Connect Marqeable to Claude: Setup, Permissions, First Test
Short answer (published October 22, 2026): Marqeable’s connector is an MCP server at https://app.marqeable.com/mcp. In Claude (web, desktop or Cowork), open Settings, then Connectors, add a custom connector with that address, click Connect and sign in with your normal Marqeable login. Claude then asks before each tool call, with an Allow always option; allow reads and drafts, keep the prompt for direct changes. It can read your calendar, campaigns, content and automations and write drafts into Marqeable. It cannot send, publish, launch or delete anything.
A Claude Project holds what you uploaded about your marketing. A connector holds your marketing. The difference shows up the first time the offer changes, the calendar fills, or an automation goes live and the Project does not know. This post is the setup for the connector: adding it in Claude, how the approval prompts work, which tools to let run and which to keep behind a prompt, and a first test with the result you should expect. It is written from our own runs in October 2026 and from Anthropic’s custom connector documentation; check the linked page if a setting has moved.
Marqeable is an independent company. Claude is Anthropic’s product, and Marqeable is not made by, endorsed by, or affiliated with Anthropic. What we provide is a connector their assistant can use.
What you need
| Requirement | Detail, as of October 2026 |
|---|---|
| A Claude plan | Custom connectors work on every Claude plan per Anthropic’s documentation, with the Free plan limited to one connector |
| For Team and Enterprise | An Owner adds the connector under Organization settings; each member then clicks Connect and signs in as themselves |
| A Marqeable account | You sign in as yourself. Claude sees exactly what your login can see, on the account you have selected |
| Claude web, the desktop app, or Cowork | The same connector serves all three. Claude Code in a terminal is covered separately |
Step 1: Add the connector
The server address is:
https://app.marqeable.com/mcpIt is a remote server over HTTP with OAuth 2.1. No API key is created, copied or stored anywhere.
- Open Settings, then Connectors.
- Click Add custom connector. Name it Marqeable and paste the address. Click Add.
- Click Connect and sign in to Marqeable in the browser window that opens. If you belong to more than one Marqeable account, the connector uses the one you last selected in the app.
On Team and Enterprise plans, step 2 is done once by an Owner under Organization settings. Step 3 is done by each person; nobody shares a login.
Step 2: Confirm it works
Open a new chat, enable Marqeable in the tools menu, and ask:
Run whoami and tell me which account I am signed in to.
The reply names the signed-in email and the current Marqeable account. If it does not, see troubleshooting below. Nothing else in this post works until this does.
Step 3: Understand the approval prompt
Claude asks before each tool call from a connector. The prompt names the tool and offers two choices: allow this once, or Allow always for that tool. On Team and Enterprise plans, admins can control whether members may always-allow write tools, which is the right control for a workspace.
The useful way to think about Allow always is by what the tool can do at worst:
| Group | At worst | Recommended |
|---|---|---|
| Reads | Nothing changes | Allow always from day one |
| Drafts and suggestions | A draft in your review queue | Allow always once its judgment has stopped surprising you |
| Direct changes | The calendar, a template, the brand look or a live page changes | Allow once, every time |
| Account switches and features | You are working in the wrong account, or a feature is off | Allow once, and only when you asked for it |
Step 4: Know which tools do what
Reads: Allow always
These change nothing. They are what a Project cannot hold: the account as it is right now.
| Tool | What it reads |
|---|---|
whoami, list_accounts | Who is signed in, and to which account |
get_business_context | Current focus, offers, audience and voice |
get_content_calendar, get_marketing_summary | Calendar entries, planned content, suggested dates, the current plan |
list_campaigns, get_campaign, get_campaign_results | Campaigns, their pieces, their numbers |
search_content, get_content, list_content_blocks | Content pieces, briefs, current copy, saved blocks |
list_content_templates, search_image_library, get_image_usages | Templates, existing images, where each image is used |
get_automation_overview, get_automation_plan, get_automation_schedule | Automations, their steps, their timing |
get_event_catalog, inspect_landing_pages, get_landing_page, get_landing_page_analytics, list_form_submissions | What an automation can start on, page states, page numbers, form entries |
check_account_setup, check_campaign_readiness, check_automation_readiness, validate_automation_plan, preview_automation, preview_audience_reach, get_sending_limits, get_open_issues | Checklists, dry runs and anything currently blocking a send |
get_brand_look | The account’s email look |
Drafts and suggestions: Allow always once you trust it
Each of these creates or edits something a person reviews in Marqeable. Nothing reaches a customer.
| Tool | What it creates |
|---|---|
create_campaign_draft, plan_campaign_pieces, add_planned_pieces, remove_campaign_piece, update_campaign_brief, set_campaign_audience, set_campaign_tags | A campaign in draft and the shape of its pieces |
create_content_draft, start_content_build, stop_content_build | A content piece in draft, and its build |
create_automation_draft, update_automation_draft, create_automation_step_content | An automation draft, a proposed revision, draft content for its empty steps |
add_content_suggestion, request_content_changes, insert_content_block | A suggested edit, a change request at a checkpoint, a saved block placed into a draft |
update_content_brief, answer_open_items | Changes to a draft’s brief, answers to the questions a build raised |
update_landing_page, send_test_submission | Edits to a Draft landing page, and a test of its form that creates nothing |
A content build runs for about a minute and can generate images, so ask Claude what images it plans before it starts one.
