mcpField
E
Elicitly

Elicitly

Local
elicitly.aiAI & Agents1Updated 4d ago

About Elicitly

Elicitly is an open-source local MCP server and toolkit for adding human input to agent prompts and skills. It provides confirmation and form dialogs, plus a diagnostic for checking host support for elicitation.

Key features

  1. 01Confirmation dialogs
  2. 02Schema-based forms
  3. 03Host elicitation diagnostics
  4. 04Inline LiquidJS templates
  5. 05Embeddable elicitation toolkit

Use cases

  1. 01Ask a person to approve an agent action
  2. 02Collect structured answers during a workflow
  3. 03Check whether an MCP host supports elicitation

MCP support

Elicitly exposes elicitation tools through a local stdio MCP server. The @elicitly/tools package also lets developers register those tools on their own McpServer.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"ai-elicitly-elicitly": {
"command": "npx",
"args": [
"-y",
"elicitly"
]
}
}
}
Run commandnpx -y elicitly

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmelicitly0.8.4

Tools

4

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
labelsobjectNoRelabel or localize the OK/Cancel buttons. Each label is trimmed, 1-40 characters; unknown keys are rejected. Button placement and styling stay fixed.
labels.okstringNoReplacement label for the OK button (e.g. "Aceptar").
labels.cancelstringNoReplacement label for the Cancel button (e.g. "Cancelar").
messagestringYesThe yes/no question shown to the user in the host's elicitation dialog.
timeoutSecondsnumberNoHow long to wait for the answer, in seconds (default 300, clamped 60-3600).

Details

From the project README

Elicitly — Free Edition

npm — elicitly npm — @elicitly/tools Docs License: Apache-2.0 CI Coverage
elicitly MCP server — quality and maintenance score on Glama Listed on mcpservers.org

Your AI has questions. Your users have answers. Elicitly connects them — human-in-the-loop for prompts and Agent Skills over MCP elicitation.

This repository is the open-source Free Edition: the elicitly local MCP server and the @elicitly/tools library. The hosted Pro Edition — durable approvals with review pages, an audit trail, and organization dashboards — lives at elicitly.ai.

Quick start

Run the local (stdio) MCP server straight from npm — no clone, no config:

npx -y elicitly

Register it in your MCP host (Claude Code shown; any stdio host works):

claude mcp add elicitly -- npx -y elicitly

Or skip the command line: in Claude Desktop, download elicitly.mcpb from the latest release and open it — a one-click, self-contained desktop extension.

Then ask your agent to call elicit_confirm ("Ship it?"), elicit_form (your own JSON schema), elicit_doctor (does this host actually support elicitation?), or elicit_display (show a LiquidJS template rendered inline as an MCP App).

Packages

PackageWhat it is
elicitlyThe local stdio MCP server (npx -y elicitly)
@elicitly/toolsEmbeddable toolkit: register the elicitation tools on your own McpServer

Why

MCP has a native answer for asking a human — elicitation — but host support is inconsistent, and only an MCP server can trigger it. Nobody wants to roll their own server just to ask a question. Elicitly is that server (or, via @elicitly/tools, the toolkit inside yours), plus the diagnostic (elicit_doctor) that makes real-world host support visible — feeding the public Support Matrix.

Develop

pnpm install
pnpm build        # tsdown builds both packages
pnpm test         # vitest
pnpm test:coverage # vitest + v8 coverage (thresholds enforced; HTML report in coverage/)
pnpm typecheck    # tsc
pnpm check        # biome

License

Apache-2.0

Elicitly™ is a trademark of Preneur LLC — see TRADEMARKS.md.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.