The request asks for a tool for human approval of AI agent actions. ActionBox offers a human approval API with a reviewer inbox and an MCP server 1, Impri lets an agent propose an action that a human approves before execution, via MCP and REST 4, and ActionDock is a human-in-the-loop approval gateway for AI-agent API writes with an MCP server 7. withHuman is an approval layer for agent actions with an MCP server 8, and Let's Clarify collects structured human input mid-workflow 5.
- 1
ActionBox Human Approval APIactionbox.cloudwebsite read, tools not yet checked
Adds human approvals to AI agents, scripts and CI/CD workflows through a hosted API, a reviewer inbox and recorded decisions, with an MCP server offered 1.
official:MCP server · ActionBox Human Input
- 2
Impriimpri.devwebsite read, tools not yet checked
Holds an agent's proposed action in a queue until a human approves, edits or rejects it, exposed via MCP and REST API 4.
+1 community tools built for it
- 3
ActionDockactiondock.appwebsite read, tools not yet checked
Supervised API-write gateway that puts owner approval of the exact request between an agent's tool call and a real API write, with an MCP server 7.
official:MCP server · ActionDock
- 4
withHumanwithhuman.aiwebsite read, tools not yet checked
Approval layer that holds consequential agent actions behind human approval before they reach the target system, with an MCP server 8.
official:MCP server · withHuman
- 5
Let's Clarifyletsclarify.aiwebsite read, tools not yet checked
Lets an agent create a form, share a URL with a human and receive structured JSON back mid-workflow 5.
Sources
- 1ActionBox: Human Approval API for AI Agentsactionbox.cloud · read 2026-10-29
- 4Impri — Human Approval for AI Agentsimpri.dev · read 2026-10-29
- 5Let's Clarify — Human-in-the-Loop for AI Agentsletsclarify.ai · read 2026-10-29
- 7ActionDock — human-in-the-loop approval gateway for AI-agent API writesactiondock.app · read 2026-10-29
- 8withHumanwithhuman.ai · read 2026-10-29
For agents: the 10 actions behind this answer
· ActionBox website read, tools not yet checked
Add human approvals to AI agents, scripts, and CI/CD workflows with the hosted ActionBox API, a reviewer inbox, and durable decisions.
arize-annotation · arize-annotation verified and signed
Creates and manages annotation configs (categorical, continuous, freeform label schemas) and annotation queues (human review workflows) on Arize. Applies human annotations to project spans via the Python SDK. Use when the user mentions annotation config, annotation queue, label schema, human feedbac
request_elevated_access · pipes-mcp found in code, not yet checked
Create a human approval request for either broad temporary Pipes access or one exact API call.
· Impri website read, tools not yet checked
Impri lets your AI agent propose an action and a human approve it before it executes. MCP and REST API, 100 free approvals a month, open-core and self-hostable.
· Let's Clarify website read, tools not yet checked
Let's Clarify lets AI agents collect structured human input mid-workflow. Create a form, share a URL, get JSON back.
custom_api_call · Resend (Activepieces) verified and signed
Custom API Call — Make a custom API call to a specific endpoint
· ActionDock website read, tools not yet checked
ActionDock is a supervised API-write gateway with human-in-the-loop approval for AI-agent API writes: MCP server, deterministic policy, server-held credentials.
· withHuman website read, tools not yet checked
withHuman is the approval layer for AI agents: withHuman lets you put your most consequential agent actions behind human approvals, so your agents can do real work.
workflows · @zapier/zapier-sdk verified and signed
· Tomiseregi website read, tools not yet checked
Explore Tomi Å eregi's work in MCP integrations, human-approval workflows, search infrastructure, and software reliability.
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.