Direct changes: allow once, every time
| Tool | Why it needs a yes |
|---|---|
add_calendar_entry, update_calendar_entry, adopt_suggested_date, dismiss_suggested_date | Calendar changes feed the next plan directly |
save_content_as_template, set_default_content_template, switch_content_template | Changes what future pieces start from |
update_brand_look, reset_brand_look | Changes the look of every email |
save_content_block | Adds to the blocks everyone can insert |
unpublish_landing_page | Takes a live page down |
decide_automation_matching_hold | Decides what happens to a held automation run |
retry_automation_post | The one tool that acts immediately: it posts a failed or held-back automation post. Confirm every time |
Yours alone
| Tool | Why |
|---|---|
set_feature_enabled | Turns account features on or off. A person’s decision |
switch_account | Only when you explicitly ask for it, and check whoami after |
Never sign in to Marqeable inside a browser the assistant controls, and never paste a password into a chat.
What the connector cannot do, under any setting
There is no tool to send a message, publish content, launch a campaign or turn on an automation. There is no delete tool. Allow always cannot allow an action that has no tool, and that is the point: approval settings drift, the tool list does not. The longer argument is in the draft-only rule.
The honest caveat is the direct-changes table. Calendar, template, brand-look and landing-page tools make real changes, and one tool retries a post. None of them reaches a new customer, but they are why the allow-once group exists.
A first test
Give it a small job with a visible result:
You: Run whoami, then get_business_context, then check my marketing calendar for the next four weeks. If there is a gap against my current focus, draft one campaign to fill it and give me the link. Do not change the calendar.
Expected result: a handful of reads, one campaign draft, and a link to review it in Marqeable. The draft sits in Draft status with nothing built, sent or scheduled. You will have approved one write prompt, for
create_campaign_draft.
Then ask: “List the exact Marqeable tool calls you made, in order.” The answer is your audit of what happened.
If you keep a Claude Project for your brand voice and positioning, keep it. Let the connector own everything that changes weekly: the offer, the calendar, the automations and every draft. Claude Projects vs a connector is the longer version of that split, and the HubSpot connector’s limits covers what to connect alongside it.
Troubleshooting
| What you see | What to try |
|---|---|
| No Add custom connector button | On Team or Enterprise, ask an Owner to add it under Organization settings. On Free, you may already have your one connector |
| Connect succeeds but no tools appear in a chat | Enable Marqeable in the chat’s tools menu, or start a new chat |
| Claude asks before every read | Click Allow always on the read tools; the list above is safe to allow in full |
| Claude wants to open Marqeable’s website | Tell it to use only the connector. Never hand over a password |
| Wrong account | Ask it to run whoami. Switch accounts yourself, deliberately, and run whoami again |
The same server works from ChatGPT (setup guide), from Claude Code with one command (Claude Code for marketing), from Codex, and from an always-on OpenAI dot. The connection is to the account, not to the client, so a team that mixes assistants shares one calendar and one review queue.
Frequently asked questions
How do I connect Marqeable to Claude?
Open Settings, then Connectors, click Add custom connector, name it Marqeable, paste https://app.marqeable.com/mcp, click Add, then Connect and sign in with your normal Marqeable login. On Team and Enterprise an Owner adds it under Organization settings and each member clicks Connect. Then open a chat, enable the connector and ask it to run whoami.
What can Claude do in Marqeable once connected?
Read your business context, campaigns, content, calendar, automations, templates, image library and landing pages, and create drafts: campaigns, content, automations, brief edits, suggestions and change requests. A few tools change the calendar, brand look or templates directly. There is no tool to send, publish, launch or delete anything.
Should I click Allow always on Marqeable tools?
For reads and draft-creating tools, yes once their output has stopped surprising you; the worst outcome is a draft in your review queue. Keep the per-call prompt for tools that change the calendar, brand look, templates or a live page, and for the one tool that retries a post. Workspace admins can control whether members may always-allow write tools.
Can Claude send my campaigns through Marqeable?
No. There is no send, publish, launch or delete tool, and no approval setting can add one. Claude drafts; a person reviews and launches in Marqeable.
The bottom line
Three steps: a custom connector with the address, your own login, and Allow always on the reads and, once you trust it, the drafts. After that Claude works from the account as it is this morning rather than from the documents you uploaded in August, and everything it writes lands as a draft with a link to the page where you approve it. The prompts protect you from surprises; the tool list protects you from everything else.
See where the drafts go: Marqeable’s agents build and run your campaigns, run behavior-triggered automations across text and email, answer and qualify every visitor with AI website chat, and tie revenue to the exact message with attribution.
Marqeable runs your campaigns, answers every visitor, text, and email in seconds, and turns them into booked jobs and meetings - even at 9pm on a Saturday. We’re in private beta with a small early cohort. Get early access
