Integration

AppVeyor integration

AppVeyor is a hosted continuous integration and deployment service for Windows, Linux and macOS builds. List projects and add a repository as a project; read the last build of a project or of a branch, a build by version, and the build history; start a build (latest commit of a branch, a given commit or a pull request), re-run or cancel one; download a job's build log and list the artifacts a job uploaded; read and replace the project's appveyor.yml settings, set the next build number and clear the build cache; list deployment environments and their deployments, start, read and cancel a deployment. Team management (users, roles, collaborators), the full project and environment settings objects (which carry webhook URLs, access keys and secure values), project environment variables (returned in clear text), value encryption, status badges and artifact file downloads (AppVeyor answers those with a redirect to temporary storage, which this integration does not follow) are not exposed. Authentication is an AppVeyor API token sent as a Bearer token; use the account-level token from the API keys page (a user-level v2 token needs a different base URL).

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in AppVeyor.Built from the 23 AppVeyor tools below, on the connection you add once.

What you can do with AppVeyor

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Each badge shows the default agent permission of an endpoint (allowed: an agent calls it without asking; ask first: you are asked before an agent calls it, when the agent or chat asks permission for sensitive actions; never: no agent may call it), which every user can change endpoint by endpoint in their credential settings.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Build, 6 operations

  • cancel_buildCancel buildDELETEAgents: ask firstCancels a queued or running build, found by version.
  • get_branch_last_buildGet branch last buildGETAgents: ask firstReturns a project and the most recent build of one branch, with the build's jobs.
  • get_build_by_versionGet build by versionGETAgents: ask firstReturns a project and one of its builds, found by version, with the build's jobs.
  • list_project_buildsList project buildsGETAgents: ask firstLists the builds of a project, newest first, recordsNumber at a time (job details are not included: use get_build_by_version for them). For the next page pass the buildId of the last build returned as startBuildId.
  • re_run_buildRe run buildPUTAgents: ask firstRe-runs a finished build and returns it. By default every job runs again; with reRunIncomplete true only the failed or cancelled jobs of a multi-job build run again.
  • start_buildStart buildPOSTAgents: ask firstStarts a build of a project and returns it queued: with branch, the most recent commit of that branch; with branch and commitId, that commit; with pullRequestId (instead of branch and commitId), that pull request.

Deployment, 5 operations

  • cancel_deploymentCancel deploymentPUTAgents: ask firstCancels a running deployment.
  • get_deploymentGet deploymentGETAgents: ask firstReturns one deployment with its project, the deployed build, the environment, the deployment jobs, status and times.
  • list_environment_deploymentsList environment deploymentsGETAgents: ask firstReturns a deployment environment and its deployments, newest first: which project and build went there, with status and times.
  • list_project_deploymentsList project deploymentsGETAgents: ask firstLists the deployments of a project, newest first: which build went to which environment, with status and times. At most 20 per call (the default); pass the last deploymentId as startDeploymentId for the next page.
  • start_deploymentStart deploymentPOSTAgents: ask firstDeploys a build of a project to a deployment environment and returns the deployment. When the build has several jobs, buildJobId selects the job whose artifacts are deployed; environmentVariables are set for this deployment only.

Project, 4 operations

  • add_projectAdd projectPOSTAgents: ask firstAdds a repository to AppVeyor as a new project and returns it, including the slug the other tools use. A plain git, mercurial or subversion repository that needs authentication takes repositoryAuthentication (credentials or ssh).
  • delete_projectDelete projectDELETEAgents: ask firstDeletes a project from AppVeyor.
  • get_project_last_buildGet project last buildGETAgents: ask firstReturns a project and its most recent build, with the build's jobs (each job's status, test counts and jobId for the log and artifact tools).
  • list_projectsList projectsGETAgents: ask firstLists every project of the account, each with its repository details and its most recent build (version, branch, commit, status and times).

Environment, 2 operations

  • delete_environmentDelete environmentDELETEAgents: ask firstDeletes a deployment environment of the account.
  • list_environmentsList environmentsGETAgents: ask firstLists the deployment environments of the account: id, name and provider (Azure, FTP, GitHub Releases, NuGet, S3, Web Deploy, webhook, deployment agent and others).

Project settings, 2 operations

  • get_project_yamlGet project yamlGETAgents: ask firstReturns the project's settings, as stored in AppVeyor, as text in appveyor.yml format.
  • update_project_yamlUpdate project yamlPUTAgents: ask firstReplaces the project's build settings with the given appveyor.yml text. Read the current text first with get_project_yaml when only part of it should change.

Artifact, 1 operation

  • list_job_artifactsList job artifactsGETAgents: ask firstLists the artifacts one build job uploaded: file path, name, type, size and upload time. The artifact files themselves cannot be downloaded through this integration.

Build cache, 1 operation

  • delete_build_cacheDelete build cacheDELETEAgents: ask firstDeletes the project's build cache, so the next build starts without cached files.

Build log, 1 operation

  • download_build_logDownload build logGETAgents: ask firstDownloads the console log of a build job (plain text) and returns it as a stored file.

Build number, 1 operation

  • set_next_build_numberSet next build numberPUTAgents: ask firstSets the number the project's next build will get (it shows in the build version through the {build} placeholder).

Use AppVeyor from Claude Code, Cursor or Codex

Connect AppVeyor in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its AppVeyor operations become tools the client can call, next to every other integration you connected.

Claude Code
claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"
Codex (~/.codex/config.toml)
[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"
Cursor, Claude Desktop and other JSON configs
{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect AppVeyor

  1. Create your workspace

    Sign up free. Nothing to install.

  2. Connect AppVeyor once

    Add your AppVeyor connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.

  3. Describe the job in chat

    The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

AppVeyor integration FAQ

What can you do with the AppVeyor integration?

LiveContext exposes 23 operations on AppVeyor, covering build, deployment, project and environment.

Popular integrations

Browse the whole catalog