DeployHQ for AI agents
DeployHQ automates deploying projects from Git, SVN, and Mercurial repositories, letting a team push code out without running deployment scripts by hand. 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.
What agents do in DeployHQ.
Check a project's recent deployments
Check a project's recent deployments before deciding whether the latest release went out.
Look up repository commit info
Look up recent commits and tags on a repository before triggering a deployment.
Confirm before deleting a project
Confirm before deleting a project, since its deployment history and settings go with it.
60 DeployHQ actions, graded by risk.
Every DeployHQ action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
21Look things up. Allowed by default.
- deployhq.get_projectsGet Projects
- deployhq.get_templatesGet Templates
- deployhq.get_projects_projectGet Project
- deployhq.get_templates_id_public_idGet Public Framework Template Details
- deployhq.get_projects_project_serversGet Project Servers
- deployhq.get_projects_project_commandsGet Project Commands
- deployhq.get_templates_public_templatesGet Public Templates
- deployhq.get_projects_project_repositoryGet Project Repository
- deployhq.get_projects_project_deploymentsGet Project Deployments
- deployhq.get_projects_project_config_filesGet Project Config Files
- deployhq.get_projects_project_server_groupsGet Project Server Groups
- deployhq.get_projects_project_excluded_filesGet Project Excluded Files
- deployhq.get_projects_project_build_known_hostsGet Project Build Known Hosts
- deployhq.get_projects_project_id_config_files_idGet Config File
- deployhq.get_projects_project_id_server_groups_idGet Server Group
- deployhq.get_projects_project_repository_branchesGet Repository Branches
write
33Create and change things. Allow, or ask the user first.
- deployhq.post_projectsCreate Project
- deployhq.post_templatesCreate Template
- deployhq.post_projects_project_serversCreate Server
- deployhq.post_projects_project_commandsCreate SSH Command
- deployhq.post_projects_project_repositoryAdd Project Repository
- deployhq.post_projects_project_deploymentsCreate Config File Deployment
- deployhq.post_projects_project_config_filesCreate Config File
- deployhq.post_projects_project_server_groupsCreate Server Group
- deployhq.post_projects_project_build_commandsCreate Build Command
- deployhq.post_projects_project_excluded_filesCreate Excluded File
- deployhq.post_projects_id_ai_deployment_overviewGenerate AI Deployment Overview
- deployhq.post_projects_project_build_cache_filesCreate Build Cache File
- deployhq.post_projects_project_build_known_hostsCreate Project Build Known Host
- deployhq.post_projects_project_id_deployments_id_abortAbort Deployment
- deployhq.patch_projects_idUpdate Project
- deployhq.patch_templates_idUpdate Template
destructive
6Delete, cancel or archive. Ask first, or deny outright.
- deployhq.delete_commandDelete Command
- deployhq.delete_projects_projectDelete Project
- deployhq.delete_templates_permalinkDelete Template
- deployhq.delete_projects_project_build_cache_filesDelete Build Cache File
- deployhq.delete_projects_project_server_groups_identifierDelete Server Group
- deployhq.delete_projects_project_excluded_files_identifierDelete Excluded File Rule
DeployHQ in three steps.
- 01Your users connect DeployHQThey add their DeployHQ username and password on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Project” can wait for the user, and “delete Command” can be denied outright.
- 03Any agent can actYour agent calls DeployHQ through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('deployhq', { read: 'allow', write: 'ask', // post_projects destructive: 'deny', // delete_command }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How DeployHQ connects.
Users add their DeployHQ username and password 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 DeployHQ 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
- Username and password
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use DeployHQ from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
DeployHQ and Arc0, answered.
Can I use DeployHQ with Claude, ChatGPT or Cursor?
Yes. Connect DeployHQ 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 DeployHQ actions you allow.
How do users connect DeployHQ?
Users add their DeployHQ username and password 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.
Which DeployHQ actions can my agent take?
60 in total: 21 read, 33 write and 6 destructive, such as “create Project”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in DeployHQ?
Yes. Actions like “delete Command” 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.
Can my own backend call DeployHQ too?
Yes. The same DeployHQ connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug DeployHQ into your agent.
Your users connect DeployHQ once, under your brand. Your agent gets 60 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan