
Security News
arXiv Is Rate Limiting Authors Following a Flood of AI Slop Submissions
arXiv now limits authors to two submissions a month as AI slop overwhelms moderators, delays good papers, and sparks debate over applying the limit to everyone.
Local (stdio) MCP server that gives your prompts and Agent Skills MCP elicitation — human-in-the-loop dialogs (elicit_confirm, elicit_form) the elicit_doctor capability report, and elicit_display for rendered HTML as an MCP App, with no server of your own
A local (stdio) MCP server that makes MCP elicitation easy to use from any prompt or Agent Skill — and its cross-host support visible.
confirm(); override labels.ok/labels.cancel to relabel or localize
(e.g. Aceptar/Cancelar).requestedSchema subset);
returns the raw {action, content}.probeElicitation: true runs one live elicitation round-trip and classifies
the result (working, advertised_but_autocanceled, user_declined,
advertised_but_unanswered, unsupported).context, and hosts that
support MCP Apps
render it inline. Templates may load Tailwind/DaisyUI from jsDelivr; allow
more image/script/style origins with ELICITLY_DISPLAY_RESOURCE_DOMAINS
(comma-separated https:// origins) — in the Claude Desktop extension, that's
the elicit_display: extra allowed origins setting.npx -y elicitly
Register it with any MCP host as a stdio server. In Claude Code:
claude mcp add elicitly -- npx -y elicitly
or in a host config file (.mcp.json or client settings):
{
"mcpServers": {
"elicitly": { "command": "npx", "args": ["-y", "elicitly"] }
}
}
Download elicitly.mcpb from the
latest release and
open it in Claude Desktop (or Settings → Extensions → Install extension).
The bundle is self-contained — no Node.js or npm setup of your own; it runs
on Claude Desktop's managed runtime. Build it from source with
pnpm --filter elicitly build:mcpb.
Claude Desktop and dialogs: current Claude Desktop builds don't advertise elicitation to local MCP servers (config-file and extension installs alike — measured, not assumed), so
elicit_confirmandelicit_formreturn their graceful no-answer contract there rather than raising a dialog.elicit_doctorstill reports the host truthfully — that report is the point. See the Elicitation Support Matrix for hosts where dialogs work, and the Pro Edition for approvals that reach a browser-based review page when the host has no native dialog.
support.elicitationForm / support.elicitationUrl.probeElicitation: true — one real elicitation
round-trip; read probes.elicitationForm.verdict.message: "Ship it?").{action, content}.Full docs: elicitly.ai/docs
pnpm install
pnpm --filter elicitly build # produces packages/elicitly/dist/cli.mjs
claude mcp add elicitly -- node /absolute/path/to/packages/elicitly/dist/cli.mjs
The server runs entirely on your machine: tool calls and elicitation answers
stay between your MCP host and the local process, and nothing is sent
anywhere. The contribute-fingerprint prompt only prepares a GitHub issue
link — you review and submit it yourself. Project privacy policy:
https://www.elicitly.ai/privacy/
FAQs
Local (stdio) MCP server that gives your prompts and Agent Skills MCP elicitation — human-in-the-loop dialogs (elicit_confirm, elicit_form) the elicit_doctor capability report, and elicit_display for rendered HTML as an MCP App, with no server of your own
The npm package elicitly receives a total of 78 weekly downloads. As such, elicitly popularity was classified as not popular.
We found that elicitly demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.

Security News
arXiv now limits authors to two submissions a month as AI slop overwhelms moderators, delays good papers, and sparks debate over applying the limit to everyone.

Research
/Security News
A new GhostAction wave hits hundreds of GitHub repos, expanding CI/CD secret theft to cloud and AI credentials in source code and git history.

Research
/Security News
Tensorlake npm SDK version 0.5.144 was compromised in a ChainDrop / Shai-Hulud attack, delivering credential-stealing malware.