Docs / Connect Claude (MCP)

Connect Claude to your workspace

Falcon Builder ships a built-in Model Context Protocol server, so Claude — on claude.ai, Claude Desktop, Claude Code, or any MCP client — can work inside your workspace: diagnose failed executions, inspect and edit workflows, duplicate them into new variants, run tests, and (if you allow it) publish. Included on every plan.

What you can ask, once connected

“Why did yesterday’s 2pm execution of my intake workflow fail?” — full forensics: status, logs with warnings surfaced first, per-node inputs/outputs.
“Duplicate my Legal Intake workflow as Insurance Intake and rewrite the AI prompt for insurance agencies.” — server-side copy plus targeted node edits, no matter how large the workflow is.
“Fix the condition on step 7 and test it with this sample payload.” — edits touch only the draft; production keeps running the published version until you publish.
“Validate this workflow — will it survive a long polling loop?” — pre-flight checks with a plain-language verdict.
“Publish it” / “roll it back to v4” — only with the publish permission, and every change is audit-logged.

Results link straight back to the editor — workflow names in Claude’s answers are clickable and open the exact workflow, execution, or agent in Falcon Builder.

Option A — One-click connect (claude.ai & Claude Desktop)

In claude.ai (or Claude Desktop), open Settings → Connectors and choose Add custom connector.
Paste the server URL: https://www.falconbuilder.dev/api/mcp — leave the OAuth Client ID and Secret fields empty (registration is automatic).
Click Connect. You’ll be sent to Falcon Builder to sign in (if you aren’t already).
On the consent screen, pick the workspace to connect and the permissions to grant — reading is always included; draft edits, running workflows, and publishing are separate opt-ins.
Approve, and you’re connected. That’s it.

claude.ai Settings showing the Connectors section with the Add menu open and 'Add custom connector' highlighted — Settings → Connectors → Add → Add custom connector.

The Add custom connector dialog with the name 'Falcon Builder' and the MCP URL filled in, OAuth Client ID and Secret left empty — Name it, paste the MCP URL, and leave the OAuth fields empty — registration is automatic.

Falcon Builder's consent screen: signed-in user, a workspace picker, and permission checkboxes for Edit drafts, Run workflows, and Publish & rollback — Pick the workspace and exactly which permissions the connection gets — read is always included, everything else is opt-in.

A toast notification reading 'Connected to Falcon Builder.' — Connected — new chats can now work with your workspace.

Connecting requires owner or admin rights on the workspace. Connections appear in Settings → Developer as “Claude (OAuth)” and can be revoked there at any time. Access tokens rotate automatically every hour.

Turn it on in a chat

In any conversation, open the + menu → Connectors and toggle Falcon Builder on. The first time Claude uses a tool you’ll get a permission prompt — choose Always allow for the read tools to skip future prompts.

The claude.ai chat plus-menu with Connectors open and the Falcon Builder toggle switched on — Enable the connector per chat from the + menu.

A chat asking 'how many agents do i have?' with Claude requesting permission to use the List agents tool from Falcon Builder — First tool call: ask a question about your workspace and approve the tool.

Option B — Access tokens (Claude Code, Cursor, and other clients)

CLI and IDE clients authenticate with a workspace access token instead of OAuth:

In Falcon Builder, open Settings → Developer.
Name the token (e.g. “My Claude Code”), tick the permissions it should carry, and click Create token.
Copy the token immediately — it’s shown exactly once, and only a hash is stored.

Then connect Claude Code:

claude mcp add --transport http falcon-builder \
  https://www.falconbuilder.dev/api/mcp \
  --header "Authorization: Bearer YOUR_TOKEN"

Any MCP client that supports streamable HTTP with a bearer header works the same way. Up to 10 active tokens per workspace.

Permissions & safety model

Read (always included) — inspect workflows, executions, logs, and version history. Everything is scoped to the connected workspace.
Edit drafts — create workflows and modify drafts. Production is never touched: live traffic runs the published version until a publish happens.
Run workflows — execute drafts or live versions with test input. Runs fire real side effects and count against your plan’s execution limit.
Publish & rollback — change what production runs. Treat tokens with this permission like deploy keys.

Additional guardrails: every edit validates before it’s written (a broken patch writes nothing), concurrent editor changes always win over stale chat edits, publish/run require explicit confirmation in the request, every mutation is recorded in the audit trail in Settings → Developer, and requests are rate-limited per token. Tokens are stored as hashes — Falcon never keeps the raw value.

FAQ

Which plans include MCP access?

All of them, including Free. Your plan’s existing workflow and execution limits still apply to what a connected assistant creates or runs.

Can a connection see my other workspaces?

No. Each connection is bound to exactly one workspace at consent time. Anything outside it simply doesn’t exist to the connection.

How do I disconnect?

Settings → Developer → Revoke on the token or OAuth connection. Access stops immediately.

My client doesn’t show new tools after an update.

MCP clients cache the tool list when they connect. Disconnect and reconnect the connector (or start a new Claude Code session) to refresh it.

Create a free workspace Back to docs