Cloud BOT MCP. Run web tasks from simple conversation.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Cloud BOT MCP lets your AI agent run complex web tasks and automate entire workflows in the cloud. It's your full command center for Robotic Process Automation (RPA), allowing you to trigger bots, scrape data from forms, or navigate websites using natural conversation.
You manage job execution, monitor real-time status, and even cancel runaway processes—all without leaving your chat window.
What your AI agents can do
Cancel job
Stops an active job immediately by providing its specific job ID.
Execute bot
Starts a bot execution run, allowing you to pass custom parameters like URLs or JSON data.
Get bot details
Pulls specific configuration and metadata for one particular bot by ID.
You can list all available bots and retrieve detailed configuration for each one.
Trigger a bot execution, passing custom data like specific URLs or JSON parameters.
Check the live status of any running automation job and pull detailed logs and results.
Cancel jobs that are running too long or suspend processes when they’re finished.
Access and organize files created by the bots within the dedicated cloud storage area.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
Cloud BOT MCP: 7 Tools Available
These tools allow you to programmatically manage the entire lifecycle of your cloud-based RPA bots, from listing them to cancelling running jobs.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Cloud BOT on Vinkius019dd0d1cancel job
Stops an active job immediately by providing its specific job ID.
019dd0d1execute bot
Starts a bot execution run, allowing you to pass custom parameters like URLs or JSON data.
019dd0d1get bot details
Pulls specific configuration and metadata for one particular bot by ID.
019dd0d1get job status
Checks the current status and logs of an existing job ID.
019dd0d1list bots
Retrieves a list of every available RPA bot configured in your account.
019dd0d1list cloudbot files
Lists all files that have been saved or generated in the cloud storage area.
019dd0d1list jobs
Shows a list of recent automation jobs that have run through the system.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Cloud BOT, then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,000+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Cloud BOT. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 7 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
The Pain of Manual Web Automation
Right now, automating web tasks means logging into Bot Dashboard A to check status, opening Sheet B to log results, and then switching over to Portal C just to copy the final data. You're spending more time managing the workflow than actually running it.
With this MCP, your agent handles that entire sequence. You ask for a web task, and you get one cohesive response—the status update, the file location, or the raw data points. It keeps everything contained right here in your chat interface.
Bot Control: The Power of `execute_bot`
Before this, if you needed to scrape a site, you had to manually set up the bot, input the parameters (like the target URL), and hit 'run' in that specific portal. If it failed, you were stuck waiting for an email or logging back into the dashboard just to check.
Now, your agent executes the task via `execute_bot`. You pass the job details directly to your conversation flow. The process is initiated, monitored, and reported back without you ever leaving this page.
What you can do with this MCP connector
This MCP gives your AI agent full control over cloud-based browser robots. Instead of logging into individual bot dashboards to run a scrape or check a job's progress, you simply tell your AI client what needs doing. Your agent takes over the role of an RPA engineer, coordinating web tasks and data extraction in the background.
You can list available bots, trigger complex runs with custom parameters, and track every step until completion. This is how Vinkius integrates high-fidelity browser automation into simple conversation flows. It lets you handle everything from lead generation to massive data dumps without writing a single line of boilerplate code.
019dd0d1-6e1a-73e0-aeef-b63421a4bafd 
How Cloud BOT MCP Works
- 1 First, subscribe to this MCP on Vinkius. Then, get your Access Token, Secret Key, and Public ID from the Cloud BOT dashboard.
- 2 Next, connect those credentials to your AI client (Claude, Cursor, etc.). Your agent now has direct control over the bot's API.
- 3 Finally, tell your agent what you want done—like 'Run the lead scraper on vinkius.com.' The job runs in the cloud, and your conversation updates with the status.
The bottom line is: Your AI client acts as a dedicated RPA coordinator, running complex browser tasks without you ever opening a web dashboard.
Who Is Cloud BOT MCP For?
This MCP is for anyone whose job involves repeating repetitive actions on websites. It’s the Ops Engineer who's tired of clicking through dashboards at 2 am, the Growth Marketer needing continuous lead scraping, or the Developer wanting to integrate web interaction into a custom script.
Manages and monitors automated processes. They use this MCP to list bots and check job statuses via get_job_status to ensure pipeline stability.
Automates lead capture and market research. They trigger data extraction using execute_bot across multiple target websites without manual intervention.
Integrates high-speed, reliable browser automation into custom codebases by managing bot lifecycles with functions like cancel_job and get_bot_details.
What Changes When You Connect
- You stop manually logging into bot portals. Your AI agent handles all job orchestration, allowing you to trigger bots and monitor status simply by asking your client a question.
