How to handle MCP elicitation in form and URL modes
Official MCP spec and SDK steps for form and URL elicitation: declare capabilities, pause a tool call, collect input, and retry safely.
Official MCP spec and SDK steps for form and URL elicitation: declare capabilities, pause a tool call, collect input, and retry safely.
Official Hermes Agent steps to add MCP servers: CLI install, config.yaml mcp_servers, tool allowlists, and /reload-mcp.
Official OpenViking docs show the Hermes memory setup command, a separate-environment warning, and how to verify the provider.
OpenAI’s Codex guidance: tighten Astra skill triggers, stop blanket AGENTS.md reads, and define done so the model does not stall.
Install Grok Bot, create a named specialist, hand off a first task, and chain bots on a shared cloud computer.
Official Claude Code docs for claude plugin eval: init cases, score plugins against a no-plugin baseline, and gate changes in CI.
Maintainer steps to import an OpenClaw or Clawdbot setup into Hermes Agent with dry-run, presets, and secret controls.
Enable Google Cloud Agent Registry, register MCP servers with tool specs, and connect the registry MCP server so agents can discover governed tools.
Install Google Maps Platform agent skills with the Skills CLI or Gemini CLI extension, then invoke google-maps-platform (or let the agent match it) so detailed Maps instructions load via progressive disclosure.
Install Unity’s official Claude Code plugin from the marketplace, pick a scope, and verify that /unity: skills load.
Official Vercel steps to point a local OpenClaw assistant at AI Gateway with install, onboard, and health checks.
Official steps for Chat vs Work vs Codex, desktop/web start, Voice, workspace toggles, and how Astra draws the shared allowance.
Official steps to turn on Cursor computer use on self-hosted Cloud Agent workers: worker flags, macOS permissions, Linux desktops, and desktop sharing.
Microsoft Learn steps to add Copilot Studio computer use: pick a CUA model, bind a Windows machine, and lock down sites, apps, and credentials.
Google’s Codelab shows gcloud commands to run OpenClaw on Cloud Run instances with GCS state and secrets.
Warp’s official Claude Code setup: install, auth, CLAUDE.md, permission allowlists, and the Warp notification plugin.
Official OpenClaw steps for a shared team gateway: Tailscale or proxy ingress, a chat bot, Control UI sessions, and operator roles.
Official steps to enable Claude Code’s macOS computer-use MCP from the CLI, including permissions, app approvals, and the session lock.
Official LangChain steps for turning traces into Harbor eval tasks with the eval-engineering skill, world specs, and Spec2Task.
Official mda CLI steps to init, test in LangSmith Studio, and deploy a Deep Agent on LangChain's managed US-region runtime.
Run a local Lanes Link MCP endpoint, connect one Gmail account with send denied, and read the hash-chained audit log—including refusals.
Official OpenClaw triage docs: generate a sanitized install prompt, then hand it to Claude Code, Codex, or the embedded agent.
Official Warp docs for enabling sandboxed Computer Use on cloud agents via settings, Oz CLI flags, and the API.
Remotion’s docs show how to add official video Agent Skills for Claude Code, Codex, Cursor, and Kimi via npx skills or remotion skills.
Official Claude Cowork setup across desktop, web, mobile, and Chrome: mode switch, /setup-cowork, working folder, and plan limits.