Claude Actively connectorWhat Claude can do in your Actively account.
The Claude Actively connector lists 13 tools. 11 read Actively's account research and recommendations, 0 write anything, and 2 have no official description. Here: what Claude can pull before a call, what stays unclear, and who controls access.
Verified Trustpilot reviews · AI, automation & growth agency
What changes for an account executive before a call
Actively holds, for each account, a research profile it calls memory and a strategic recommendation. With the connector, you ask Claude about an account in plain English and it reads that work directly, instead of you clicking through Actively first. Everything runs in your own user and organization context.
Meeting prep in one question. Claude first finds the account with lookup_accounts, by name or Salesforce ID, then reads the agent's full research profile through get_agent_memory and the latest cited signals through get_recent_account_activity.
A deal strategy to react to. get_agent_decisions returns the agent's complete strategic recommendation for one account. You discuss it with Claude, push back, and turn it into your own plan.
Territory review across several accounts. The bulk tools, such as get_bulk_agent_memory, read up to 10 accounts at once, which suits a Monday pipeline pass.
The part the directory sheet leaves out. Actively says its public tools are read-only and built for read-oriented work, yet two listed names, including generate_smart_fields, appear in none of its documentation, so this page cannot say what they do. Nothing runs on its own either: Claude reads this material while it answers you, and no message goes out when an account heats up. That background job belongs to an automation tool, a different line of work covered on the Integrations hub.
Five words before you connect
The vocabulary you will meet while plugging Actively into Claude.
- Connector
- The link you set up once between Claude and an account you already have, so Claude can work in it while it answers you.
- Tool
- One named thing a connector lets Claude do. Claude picks the ones it needs mid-answer, and the directory lists them by name.
- Authorization
- The service's own sign-in screen, where you hand Claude the access it will use. Granted once per person, revocable later.
- Approval
- The confirmation Claude waits for before it goes through with something that changes your account, shown right in the chat.
- MCP
- The shared standard connectors are built on: the piece that lets an assistant like Claude talk to an outside service.
Connect Actively to Claude in three steps
- 01
Find Actively in Claude
In Claude's settings, open Customize, then Connectors, and look for Actively in the list. On a Team or Enterprise workspace, an Owner or Primary Owner has to enable it first, before any member can sign in.
- 02
Start the connection
Click Connect on its row, then sign in with your Actively workspace identity in the window the service opens. If the link ever breaks, use Disconnect and connect again.
- 03
Read the authorization screen
Check the authorization screen before you accept. It belongs to Actively, not to Claude, and it sets what the access covers. That access can also be withdrawn later from the Actively side.
The 13 tools, sorted by what they do
Actively gives Claude 13 tools: 11 that read your account, 0 that change something in it, and 2 no official source describes.
Two groups: what Claude reads, and what no official source describes. Tool names stay exactly as Claude shows them.
- 11 read
- 2 not documented
What Claude reads (11)
11 toolsEleven tools that Actively documents as read-only, non-destructive and closed-world.
get_agent_decisions
Returns the full strategic recommendation Actively holds for one account, the full output rather than selected sections. Claude can then explain it, challenge it or turn it into a call plan.
get_agent_decisions_sections
Fetches only the decision sections you need for one account rather than the whole recommendation. It is the lighter sibling of the full recommendation tool, aimed at one account.
get_agent_memory
Opens the complete research profile the agent keeps for a single account, its memory. Actively's documentation names it the full research profile, as opposed to the section-by-section version.
get_agent_memory_sections
Pulls a chosen subset of an account's memory instead of the full profile, which keeps the answer focused and the call lighter.
get_bulk_agent_decisions
Collects the agents' recommendations for multiple accounts in one go. Actively advises using bulk tools for up to 10 accounts to cut round trips.
get_bulk_agent_memory
Reads research profiles for a batch of accounts at the same time, the memory counterpart of the bulk decisions tool, with the same advice of 10 accounts at most per call.
get_recent_account_activity
Brings back recent signals on an account, each backed by a citation, so Claude can tell you what moved lately and where that information comes from.
get_workflow_instructions
Retrieves the instructions attached to a specific workflow label in Actively. The label is the key: one label, one set of instructions.
list_workflows
Lists the workflow templates available in your Actively workspace, the discovery step Actively lists among the jobs its server is designed for.
lookup_accounts
Searches accounts by name or Salesforce ID and returns the identifier the other tools need. Actively recommends calling it first, then using that ID for memory and decision lookups.
search_agent_memory
Runs a semantic search across account memory, meaning it matches ideas rather than exact words. Claude can surface accounts where a theme comes up without you naming them.
Not documented (2)
2 toolsThe directory lists these two names and nothing else. No official text says what they do, so this page will not guess from a name.
generate_smart_fields
This name appears in the directory's tool list, and that is all. Actively's documentation describes eleven public tools and this is not one of them, so no source documents it.
get_smart_field_schemas
Same situation for this second name: listed on the directory sheet, yet no source documents it, neither the publisher's public tool list nor Claude's help center. Flagging the gap beats filling it with a guess drawn from the wording of the name.
What Claude asks before acting
By default, Claude stops and asks for your go-ahead before every action it takes on an account on your behalf. The request shows up in the conversation, at the moment it matters.
On Team and Enterprise, workspace owners decide whether a member can let some actions through without being asked each time. They can also cap what a connector may do for the whole organization, for example keeping reads open and closing writes. Nobody overrides that from their own account. On Actively's side, tools run in the context of the signed-in user and organization, and what they show follows your organization's permissions.
Which plans it works on
Out of 819 sheets in the official directory, not one shows availability by plan. That answer, connector by connector, is published nowhere: it is a real gap in the catalog.
The general rule is public: remote connectors are open to all users on Claude, Cowork, Claude Desktop and mobile. On Team and Enterprise, an Owner or Primary Owner enables the connector for the organization before each member can connect. For the current state of this one, check the Actively sheet in the official directory from your own account.
Where this connector stops
A connector is not an automation. Claude calls these tools while it answers you: nothing fires when an account shows a new buying signal.
A tool list that only shows reads is an observed floor, not a promise: an admin can open actions that appear on no public sheet. The partner badge is not a security audit either, and Anthropic says so on every sheet: it does not choose the tools a publisher exposes and does not guarantee they behave as described. This connector is documented only by its publisher; neither Claude's help center nor Anthropic's developer docs have a page for it. For another sales-side connector, see the Claude affinity connector.
Need help connecting Actively to Claude?
A person reads every message.
