Claude Lindo AI connectorWhat Claude can do in your Lindo AI workspace.
The Claude Lindo AI connector exposes 10 tools. 2 read your workspace, 7 create, publish or hand things to clients, and 1 is undocumented. Below: what Claude can build for your agency, what it asks first, what Lindo needs from you, and its limits.
Verified Trustpilot reviews · AI, automation & growth agency
What changes once Claude can work in Lindo
Lindo AI is a website builder aimed at agencies. Its connector is a desktop extension for Claude Desktop: once installed, you describe a site or an article in the conversation and Claude asks Lindo to generate it, then can assign it to a client and produce that client's login link, without you switching to the Lindo dashboard.
Spin up a site from a brief. create_website asks Lindo to generate a new website from a text prompt, and list_websites lets Claude check what already exists in the workspace before starting.
Feed the blog. create_blog has Lindo write a post on a given site, while publish_blog puts a static post online from markdown you already have.
Hand the work over to a client. create_client registers the client, assign_website attaches the site to them, generate_magic_link produces their login link and allocate_credits gives them credits to spend.
What Claude cannot do here: the tool called create_page is listed but described by no source, so this page makes no claim about it. Lindo's README also mentions an editing tool absent from the directory sheet. Nothing runs on its own either: generation can be scheduled for later, but only when Claude sets it while answering you. For other integrations, see the Integrations hub.
Five words before you install
The vocabulary around this connector, briefly.
- Connector
- A link you set up once between Claude and an account you already have; for Lindo, it takes the form of a desktop extension.
- Tool
- One named capability the connector hands Claude. Claude picks which to call while answering, and the directory lists them by name.
- Authorization
- The step where you grant Claude access to the service. Granted once per person and withdrawable; for Lindo it involves an API key.
- Approval
- The confirmation Claude waits for before doing something that changes an account, displayed in the conversation at that moment.
- MCP
- The shared standard every connector is built on, which lets an assistant like Claude talk to an outside service.
Connect Lindo AI to Claude in three steps
- 01
Find Lindo AI in Claude Desktop
Lindo AI is a desktop extension, so it lives in Claude Desktop. Open the settings, go to Customize then Connectors, and look it up. On a Team or Enterprise workspace, an Owner or Primary Owner enables a connector before members can each use it.
- 02
Set up the connection
Start the install from its row. Lindo's README says the extension expects your Lindo API key, pasted as LINDO_API_KEY; no Lindo-specific source describes Claude Desktop's exact screens for an extension. If the link misbehaves later, Disconnect and connect again.
- 03
Know what the key opens
Before you confirm, keep in mind that access runs through your Lindo key: that key, on the Lindo side, not Claude, sets what the extension reaches in your workspace. On Claude's side, approval per action stays the default.
The 10 tools: 2 read, 7 write, 1 undocumented
Lindo AI gives Claude 10 tools: 2 that read your account, 7 that change something in it, and 1 no official source describes.
Tool names stay exactly as Claude shows them. The split comes from Lindo's README, not from the names.
- 2 read
- 7 write
- 1 not documented
What Claude reads (2)
2 toolsTwo listing tools that show what is in your workspace without changing it.
list_websites
Returns every website held in your Lindo workspace. Claude reads that list to pick the right site, check names, or spot one that already covers the request.
list_clients
Brings back all the clients registered in your workspace. Claude finds the record to use there before assigning a site or allocating credits.
What Claude creates or changes (7)
7 toolsSeven tools that add or publish something in Lindo. No source describes a confirmation for them, so the general approval rule applies.
create_website
Approval: see the ruleAsks Lindo to generate a brand new website with AI from a text prompt you give Claude. The run can also be scheduled for a later date instead of starting right away.
create_blog
Approval: see the ruleHas Lindo write a new blog post with AI on one of your websites. Like site creation, it accepts a future date if you would rather schedule it.
publish_blog
Approval: see the rulePuts a static blog post live on a site, from markdown content you supply. Unlike the AI writer, this one publishes text you already have.
create_client
Approval: see the ruleRegisters a new client in your Lindo workspace, the record you will later attach sites and credits to.
assign_website
Approval: see the ruleLinks an existing website to a client in Lindo, as the README describes it.
generate_magic_link
Approval: see the ruleProduces a login link a client can use to get into Lindo, a magic link in Lindo's words, which you can then pass on to them.
allocate_credits
Approval: see the ruleGives a client a number of Lindo credits to use. The README describes the allocation, not how credits are priced or consumed.
Undocumented (1)
1 toolListed in the directory, described nowhere. We do not guess what it does from its name.
create_page
The directory lists this name, and Lindo's README, which describes the other tools one line each, does not include it. No official source describes it, so this page adds nothing more.
What Claude checks with you first
By default, Claude stops and asks for confirmation before each action it takes on an account in someone's place.
None of the seven Lindo tools that create or publish has a documented confirmation of its own, so the default rule is what applies to building sites, publishing posts, registering clients, generating login links and allocating credits. On Team and Enterprise, workspace owners decide whether members may let some actions run without a prompt each time, and they can restrict a connector for the whole organization. Claude also works with the access of the person who connected it, through that person's Lindo key, and sees nothing more than that key reaches.
Which plans this works on
Plan availability is published for no individual connector: 0 of the 819 directory sheets shows it.
Anthropic's rule is general. Remote connectors are open to all users on Claude, Cowork, Claude Desktop and mobile, and desktop extensions such as this one install on Claude Desktop. On Team and Enterprise, an Owner or Primary Owner enables a connector before members use it. Lindo's own plan requirement concerns the Lindo side, not Claude. The connector's sheet in the official directory is where its current state appears.
Where this connector stops
A connector is not an automation. Claude calls Lindo while it answers you; a new client signing up or a site going live does not start anything by itself.
Only Lindo documents this connector, through the README of its official package; no Claude help page covers it. The partner badge is not a security audit, and Anthropic says on every sheet that it does not choose the tools a publisher exposes or guarantee their behavior. Scheduling exists, but Claude has to set it while answering. The sheet's description also mentions creating pages, yet create_page is described in no source.
Need help connecting Lindo AI to Claude?
A person reads every message.
