ViablyViably
Claude

Hand Claude your inbox.

Add Viably's MCP server to Claude Code or Claude.ai and sign in once. Claude reads the people waiting on you, the pipeline and the board, and asks before it changes anything. Whatever it does appears in the dashboard and in Slack under your name.

Add to SlackRead the setup guide
Claude Code

what's waiting on me in Viably?

viably.list_inbox (queue: "mine")4 items: 3 people waiting on a reply, 1 Search Console finding
viably.get_contact (id: 985)Michael Scott, lead from the pricing form, unclaimed for 2 days

Michael asked on Tuesday whether annual billing covers extra seats, and nobody has picked him up. I can claim him and leave a draft reply on his record for you to send.

Claude wants to run claim_contactDenyAllow
Connect itRun one command in Claude Code, or paste the server URL into a Claude.ai custom connector, then approve the sign-in
What you needA Viably workspace you belong to. The agent gets your role, so it sees what you see
Up and running in1 minute
On your planEvery plan, with 500 tool calls a month on Free and 15,000 on Viably+
Where it landsYour inbox, pipeline and board, as if you had made the changeThe Slack card of any task or issue it filesThe audit trail on API and agentsTwo-way
What it can reach

Your workspace, as tools an agent can call.

The server lists these to any app that connects. Reads are ticked when you sign in, and each area of changes needs its own tick.

Inbox and contacts

A list shows names only to a member who may also download contacts, since an agent can page through the whole book.
list_inboxfind_contactsget_contactclaim_contactset_contact_statustag_contactadd_contact_notedismiss_inbox_itemsnooze_inbox_item

Deals

Stages come from your own pipelines, and list_deals returns the keys move_deal expects.
list_dealsopen_dealmove_deal

Tasks, issues and the calendar

A task or issue an agent creates posts its card to Slack, the same as one filed from the dashboard.
list_taskscreate_taskupdate_tasklist_issuesget_issuecreate_issueresolve_issuelist_eventscreate_eventset_reminder

Logs, search and signals

Replaying a relay event is for workspace admins.
query_relay_logsreplay_relay_eventsearch_console_summarysocial_summaryuptime_statusgithub_activitymedal_leaderboardsearchwhoami
Sign-in

Reads to start, changes when you tick them.

Claude opens a Viably sign-in in your browser. You pick the workspace and see what Claude may read and what it may change. Reads come ticked, and each area of changes stays off until you tick it.

  • Your role and no more

    A member whose role masks customer names sees them masked through Claude too. Scopes can narrow that access further.

  • A list counts as a download

    Names in a contact list need the download permission, and each list that carries them is logged under Downloads on the Members page.

  • Replies stay with people

    Claude can draft a reply as a note on the contact, and a person on your team reviews it and sends it.

viably.app/oauth/authorize

Connect Claude to Viably

Claude will act in your workspace as you, limited to what your role allows. Untick anything it doesn’t need.

What it can read in Athlead

Your inbox

Contacts

Deals

Tasks

Issues

What it can change

Claim contacts, set their status, tag them and add notes

Open deals and move them between stages

Create tasks, which post to Slack, and change their status, assignee and due date

Create issues and resolve them, noting it in their Slack thread

AllowCancel
In Claude Code

Three saved prompts, run as slash commands.

The server ships prompts that chain the tools the way you would work the dashboard. Type /mcp__viably__triage_inbox and Claude reads your queue, proposes an ending for each item, and acts on the ones you approve.

To bring one record into the conversation, type @viably: and pick a contact waiting on a reply or an open issue. It loads with its deals and timeline before Claude starts.

  • triage_inbox

    Proposes a reply, a task, a dismissal with a reason, or a snooze for each item in your queue.

  • pipeline_review

    Finds deals sitting past their stage's usual pace, follow-ups you missed, and deals without an owner.

  • weekly_digest

    Sums up the week across deals, tasks, issues, search, social, uptime and GitHub, ready to post to the team.

In Slack

What Claude files posts to Slack like anything else.

A task Claude creates posts its card to the channel you named, with you as the author. An issue it resolves gets a note in its Slack thread. API and agents lists every change with the app that made it.

ViablyViably
The Viably kanban board with issue and task cards grouped into open, active, and closed columns
See task management

Every tool on every plan, counted by the call.

Free includes 500 tool calls a month and Viably+ includes 15,000, shared by the whole workspace. A top-up pack adds 3,000 more. Connecting a second app or a second teammate costs nothing extra.

14 days
Viably+ trial.
Seats on every plan
$7
per day, billed annually
3,000
Events each month
The Viably contacts dashboard, the record an agent reads through find_contacts and get_contact
The Viably board, holding tasks and issues filed from Slack, the dashboard and connected agents
The Viably relay log, listing webhook deliveries with their payloads
The people your agent reads and claims, masked exactly as your role masks them in the dashboard.
FAQ

Questions about the Claude integration

How do I connect Claude Code?
Run claude mcp add --transport http viably https://api.viably.app/mcp in a terminal. Then run /mcp inside Claude Code, choose viably, and approve the sign-in in your browser.
How do I connect Claude.ai?
Open Settings, then Connectors, choose Add custom connector and paste https://api.viably.app/mcp. Claude.ai opens the Viably sign-in and keeps the connection renewed.
Do the saved prompts work outside Claude Code?
They are standard MCP prompts, so any app that shows MCP prompts can run them. Claude Code lists them as slash commands, and the tools work in every app whether or not it shows prompts.
Can the agent see anything I can't?
No. Every call runs as you, through the same checks the dashboard runs. If your role hides customer names, the agent gets them masked too, and the scopes you untick at sign-in narrow its access further.
Can it email or message our customers?
No tool sends anything to a customer. An agent can leave a draft reply as a note on the contact, and a person sends it.
What if a customer's message tries to give the agent instructions?
Anyone who writes to your inbox or fills in your form puts text in front of the agent. Viably labels that text as data in every tool result, and no tool can reply to a customer. Keep your app asking before each change, and give an agent that runs unattended read scopes only.
What happens when someone leaves the workspace?
Their agents lose access on the next call. Viably checks the member behind every token each time, so there is nothing to revoke by hand.
Read the full guideConnect Claude and Other Agents (MCP)
Go deeper

Where this leads next

MCP server guide

Setup for each app, what every scope allows, the saved prompts, and the rate limits.

REST API reference

The same tools as HTTP endpoints, for scripts and CI jobs that call Viably without an agent.

More integrations

Connect something else

Everything lands in the same record, so the second service you connect takes less setting up than the first.

Cursor

File issues and read webhook payloads from the editor

Codex

Deals, tasks and relay logs, from the terminal

Slack

@Via coordinates tasks and automations in your Slack channels. Natural language support and emoji-triggered shortcuts.

Ready when you are

Ask Claude what's waiting on you.

Install Viably in Slack, then connect Claude from API and agents. Your inbox has an assistant the same afternoon.

Add to SlackSee pricing
SignalRecordOwned work
  • Free to start
  • No credit card required
  • Powers on when you need them