Appveyor for AI agents

AppVeyor is a hosted continuous integration service for building and deploying Windows and cross-platform applications, used by development teams to automate their build and test pipeline. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Developer toolsAPI keyMCP + RESTappveyor.com
AUDIT LOG · APPVEYORPOLICY: acme-support
09:41:07 · claude · u_8f2read
appveyor.list_collaborators
List Collaborators✓ allowed · 212ms
09:41:08 · claude · u_8f2read
appveyor.get_role
Get Role✓ allowed · 164ms
09:41:12 · claude · u_8f2destructive
appveyor.delete_build
Delete Build✕ blocked · policy: deny
EVERY APPVEYOR CALL, ON THE RECORD
01 · USE CASES

What agents do in Appveyor.

01

Check the status of a build

Get a build by its version number to see whether it passed or failed.

02

Download a build log for debugging

Download the log for a failed build to help diagnose the issue.

03

Confirm before deleting a build

Removing a build record is permanent and should be confirmed before it runs.

02 · ACTIONS

14 Appveyor actions, graded by risk.

Every Appveyor action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

13

Look things up. Allowed by default.

  • appveyor.get_role
    Get Role
  • appveyor.get_roles
    Get Roles
  • appveyor.get_users
    Get Users
  • appveyor.get_projects
    Get Projects
  • appveyor.get_environments
    Get Environments
  • appveyor.list_collaborators
    List Collaborators
  • appveyor.get_build_artifacts
    Get Build Artifacts
  • appveyor.get_build_by_version
    Get Build By Version
  • appveyor.get_user_invitations
    Get User Invitations
  • appveyor.get_project_status_badge
    Get Project Status Badge
  • appveyor.get_project_branch_status_badge
    Get Project Branch Status Badge
  • appveyor.get_public_project_status_badge
    Get Public Project Status Badge
  • appveyor.download_build_log
    Download Build Log

write

0

Create and change things. Allow, or ask the user first.

  • No write actions.

destructive

1

Delete, cancel or archive. Ask first, or deny outright.

  • appveyor.delete_build
    Delete Build
03 · HOW IT WORKS

Appveyor in three steps.

  1. 01Your users connect AppveyorThey add their Appveyor api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “updates” can wait for the user, and “delete Build” can be denied outright.
  3. 03Any agent can actYour agent calls Appveyor through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('appveyor', {
  read: 'allow',
  write: 'ask',        
  destructive: 'deny',  // delete_build
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Appveyor connects.

Users add their Appveyor api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Appveyor connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Appveyor from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Appveyor and Arc0, answered.

Q01

Can I use Appveyor with Claude, ChatGPT or Cursor?

Yes. Connect Appveyor to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Appveyor actions you allow.

Q02

How do users connect Appveyor?

Users add their Appveyor api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Appveyor actions can my agent take?

14 in total: 13 read, 0 write and 1 destructive. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Appveyor?

Yes. Actions like “delete Build” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Appveyor too?

Yes. The same Appveyor connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Appveyor into your agent.

Your users connect Appveyor once, under your brand. Your agent gets 14 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan