# Elicitly (npm · elicitly)

Human-in-the-loop for AI agents over MCP elicitation: confirm/form dialogs plus a capability doctor

- Trust score: 95/100 (high trust)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- npm · `elicitly`: 95/100 (this document), [markdown](https://verifymcp.io/servers/ai-elicitly-elicitly/elicitly.md), [page](https://verifymcp.io/servers/ai-elicitly-elicitly/elicitly)

## Channel facts

- Registry: `npm`
- Package: `elicitly`
- Version: `0.7.2`
- 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 2026-09-20.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 95 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to elicitly/elicitly).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 12 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 86/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 554 tokens (~184/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**: 93/100
  - Stability observed for 28 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 3 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 Elicitly MCP server?

Elicitly runs locally as an npm package, launched with npx -y elicitly. 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 ai-elicitly-elicitly -- npx -y elicitly
```

### Cursor

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

### VS Code

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

### Codex

```bash
codex mcp add ai-elicitly-elicitly -- npx -y elicitly
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add ai-elicitly-elicitly --command npx --arg -y --arg elicitly
```

### Hermes

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

### Netclaw

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

### Vellum

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

### Other

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

## 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.

### 2026-09-20 (score 95, −1)

- [functional] Stability: pass → 0.93

### 2026-09-19 (score 96, 0)

- [security] Stability: 0.97 → pass

### 2026-09-18 (score 96, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-16 (score 95, −1)

- [functional] Stability: pass → 0.90

### 2026-09-15 (score 96, 0)

- [security] Stability: 0.97 → pass

### 2026-09-14 (score 96, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-12 (score 95, +1)

No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-11 (score 94, 0)

- [functional regression] Security disclosure: unverified → fail

## MCP tools (3)

### `elicit_confirm` (~187 tokens)

Ask the user to confirm (OK/Cancel)

Ask the user an OK/Cancel confirmation via elicitation (convenience wrapper over elicit_form), modeled on JavaScript's confirm(). Use this for a single yes/no question; use elicit_form to collect arbitrary fields. Returns three-state {confirmed}: true = proceed, false = a human explicitly said no, null = no answer was obtained (reason: "dismissed" | "error") — ask again later.

Input parameters:

- `labels` (object): Relabel or localize the OK/Cancel buttons. Each label is trimmed, 1-40 characters; unknown keys are rejected. Button placement and styling stay fixed.
- `message` (string, required): The yes/no question shown to the user in the host's elicitation dialog.
- `timeoutSeconds` (number): How long to wait for the answer, in seconds (default 300, clamped 60-3600).

Output parameters:

- `confirmed` (boolean|null): true = the user chose OK; false = an explicit no (Cancel choice or declined elicitation); null = no answer was obtained.
- `reason` (string): Present only when confirmed is null: "dismissed" = the elicitation was closed unanswered (including timeout), "error" = it failed.

### `elicit_doctor` (~170 tokens)

Diagnose the host's elicitation support

Check whether the connected MCP host actually supports elicitation (and sampling/roots) before relying on it — advertising a capability is not the same as it working. Use it to decide whether to call elicit_form/elicit_confirm, to explain why a prompt did or didn't appear, or to contribute a host capability fingerprint. Returns a passive report derived from the initialize handshake; set probeElicitation: true to also run one live form round-trip (the user may see a dialog) and classify what really happened. Read-only; safe to call anytime.

Input parameters:

- `probeElicitation` (boolean): Also fire one live form-elicitation round-trip (the user may see a dialog) and report the outcome under probes.elicitationForm. Default false: passive capability report only, no prompt.

Output parameters:

- `deprecations` (array): Spec-level deprecation advisories (MCP 2026-07-28, SEP-2577) for the client features the report surfaces.
- `initialize` (object): The MCP initialize handshake echoed verbatim: { request: { clientInfo, capabilities }, response: { protocolVersion, capabilities, serverInfo } }.
- `probes` (object): Present only when probeElicitation was true: the live round-trip's attempted/action/latencyMs/verdict.
- `support` (object): Elicitly's derived support booleans, inferred from the advertised capabilities.

### `elicit_form` (~197 tokens)

Ask the user to fill a form

Trigger a form elicitation with a caller-supplied JSON schema; returns the raw {action, content}. For a plain OK/Cancel question, prefer elicit_confirm. MUST NOT be used to request secrets, credentials, or other sensitive information.

Input parameters:

- `message` (string, required): The instruction shown to the user above the form fields.
- `requestedSchema` (object, required): JSON Schema for the form, restricted to the MCP elicitation requestedSchema subset: a flat object whose properties are strings, numbers/integers, booleans, or enums — no nested objects, arrays of obj…
- `timeoutSeconds` (number): How long to wait for the answer, in seconds (default 300, clamped 60-3600) — raise it for forms with several fields.

Output parameters:

- `action` (string): accept = the user submitted the form; decline = an explicit no; cancel = dismissed unanswered (including timeout); error = the elicitation failed.
- `content`: On accept, the submitted values keyed by requestedSchema property name; null for every other action.

## Diagnostics

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

## Score history

- 2026-09-20: 95
- 2026-09-19: 96
- 2026-09-18: 96
- 2026-09-17: 95
- 2026-09-16: 95
- 2026-09-15: 96
- 2026-09-14: 96
- 2026-09-13: 95
- 2026-09-12: 95
- 2026-09-11: 94
- 2026-09-10: 94
- 2026-09-09: 93
- 2026-09-08: 93
- 2026-09-07: 93
- 2026-09-06: 66
- 2026-09-05: 91
- 2026-09-04: 88
- 2026-09-03: 88
- 2026-09-02: 87
- 2026-09-01: 87
- 2026-08-31: 86
- 2026-08-30: 86
- 2026-08-29: 85
- 2026-08-28: 85
- 2026-08-27: 85
- 2026-08-26: 84
- 2026-08-25: 82
- 2026-08-24: 82
- 2026-08-23: 81
- 2026-08-22: 81

## Common questions

### What is the Elicitly MCP server?

Elicitly is an MCP server listed in the public MCP registry as ai.elicitly/elicitly. Human-in-the-loop for AI agents over MCP elicitation: confirm/form dialogs plus a capability doctor. This page covers its npm package (elicitly).

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

Elicitly scores 95 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 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 Elicitly MCP server expose?

Elicitly exposes 3 tools: elicit_confirm, elicit_doctor, elicit_form. Their descriptions and schemas cost roughly 554 tokens of context every time the server is loaded.

### Is the Elicitly MCP server still maintained?

Elicitly is still listed as active in the MCP registry. We last reached this channel on 20 September 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 Elicitly MCP server under?

Elicitly declares the Apache-2.0 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/elicitly
- Socket report: https://socket.dev/npm/package/elicitly
- Repository: https://github.com/elicitly/elicitly
- Website: https://www.elicitly.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-elicitly-elicitly/elicitly.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-elicitly-elicitly/elicitly.json
- HTML version of this page: https://verifymcp.io/servers/ai-elicitly-elicitly/elicitly