Connect Close to your AI assistant
How Close connects to your AI assistant: the honest verdict, the tools on offer, and how write safety works, spelled out before you commit.
Every system here gets an honest, affirmative path: verified and instant, buildable and provisioned, human-assisted, or a done-for-you conversation. Zero dead ends.
Where Close stands today
Pipelines, contacts, deals, and activity history: the context an assistant needs at hand when you ask about your book of business.
Also searched as close crm, close io, close.com. The vendor's developer documentation lives at developer.close.com. A machine-readable OpenAPI description is on file.
What a Close connector would expose
The proposal you review during intake, separated into Read and Write. Nothing writes without asking you first.
Generated from the published machine-readable spec, then run through validation gates before going live. The list shown here is a representative preview; the real spec build produces the full tool list.
- search_contacts
Find contacts by name, email, company, or owner
- get_contact
Fetch one contact with its full field set
- list_deals
List deals filtered by stage, owner, or close date
- list_activities
List calls, emails, and notes on a record
- create_contactconfirm
Create a new contact record
fields: name, email, phone, company
- update_deal_stageconfirm
Move a deal to another pipeline stage
fields: stage, probability
- add_noteconfirm
Attach a note to a contact or deal
fields: body
- delete_contactdestructivedry-run
Permanently delete a contact record
fields: id
Every write asks first: it pauses on a preview of the exact change and runs only when you approve it, before anything reaches Close. Turn off anything you never want your AI to touch.
From "Close" to a working connector URL
Designed for operators, not developers. You never read API docs, manage tokens, or touch a line of code.
- 01
Name it
A 30-second eligibility check confirms your AI client accepts a custom connector URL, then you pick the software. This page pre-fills that step.
- 02
Describe what you need
Plain language, not configuration. What should the assistant be able to look up, and what should it be able to change?
- 03
Review your Connector Blueprint
The exact Read and Write tool list, before you pay anything. Every write ships on in confirm mode and asks before it runs, every tool is individually toggled, and anything destructive carries a distinct warning.
- 04
Deploy and paste the URL
You get a hosted connector URL plus paste-in instructions matched to your AI client, and a live test panel that confirms the connection.
Close supports Team mode
Close supports per-user credentials, so each team member connects as themselves: upstream audit trails stay truthful, each member's reach is capped by their own Close permissions, and per-member URLs are individually revocable.
You paste an API key generated in Close. It is encrypted at rest, sent only to Close's API, and destroyed within 24 hours if you cancel.
Write access to Close your IT team will approve
Nothing executes unapproved. Every write runs behind a human confirmation of the exact change, destructive actions demonstrate in dry-run until you graduate them, and any tool can be turned off.
Confirm mode
Enabled writes run through Multi Round-Trip Requests: the tool pauses, shows a human-readable preview of the exact change, and only proceeds with approval. Nothing reaches Close on the model's intent alone.
Guardrails
Any tool can be turned off. Field-level constraints restrict what can be touched, per-tool rate limits are enforced at the gateway edge, and destructive operations ship in dry-run, demonstrating what they would do until you graduate them.
Activity log
Every tool call is logged: who, what, when, result. Write actions and confirmations are highlighted, redaction controls decide how much argument data is stored, and the log is append-only, with updates and deletes refused by the database.
Connecting Close: the specifics
Can my AI assistant write to Close?
Yes, with guardrails. Write tools work out of the box in confirm mode: every write asks first, pausing on a preview of the exact change before anything reaches Close. Destructive operations ship in dry-run and never execute until you graduate them, and you can turn off any tool you never want touched.
Is it safe to connect Close to an AI assistant?
Safety is the architecture, not a setting. Every write asks first: it pauses on a human confirmation with the exact change previewed before it reaches Close. Destructive operations demonstrate in dry-run and never execute until you graduate them, any tool can be turned off, and every call lands in an activity log with redaction controls.
If my team uses a Close connector, whose name is on the actions?
The right one. In Team mode each member connects with their own Close identity, so upstream audit trails show the real person, and each member's effective access is the intersection of the connector's guardrails and their own Close permissions. Per-member URLs are individually revocable.
Which AI clients work with a Close connector?
Any client that accepts a remote MCP connector URL: Claude (Free, Pro, Max, Team, and Enterprise), ChatGPT on paid plans with developer mode enabled, Cursor, and other MCP-compatible clients. Team and Enterprise workspaces may need an admin to allow custom connectors first.
How long until a Close connector is live?
Typically the same day. Close publishes a machine-readable spec, so the pipeline generates the mapping, validates it, and deploys without waiting on a human.
Anything specific to the Close API worth knowing?
Yes. From our index notes on Close: API keys are created per user, so team mode is possible.
More CRM systems
Same category, same connector quality. Every one gets an honest verdict.
Connect Close. We take it from there.
Start a 14-day free trial, no card: live reads plus 3 supervised writes, each executed only after you approve it.