Developers
Wireflow MCP Connector
Wireflow speaks the Model Context Protocol. Connect Claude or any MCP client and let it build, inspect, and run your AI workflows on your behalf, with explicit consent and per-scope permissions.
Connect
Add a custom connector in your MCP client and point it at the Streamable HTTP endpoint below. The client walks you through Wireflow’s OAuth sign-in and a consent screen, no manual API keys, no client setup.
https://www.wireflow.ai/api/mcpHow auth works
- OAuth 2.1 authorization code flow with PKCE (S256).
- Dynamic Client Registration (RFC 7591), so clients self-register with no pre-shared credentials.
- You approve a consent screen listing exactly the permissions the client asked for. Revoke anytime from settings.
Permissions
A client that asks for nothing in particular gets the read and run scopes. Anything marked opt-in is withheld unless the client names it in its OAuth scope parameter, so no existing connection silently gains it.
| workflows:read | View your workflows and templates |
| workflows:execute | Run your workflows on your behalf (this spends credits) |
| executions:read | View the status and results of your runs |
| models:read | List the available AI models |
| usage:read | View your credit balance and usage |
| automations:read | View your scheduled automations and their run history |
| workflows:write | Create and edit workflows in your accountopt-in |
| automations:write | Create, edit and delete scheduled automations (a schedule spends credits on every run, unattended)opt-in |
| teams:invite | Invite people to your teams (this sends a real email invitation from you, and cannot be unsent)opt-in |
Tools
| whoami | Confirm which Wireflow account this connection acts as |
| list_workflows | List the workflows in your account |
| get_workflow | Inspect a workflow’s nodes and the inputs it accepts |
| list_templates | Browse published template workflows, filtered by category tag or by what the graph contains |
| list_models | List available image / video / audio models |
| get_credit_balance | Check your credit balance and plan |
| clone_template | Copy a template into your account as a private draft (free, exact) |
| create_workflow_from_prompt | Build a new workflow from a description and save it as a private draft |
| update_workflow_config | Change config or prompt values on nodes in a workflow you own |
| get_video_timeline | Read what is in a video node — every scene and clip, its timing, and whether each src is a wired {{token}} or a literal url |
| edit_video_timeline | Replace a video node’s cut through the version-checked writer, and read back what landed |
| preview_video_frames | See still frames of a video node before paying to render it (Lambda stills, no credits) |
| run_workflow | Run a workflow (consumes credits) and get an executionId |
| get_execution | Poll a run for status and output URLs |
| list_automations | List your scheduled automations, their schedules and their last run |
| create_automation | Schedule one of your workflows to run repeatedly (every fire spends credits) |
| update_automation | Pause, arm, rename or re-schedule an automation you own |
| delete_automation | Delete an automation and clear the runs it still had planned |
| invite_teammate | Invite someone to a team you own or administer — sends a real email, and needs the opt-in teams:invite scope |
| send_feedback | Tell the maintainers what blocked you — a bug, a missing capability, a contract that was wrong. Needs no scope and spends nothing |
Only run_workflow spends credits. The three write tools save private drafts and never run anything, so building a workflow costs nothing until you ask for a run.