Conductor for AI agents
Conductor is a cloud platform for running coding-agent sessions, letting a team spin up workspaces and track agent conversations across projects. 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 Conductor.
Create a new coding session
Create a new session in a workspace to start an agent working on a task.
Check a session's messages
List a session's messages to review what an agent has done so far.
Confirm before stopping a session
Stop a running session once its work is confirmed complete or no longer needed.
17 Conductor actions, graded by risk.
Every Conductor action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
10Look things up. Allowed by default.
- conductor.get_messageGet Message
- conductor.get_projectGet Project
- conductor.get_sessionGet Session
- conductor.get_workspaceGet Workspace
- conductor.list_messagesList Messages
- conductor.list_projectsList Projects
- conductor.list_sessionsList Sessions
- conductor.list_workspacesList Workspaces
- conductor.get_current_userGet Current User
- conductor.query_transcriptsQuery Transcripts
write
7Create and change things. Allow, or ask the user first.
- conductor.send_messageSend Message
- conductor.create_sessionCreate Session
- conductor.create_workspaceCreate Workspace
- conductor.stop_sessionStop Session
- conductor.rename_sessionRename Session
- conductor.rename_workspaceRename Workspace
- conductor.change_workspace_stateChange Workspace State
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Conductor in three steps.
- 01Your users connect ConductorThey add their Conductor api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “create Session” can wait for the user to approve.
- 03Any agent can actYour agent calls Conductor through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('conductor', { read: 'allow', write: 'ask', // create_session destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Conductor connects.
Users add their Conductor 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 Conductor 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
Use Conductor from any agent.
Conductor and Arc0, answered.
Can I use Conductor with Claude, ChatGPT or Cursor?
Yes. Connect Conductor 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 Conductor actions you allow.
How do users connect Conductor?
Users add their Conductor 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.
Which Conductor actions can my agent take?
17 in total: 10 read, 7 write and 0 destructive, such as “create Session”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Conductor?
Yes. Allow read actions and deny writes in the Conductor policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Conductor too?
Yes. The same Conductor connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Conductor into your agent.
Your users connect Conductor once, under your brand. Your agent gets 17 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan