An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Semaphore to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Run pipelines and debug builds through your AI agent.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 36 capabilities

We ship only the actions that matter.

Capability set01 / 09

01-04

4 capabilities in this set.

Part of 36 available through Semaphore.

  1. 01

    Activate deployment target

    This capability activates a specific deployment target in Semaphore.

  2. 02

    Configure artifact retention

    Use this to set how long Semaphore keeps your build artifacts.

  3. 03

    Delete agent type

    This capability removes a self-hosted agent type from your organization.

  4. 04

    Delete deployment target

    Use this to delete an existing deployment target.

Capability set02 / 09

05-08

4 capabilities in this set.

Part of 36 available through Semaphore.

  1. 05

    Get deployment history

    This capability retrieves the deployment history for a specific target.

  2. 06

    Get job

    This capability provides detailed information about a specific job.

  3. 07

    Get job logs

    Use this to pull the logs for a specific job to debug failures.

  4. 08

    List pipelines

    This capability lists all pipelines associated with a project.

Capability set03 / 09

09-12

4 capabilities in this set.

Part of 36 available through Semaphore.

  1. 09

    Run workflow

    Use this to start a new Semaphore workflow.

  2. 10

    Trigger promotion

    This capability initiates a promotion to a different environment.

  3. 11

    Trigger task

    Use this to run a specific task immediately.

  4. 12

    Update agent type

    This capability modifies the configuration of a self-hosted agent type.

Capability set04 / 09

13-16

4 capabilities in this set.

Part of 36 available through Semaphore.

  1. 13

    Create agent type

    Use this to set up a new self-hosted agent type.

  2. 14

    Get workflow

    This capability retrieves the details of a specific workflow.

  3. 15

    List agent types

    This capability lists all self-hosted agent types in your account.

  4. 16

    Rerun workflow

    Use this to restart a specific workflow.

Capability set05 / 09

17-20

4 capabilities in this set.

Part of 36 available through Semaphore.

  1. 17

    Update deployment target

    This capability updates the settings for a deployment target.

  2. 18

    Create deployment target

    Use this to create a new deployment target.

  3. 19

    Deactivate deployment target

    This capability deactivates a deployment target.

  4. 20

    Disable all agent types

    Use this to disable every agent belonging to a specific type.

Capability set06 / 09

21-24

4 capabilities in this set.

Part of 36 available through Semaphore.

  1. 21

    Get agent

    This capability retrieves information about a specific self-hosted agent.

  2. 22

    Get agent type

    This capability provides details for a specific self-hosted agent type.

  3. 23

    Get artifact retention

    Use this to check the current artifact retention policies for a project.

  4. 24

    Get deployment target

    This capability fetches details for a deployment target using its ID.

Capability set07 / 09

25-28

4 capabilities in this set.

Part of 36 available through Semaphore.

  1. 25

    Get deployment target by name

    Use this to find deployment target details by its name.

  2. 26

    Get pipeline

    This capability retrieves the full details of a specific pipeline.

  3. 27

    List agents

    This capability lists all self-hosted agents of a certain type.

  4. 28

    List artifacts

    Use this to see the artifacts available within a specific scope.

Capability set08 / 09

29-32

4 capabilities in this set.

Part of 36 available through Semaphore.

  1. 29

    List deployment targets

    This capability lists all deployment targets for a project.

  2. 30

    List promotions

    Use this to view the list of promotions for a pipeline.

  3. 31

    List workflows

    This capability lists all workflows for a given project.

  4. 32

    Rebuild pipeline

    Use this to trigger a rebuild of failed blocks within a pipeline.

Capability set09 / 09

33-36

4 capabilities in this set.

Part of 36 available through Semaphore.

  1. 33

    Stop job

    This capability stops a job that is currently running.

  2. 34

    Stop pipeline

    Use this to halt a running pipeline.

  3. 35

    Stop workflow

    This capability stops a running workflow.

  4. 36

    Validate yaml

    Use this to check a Semaphore pipeline YAML definition for errors.

Real work

What teams actually run

01

Rapid Debugging

When a build fails, ask your agent to read the logs and suggest a fix immediately.

02

Environment Promotion

Trigger a promotion from staging to production by simply telling your agent to do so.

03

Pipeline Maintenance

Use the agent to validate YAML definitions before you commit them to your repository.

04

Agent Management

Create or update self-hosted agent types through a single chat interface.

One connector, every AI

Semaphore works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Semaphore to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

1260ms average. Fast in production.

Semaphore is checked daily against the live service.

Daily averagePeak 1667ms
Oct 3Today
Fastest day
1037ms
Slowest day
1667ms
14-day trend
Improving-23%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 36 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Semaphore, so you can see the experience inside your AI.

It does not authenticate your account with Semaphore. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Semaphore Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_4boMMcM8niVqPugdtaODagPmB0iDjPIFB9fElanu/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Semaphore capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "semaphore-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_4boMMcM8niVqPugdtaODagPmB0iDjPIFB9fElanu/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Semaphore in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Semaphore owners hand off.

This MCP is built for engineering teams who want to manage their delivery lifecycle without leaving their development environment.

  • 01

    DevOps Engineers

    They use the agent to monitor pipeline health and manage deployment targets.

  • 02

    Software Developers

    They use the agent to check build logs and trigger reruns directly from their editor.

  • 03

    Release Managers

    They use the agent to orchestrate deployment sequences and audit history.

FAQ

Questions Semaphore owners ask.

  • 01

    How do I connect my Semaphore account?

    You just need to subscribe to the MCP on Vinkius and enter your Semaphore API Token and Organization Slug. Once that is done, it is ready to use in your AI client.

  • 02

    Which AI clients can I use with this MCP?

    You can use any MCP-compatible client, including Claude, Cursor, and Windsurf.

  • 03

    Can I debug failed builds with this capability?

    Yes. You can ask your agent to fetch specific job logs to see exactly why a build failed.

  • 04

    Is it possible to trigger a new workflow?

    Yes. You can use the run_workflow capability to start a new workflow through your agent.

  • 05

    Can I manage my self-hosted agents?

    Yes. The MCP includes capabilities to create, update, list, and delete self-hosted agent types.

  • 06

    Can I check the logs of a specific job to debug a failure?

    Yes! Use the get_job_logs capability with the Job ID. Your agent will retrieve the execution logs, allowing you to identify errors directly in the conversation.

  • 07

    How do I list all active pipelines for a specific project?

    Simply ask the agent to run the list_pipelines action providing the Project ID. You can also filter by branch name or workflow ID.

  • 08

    Is it possible to trigger a promotion to production via chat?

    Yes. If your pipeline has promotions configured, you can use the trigger_promotion capability by providing the Promotion ID to move your code to the next stage.

Explore

More in Developer Tools

Suggestions

Connect Semaphore to Claude, Cursor, ChatGPT & more