Index / MCP servers / Pushary: human-in-the-loop for AI agents

Pushary: human-in-the-loop for AI agents MCP server

Pushary: human-in-the-loop for AI agents is an MCP server with 5 tools an agent can call, among them ask_user, cancel_question, propose_scope. It answers at https://pushary.com/api/mcp/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 5 September 2026; the last check, on 18 October 2026, succeeded.

Status
Answering
Tools
5
Reliability
10 of 10 checks
Response time
118 ms
Transport
streamable HTTP
Last checked
18 October 2026

Reach a human from a running agent. Approvals on the lock screen, plus a cross-agent audit trail.

Description as the publisher wrote it.

The 5 tools Pushary: human-in-the-loop for AI agents offers

ToolWhat it does
ask_userAsk the user a question as a push notification on their phone and block until they answer. Reach for this whenever you need the user's decision and they may be away from the current client: approving a risky or irreversible step (deleting f
Inputs: question, type, options, questions, placeholder, context
cancel_questionRetract a pending question so it can no longer be answered. Use this when a question became irrelevant before the user replied: the agent found the answer itself, the task was aborted, or a newer question supersedes it. Cancelling prevents
Inputs: correlationId
propose_scopePropose what this run will touch and block until the user ratifies it. Call ONCE at the start of a multi-step run, before doing work. The user sees the paths you intend to change, the areas you promise to leave alone, and your definition of
Inputs: doneWhen, sessionId, allowedPaths, offLimitsPaths, agentName, machineId
send_notificationSend a one-way push notification to the user's phone and browser. Nothing is awaited; use ask_user instead when you need an answer back. Reach for this when a long-running task finishes and the user asked to be told, when the agent hits an
Inputs: title, body, url, iconUrl, imageUrl, agentName
wait_for_answerPoll once for the user's answer to a previously created question: after ask_user times out, after ask_user with wait:false, or with a linkedCorrelationId from send_notification. Each call blocks until the answer arrives or timeoutMs expires
Inputs: correlationId, timeoutMs

Add Pushary: human-in-the-loop for AI agents to your AI client

Every block below points at https://pushary.com/api/mcp/mcp. Pick your client and copy.

Claude Code: one command in your terminal
claude mcp add --transport http pushary https://pushary.com/api/mcp/mcp
Claude Desktop: claude_desktop_config.json
{
  "mcpServers": {
    "pushary": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://pushary.com/api/mcp/mcp"]
    }
  }
}
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json in a project
{
  "mcpServers": {
    "pushary": {
      "url": "https://pushary.com/api/mcp/mcp"
    }
  }
}
VS Code and GitHub Copilot: .vscode/mcp.json
{
  "servers": {
    "pushary": {
      "type": "http",
      "url": "https://pushary.com/api/mcp/mcp"
    }
  }
}
Zed: Zed settings.json
{
  "context_servers": {
    "pushary": {
      "url": "https://pushary.com/api/mcp/mcp"
    }
  }
}
Windsurf: ~/.codeium/mcp_config.json
{
  "mcpServers": {
    "pushary": {
      "serverUrl": "https://pushary.com/api/mcp/mcp"
    }
  }
}
JetBrains AI Assistant: Settings, Tools, AI Assistant, MCP, New MCP Server, as JSON
{
  "mcpServers": {
    "pushary": {
      "url": "https://pushary.com/api/mcp/mcp"
    }
  }
}
Continue: .continue/mcpServers/neuronto.yaml
name: Pushary
version: 0.0.1
schema: v1
mcpServers:
  - name: Pushary
    type: streamable-http
    url: https://pushary.com/api/mcp/mcp
Gemini CLI: ~/.gemini/settings.json
{
  "mcpServers": {
    "pushary": {
      "httpUrl": "https://pushary.com/api/mcp/mcp"
    }
  }
}
Codex CLI: MCP server config
{
  "mcpServers": {
    "pushary": {
      "type": "http",
      "url": "https://pushary.com/api/mcp/mcp"
    }
  }
}
Warp: MCP servers, + Add, paste JSON
{
  "mcpServers": {
    "pushary": {
      "url": "https://pushary.com/api/mcp/mcp"
    }
  }
}
Goose: a one-click extension link
goose://extension?url=https%3A%2F%2Fpushary.com%2Fapi%2Fmcp%2Fmcp&type=streamable_http&id=pushary&name=Pushary

Is Pushary: human-in-the-loop for AI agents up right now?

It answered our last check on 18 October 2026 in 118 ms. Over 10 checks since 5 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.

MCP servers similar to Pushary: human-in-the-loop for AI agents

Questions about Pushary: human-in-the-loop for AI agents

How many tools does Pushary: human-in-the-loop for AI agents have?

5, as returned by the server's own tools/list on 31 August 2026: ask_user, cancel_question, propose_scope, send_notification, wait_for_answer.

Is Pushary: human-in-the-loop for AI agents down?

It answered our last check on 18 October 2026 in 118 ms. Over 10 checks since 5 September 2026 it answered 10.

How do I add Pushary: human-in-the-loop for AI agents to Cursor?

Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://pushary.com/api/mcp/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.

Does Pushary: human-in-the-loop for AI agents need an API key?

It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.

Where this comes from

Publisher: io.github.pushary. Endpoint host: pushary.com. ARD identifier: urn:air:io.github.pushary:mcp:pushary. First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page is inferred from its name. Ranking in Neuronto search is never for sale.

Is this your server? Get a message the day it stops answering or its tools change: monitoring, 14 days free. Or claim the domain to manage how it is listed.