AI agents (MCP)

Connect Claude — or any MCP client — to FounderDB so it can triage your inbox, reply and follow up from your mailboxes, and keep your to-dos. Everything it does is recorded as the agent's, not yours.

Connect

claude.ai (and Claude Desktop / mobile)

In Claude, open Settings → Connectors → Add custom connector.
URL: https://founderdb.co/api/mcp. Leave the OAuth client on Use Claude's published identity (recommended) — nothing else to fill in.
Click Connect. You'll sign in to FounderDB, choose how the agent's actions are labelled (“Claude”), and allow access.

FounderDB supports OAuth 2.1 for MCP: Client ID Metadata Documents, dynamic client registration, PKCE (S256), and refresh tokens that rotate. Connections show in Settings → AI agents, where you can disconnect them.

Claude Code and other clients, with a token

Or skip OAuth: in FounderDB, open Outreach → Settings → AI agents (MCP). Name the agent (e.g. “Claude” — that's how its actions are labelled) and create an access token. Copy it; it's shown once.
Add the server to your client.

Claude Code

claude mcp add --transport http founderdb https://founderdb.co/api/mcp also works without a token — Claude Code will open the FounderDB sign-in. Or pass a token:

claude mcp add --transport http founderdb https://founderdb.co/api/mcp \
  --header "Authorization: Bearer fdb_…"

Other MCP clients

config

{
  "mcpServers": {
    "founderdb": {
      "type": "http",
      "url": "https://founderdb.co/api/mcp",
      "headers": { "Authorization": "Bearer fdb_…" }
    }
  }
}

The server speaks MCP over Streamable HTTP (stateless JSON responses) and supports protocol versions 2025-06-18, 2025-03-26 and 2024-11-05. A client that only supports stdio can use a bridge such as npx mcp-remote https://founderdb.co/api/mcp --header "Authorization: Bearer fdb_…".

What the agent can do

Tool	Does
`list_inbox`	Conversations that need you (view todo), or all / snoozed / done
`get_contact`	One contact: details, stage, variables, sequences, open to-dos and the email thread
`search_contacts`	Find contacts by name, email, handle, stage or tag
`send_email`	Send now or schedule (send_at) from one of your mailboxes; continues an existing thread
`list_scheduled_emails`	Emails queued to go out
`cancel_scheduled_email`	Cancel one that hasn't gone out
`add_note`	Private note on a conversation
`set_stage`	Move a contact in the pipeline
`set_contact_variables`	Set or unset contact variables
`list_variable_definitions`	Your defined variables and their types
`triage_contact`	Mark done, snooze until a time, or reopen
`list_todos / create_todo / update_todo`	Your to-do list
`list_quick_actions / create_quick_action / update_quick_action`	Inbox buttons: reply (AI or fixed), tags, stage, stop sequence
`delete_quick_action / reorder_quick_actions / run_quick_action`	Remove, order, or run one on a contact
`list_templates / get_template / create_template / update_template / delete_template`	Email templates, with deliverability warnings and a per-contact preview
`list_sequences / get_sequence`	Sequences, with a readable outline of each flow and every step's settings
`create_sequence / duplicate_sequence / update_sequence_settings / delete_sequence`	Start blank or from the starter flow; send window, weekends, caps, AI settings
`add_sequence_step / update_sequence_step / remove_sequence_step`	Edit a flow step by step: emails, waits, reply waits, AI intent branches, stages, variables, API calls, conditions
`connect_sequence_steps / disconnect_sequence_steps / replace_sequence_flow`	Rewire paths, or replace the whole flow
`simulate_sequence`	When each step would run, for chosen branch outcomes
`enroll_contact / stop_sequence_for_contact / resume_sequence_for_contact`	Start, stop or resume a sequence for a contact
`get_setup_overview`	How everything is configured and how it's doing: mailboxes, domains, sequences, AI key, queue, failures, bounces
`get_account_report / get_daily_report / get_sequence_report`	Deliverability per mailbox (bounce, reply, open, complaint rates), per-day activity, sequence funnels
`inspect_send_queue`	What's due, scheduled per day and mailbox, failed and why; queue health
`list_activity_log / list_send_log / list_sequence_runs`	What happened: replies, bounces, stage moves, sends, and each sequence step taken
`list_integration_calls / list_agent_actions`	External API calls, and the agent audit log
`list_sending_accounts`	Your mailboxes and whether they can send
`list_receiving_addresses`	Where replies are received and forwarded

Try asking: “Go through my FounderDB to-do inbox, draft replies, and send the ones I approve.”

Editing sequences safely

Every change is validated before it's saved; an invalid flow is never stored.
A change that removes the step contacts are currently on is refused, with how many contacts it affects, unless the agent passes force.
Removing or rewiring a step never silently deletes the steps after it — the agent has to ask for that with remove_cut_off.
New sequences start disabled; deleting one needs its exact name. Steps are laid out automatically, so the builder shows the agent's changes neatly.

Sending email

send_email really sends from your mailbox. If you've emailed the contact before, it continues that thread from the same mailbox; otherwise it needs a subject and starts a new one.
Pass send_at (ISO 8601) to schedule a follow-up. Scheduled emails show in the conversation, marked as the agent's, until they go out, and can be cancelled with cancel_scheduled_email.
Contacts marked do not contact can't be emailed.

Everything is on the record

Every tool call — reads too — is logged in Outreach → Agent activity: which agent, what, when, which contact, what it sent, and whether it worked. Filter by agent, action or result.
Emails the agent sends are labelled “Claude · AI agent” in the conversation instead of “You”. Its notes, stage moves, snoozes and variable changes are labelled too.
To-dos it adds say “Added by Claude”.

A token gives the agent the same reach as you in outreach. Give each agent its own token, and revoke it in Settings when you stop using it — it loses access immediately, and its history stays.