-10-17: 80
- 2026-10-16: 80
- 2026-10-15: 68
- 2026-10-14: 79
- 2026-10-13: 50
- 2026-10-12: 50
- 2026-10-08: 50

## Common questions

### What is the offprompt MCP server?

offprompt is an MCP server listed in the public MCP registry as io.github.offprompt/offprompt. Ask the human for API keys in a browser page and write them to .env. The model only sees key names. This page covers its npm package (offprompt).

### Is the offprompt MCP server safe to use?

offprompt scores 89 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the offprompt MCP server expose?

offprompt exposes 3 tools: collect_secret, await_secret, cancel_secret. Their descriptions and schemas cost roughly 1,539 tokens of context every time the server is loaded.

### Is the offprompt MCP server still maintained?

offprompt is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the offprompt MCP server under?

offprompt declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/offprompt
- Socket report: https://socket.dev/npm/package/offprompt
- Repository: https://github.com/offprompt/offprompt
- Website: https://offprompt.dev/
- Changelog RSS feed: https://verifymcp.io/servers/offprompt-offprompt/offprompt.xml
- Changelog JSON feed: https://verifymcp.io/servers/offprompt-offprompt/offprompt.json
- HTML version of this page: https://verifymcp.io/servers/offprompt-offprompt/offprompt