Streamtime for AI agents
Streamtime is project management software for creative agencies, design studios, and architects, covering job tracking, time tracking, scheduling, quoting, and invoicing. 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 Streamtime.
Look up organisation details
Retrieve the agency's organisation details as a quick read-only check before configuring a new integration.
List team roles before assigning
Pull the list of roles set up in the account before assigning one to a new team member.
Check a user's saved segments
List the saved segments a user has set up to see how they filter jobs and time entries.
4 Streamtime actions, graded by risk.
Every Streamtime action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
1Look things up. Allowed by default.
- streamtime.list_rolesList Roles
write
3Create and change things. Allow, or ask the user first.
- streamtime.roles_get_roleGet Role
- streamtime.users_list_saved_segmentsList Saved Segments for User
- streamtime.organisation_get_organisationGet Organisation Details
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Streamtime in three steps.
- 01Your users connect StreamtimeThey add their Streamtime api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “get Role” can wait for the user to approve.
- 03Any agent can actYour agent calls Streamtime through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('streamtime', { read: 'allow', write: 'ask', // roles_get_role destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Streamtime connects.
Users add their Streamtime 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 Streamtime 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 Streamtime from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraphMore project management apps.
Streamtime and Arc0, answered.
Can I use Streamtime with Claude, ChatGPT or Cursor?
Yes. Connect Streamtime 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 Streamtime actions you allow.
How do users connect Streamtime?
Users add their Streamtime 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 Streamtime actions can my agent take?
4 in total: 1 read, 3 write and 0 destructive, such as “get Role”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Streamtime?
Yes. Allow read actions and deny writes in the Streamtime policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Streamtime too?
Yes. The same Streamtime connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Streamtime into your agent.
Your users connect Streamtime once, under your brand. Your agent gets 4 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan