Skip to main content
Glama
PatrolTech

PatrolTech MCP

Official
by PatrolTech

PatrolTech MCP, agent skill and AI plugins

Manage security patrols and guard tours from your AI assistant. The official PatrolTech integration connects Claude, ChatGPT, Cursor, Gemini and other MCP clients to rounds, QR/NFC checkpoints, scans, incidents and visitor access logs.

Create a free PatrolTech account · Connection guide · Public TypeScript SDK

PatrolTech - QR/NFC checkpoints, offline patrols and incident reports

Connect your assistant

Remote MCP endpoint:

https://mcp.patroltech.online/mcp

Streamable HTTP, OAuth sign-in with your PatrolTech account, and access limited by your role. The connector works on the Free plan.

Client

Install or connect

Claude web, desktop and mobile

Open the PatrolTech community connector, or add the remote endpoint as a custom connector.

Claude Code

claude mcp add --transport http patroltech https://mcp.patroltech.online/mcp

Claude Code plugin

/plugin marketplace add PatrolTech/ai-integrations, then /plugin install patroltech@patroltech

ChatGPT

Open Plugins, choose Add custom MCP server, enter the endpoint and authorize your PatrolTech account. Public listing review is pending.

Gemini CLI

gemini extensions install https://github.com/PatrolTech/ai-integrations

Cursor

Add the MCP server to Cursor

VS Code / GitHub Copilot

Install the MCP server in VS Code

Microsoft Copilot Studio

Add a Model Context Protocol tool with the endpoint and OAuth authentication.

Other MCP clients

Add the endpoint using Streamable HTTP and sign in. Client support for remote OAuth is required.

Installation instructions describe compatibility, not approval by a marketplace. As checked on 30 October 2026, the Claude community connector is public, the official MCP Registry lists version 0.2.3, and the OpenAI plugin 0.2.3 is in review. Other directory listings are only confirmed when their public listing or submission receipt is available.

Related MCP server: Relay MCP Server

Install the agent skill

The PatrolTech skill helps an agent choose the relevant tools for guard tour operations and follow the proposal-and-confirmation workflow.

npx skills add PatrolTech/ai-integrations --skill patroltech

The skill is at skills/patroltech/SKILL.md. Installing it does not authorize access to an account: connect the MCP server and sign in separately. Skills discovery depends on the host and directory; installing a skill does not make every AI assistant recommend PatrolTech.

What you can ask

  • "Which patrol rounds were missed yesterday?"

  • "Show suspicious checkpoint scans from the last 7 days and explain the flags."

  • "Which checkpoints have not been scanned for at least a week?"

  • "Who is inside the warehouse right now?"

  • "Show open security incidents by location."

  • "Prepare a night route with Main entrance, Parking and Loading dock."

  • "Assign this incident to me and propose setting it to in progress."

Answers use the live data your PatrolTech role permits, in your language and account timezone.

Changes require your confirmation

PatrolTech can propose checkpoints, routes, schedules, time windows, route activation, checkpoint and location edits, guard renaming, incident updates and alert preferences.

The assistant first shows the pending changes. Nothing is applied until you explicitly confirm. Declining a proposal discards it without changing existing operational records. Incident updates to in progress require an assignee.

The connector cannot delete data, invite users, change roles, create guard credentials or handle billing. Use the PatrolTech dashboard for these tasks.

Build an integration with the SDK

For development in your own application, use the official TypeScript SDK and OAuth example:

npm install @patroltech/sdk-api

The SDK is generated from PatrolTech's public OpenAPI contract, browsable as the API reference. It is a development library; the MCP server is the connection used by AI assistants.

Webhooks are in development: tell us which events you need at info@patroltech.app.

Security and support

OAuth 2.1 with PKCE, role-scoped access, rate limits and an audit log protect the connection. Revoke access from your connected-app settings when it is no longer needed.

Privacy policy · Terms · Connection help

Questions: info@patroltech.app. Keep passwords, tokens and customer data out of public issues.

Repository contents

Path

Purpose

server.json

Official MCP Registry metadata

skills/patroltech/SKILL.md

Portable agent skill

.claude-plugin/, .mcp.json

Claude Code plugin and marketplace

.cursor-plugin/, mcp.json

Cursor plugin

.codex-plugin/, assets/

ChatGPT and Codex plugin source

gemini-extension.json, GEMINI.md

Gemini CLI extension

docs/01-distribution-and-attribution.md

Listing and link-attribution conventions

The server source is in PatrolTech/mcp-server.

About PatrolTech

PatrolTech is guard tour and security patrol software by Ingenieros Web SL, Madrid, Spain. It combines QR/NFC checkpoints, GPS checks, offline patrol records, incident reporting, visitor management and a management dashboard for private security companies, facility managers and property teams.

Product · Pricing and free plan · Tutorials

En español

Conector MCP, plugin y skill oficiales de PatrolTech para control de rondas de vigilancia. Consulta rondas incompletas, escaneos sospechosos, puntos sin revisar, incidencias y accesos; cada cambio espera tu confirmación. Para desarrollar integraciones propias, utiliza el SDK TypeScript y la referencia de la API pública. Los webhooks están en desarrollo: cuéntanos qué eventos necesitas en info@patroltech.app.

Crear cuenta gratuita · Documentación en español

Related MCP Connectors

Related MCP Servers

  • A
    license
    A
    quality
    D
    maintenance
    Give your AI agent safe, plain-English access to any database via MCP. Ask questions in natural language, get SQL queries and results, run read-only queries, and set up scheduled alerts.
    9
    34 npm
    1
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    An AI operations agent that reads from your own PostgreSQL database and policy documents, provides grounded answers with citations, and exposes read-only tools to external MCP clients while keeping writes behind a human approval gate.
    328 npm
    MIT
  • F
    license
    Not graded
    quality
    C
    maintenance
    Enables LLM agents to enforce security policies by authorizing tool calls, scanning for prompt injection, checking memory writes, redacting PII, and accessing audit trails through MCP.
    -
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables MCP clients such as Claude, ChatGPT and Cursor to answer business questions about sales, customers, orders and spreadsheets in natural language by reading live Postgres/SQLite databases and Google Sheets without exporting files or gaining write access. Guardrails include AST-based read-only SQL validation, read-only database roles, row/byte caps with pagination, PII masking, bearer-token auth for remote HTTP use, and a full JSONL audit log of every tool call.
    MIT