- Need to check if the data is ready? Use
get_job_statuson an active job ID. You get real-time feedback and full logs immediately, so you know exactly where things stand. - Stop losing track of output files. By running
list_cloudbot_files, your AI can show you every saved result and help you retrieve the download link instantly. - If a bot gets stuck or runs too long, don't panic. You can use
cancel_jobto stop it immediately with just its job ID. - The setup is clean. Instead of needing specific code for every action, your agent uses simple queries like those provided by
list_botsandget_bot_detailsto guide you through the process.
Real-World Use Cases
Daily Lead Scraping Cycle
A growth marketer needs 50 competitor data points. They ask their agent to execute a bot, passing the target site URL and desired form fields as JSON parameters. The system runs the job, updates on progress, and saves all results for later download via list_cloudbot_files.
Debugging Failed Pipelines
A developer suspects a bot failed during execution. Instead of diving into complex logs, they ask their agent to check the job status using get_job_status and review the detailed output provided by the tool.
Emergency Process Interruption
An operations engineer runs a bot that starts cycling indefinitely. They quickly issue a command to cancel the job using cancel_job, preventing unnecessary resource consumption and system overload.
Inventory Check Before Deployment
A team leader needs to know what automation tools are available for a new project. They simply ask the agent to list all bots, which uses list_bots to provide an immediate inventory of every usable asset.
The Tradeoffs
Trying to 'run' data without parameters
A user tries to tell the AI: 'Run the Price Scraper bot and get me prices.' The system doesn't know which site or what fields to target.
→
You must specify the input. Use execute_bot and pass a JSON object containing the necessary parameters, such as the URL for scraping.
Assuming success immediately
The AI says 'Job started.' The user assumes everything is fine and moves on, only to find hours later that the job failed silently.
→
After triggering a run with execute_bot, always use get_job_status periodically. This confirms the active status and provides immediate error reports.
Starting from scratch every time
Instead of checking what was done yesterday, the user starts by asking for general help, wasting time.
→
Always start with list_jobs. This gives you a quick view of recent activity and job IDs needed to track or inspect past work.
When It Fits, When It Doesn't
Use this MCP if your process involves interacting with web pages—filling forms, navigating multiple tabs, scraping visible data. You need the full power of RPA, which is what execute_bot delivers.
Don't use it if you are simply calling a clean API endpoint that doesn't require browser interaction (e.g., just pulling user records from a database). If all your tasks are single-step data retrieval without navigating or clicking, a simpler direct API connector will be better. However, because this MCP handles the entire lifecycle—from list_bots to cancel_job and file management—it remains the most powerful tool for complex, multi-stage web workflows.
Common Questions About Cloud BOT MCP
How do I find out what bots are available using list_bots? +
You simply ask the agent to call list_bots. It returns a full inventory of every bot you've set up, giving you their names and IDs so you know exactly what tools are at your disposal.
What happens if my job is running too long? Can I use cancel_job? +
Yes. If a process runs indefinitely, you can ask the agent to cancel_job. You just need to provide the specific job ID for the bot to stop the execution immediately.
I ran a scrape; where do I find the output data? Should I use list_cloudbot_files? +
The results are saved in the cloud storage. Ask your agent to call list_cloudbot_files to see what files were generated, and then you can retrieve the necessary download link.
How do I start a new scraping task using execute_bot? +
You use execute_bot. You must provide all required parameters in JSON format—this includes the bot ID, the URL, and any specific fields you want the scraper to look for.
How do I view my historical runs and job IDs using list_jobs? +
You can see a comprehensive log of all your past automation attempts. This function retrieves metadata for executed jobs, letting you track when they ran, who triggered them, and their initial status. It's essential for auditing performance or finding the ID needed to check an old job's specific details.
What information can I get about a specific bot using get_bot_details? +
This tool gives you all the technical specifics of a single robot, including its configuration parameters and intended purpose. You use this to confirm if the bot is set up correctly for your task before triggering it. It’s how you verify that 'Price Scraper' actually expects a URL parameter.
If my web scraping job fails when I run execute_bot, where do I find the error log? +
The detailed logs are retrieved using get_job_status. Instead of just looking for 'Success,' check the status field for failure codes and associated messages. This tells you exactly why the bot quit—whether it was a timeout, an element not found, or bad parameters.
I'm setting up my account; do I need to verify connectivity before using any tools? +
Yes, always confirm your API connection first. While there isn't one specific tool for this, you can test the full setup by listing all available bots with list_bots. If that works, it confirms your access token and secret key are correctly registered with Vinkius.
How do I find my Cloud BOT API credentials? +
Log in to your account, navigate to the API Settings section, and you will find your Access Token, Secret Key, and Public ID.
Can I pass custom parameters to a bot? +
Yes! The execute_bot tool accepts a params_json string where you can provide a JSON object matching your bot's input configuration.
How do I check the results of an automation? +
Use the get_job_status tool with a job ID to retrieve the execution status and any outputs or files generated by the bot.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.