Claude Tseha.io connectorWhat Claude can do in your Tseha.io account.
The Claude Tseha.io connector exposes 9 tools: 9 read, 0 write, 0 undocumented. They let Claude look up your organization's projects, component packages, UI components, design tokens and development standards before it writes front-end code, instead of guessing them.
Verified Trustpilot reviews · AI, automation & growth agency
What changes when Claude reads your Tseha.io standards
An assistant that writes interface code from memory tends to invent component names, props and colors that do not exist in your design system. With this connector, Claude asks Tseha.io first: which components your project uses, how they are imported, which tokens hold your real colors and spacing, and what your team's coding rules say.
The right component, with the right props. search_components finds candidates from a plain description of the need, then get_component returns the full spec: import path, props, usage example, anti-patterns and when not to use it.
Real theme values instead of made-up hex codes. get_style_tokens returns your design tokens by category, so colors, typography and spacing come from your style, not from a guess.
An upgrade planned before it breaks. get_component_updates lists breaking differences and a migration guide between your installed package version and the latest one.
What it will not do: Tseha.io states that its server is read-only for every role, and that writing happens only in its admin panel. Claude does not install packages, run an upgrade or edit your standards through this connector. And nothing runs by itself: Claude calls these tools while it answers you. If you need a recurring job, such as a nightly report, that belongs to an automation platform; see the Integrations hub for the ones we cover.
Five words before you plug it in
Claude's vocabulary around this connector, in one minute.
- Connector
- The link you set up once between Claude and an account you already have, so Claude can use it while it answers you.
- Tool
- One named capability a connector opens to Claude. Claude picks which ones to call; the directory sheet lists all of them by name.
- Authorization
- The sign-in screen of the service, where you grant the access Claude will use. For Tseha.io, a browser sign-in. Per person, revocable.
- Approval
- The confirmation Claude waits for before changing something in an account on your behalf, shown in the chat at the right moment.
- MCP
- The shared standard connectors are built on: it is what lets an assistant like Claude query a service such as Tseha.io.
Connect Tseha.io to Claude in three steps
- 01
Find Tseha.io in the connector list
Open Claude's settings, go to Customize, then Connectors, and look for Tseha.io. On a Team or Enterprise workspace, an Owner or Primary Owner enables it for the organization before members connect individually.
- 02
Sign in once
Click Connect on its row. Tseha.io says the first connection opens a sign-in in your browser, which you approve once. If the link breaks later, Disconnect it and connect again.
- 03
Read the authorization screen
Look at what the Tseha.io screen asks before you accept. It is the service's screen, not Claude's, and it decides what the access covers. You can take that access back later the same way.
The 9 tools, sorted by what they do
Tseha.io gives Claude 9 tools: 9 that read your account, 0 that change something in it.
All nine read. Tseha.io describes each one in the tool list its service publishes, and the names stay exactly as Claude shows them.
- 9 read
What Claude reads (9)
9 toolsNine tools that look up projects, components, tokens and rules without touching them.
get_component
Returns everything about one component: import path, props schema, usage example, anti-patterns, when to use it and when not, its Figma spec and dependencies.
get_component_updates
Reports, component by component, what breaks between the package version you have installed and the latest published one, along with a migration guide. It only reports; it never performs the upgrade.
get_standards
Gives your organization's coding conventions, project structure and framework-specific rules. A first call returns an index of sections; a second call fetches the one section a task needs.
get_style
Describes the project's active style: its name, its Figma file key, the last sync date and how many tokens each category holds. It names categories but returns no values.
get_style_tokens
Lists the project's design tokens with their names, values and paths, for one category such as color, typography, spacing, radius, shadow or blur, or for all of them at once.
list_components
Returns the whole catalog of UI components assigned to a project, each with its name, source package, import path and a short note on its intended use, in one unpaginated answer.
list_packages
Shows the component packages assigned to a project, with name, version and description, and flags which one is active.
list_projects
Lists your organization's projects with their id, name and framework. The id it returns is the project reference every other Tseha.io tool expects.
search_components
Searches every package assigned to a project from a description of the need, its use case or its behavior, and returns up to 10 ranked matches with a relevance score.
What Claude asks before acting
Claude's default is to stop and ask before any action it takes on an account for you. Every Tseha.io tool listed here reads, so in normal use there is nothing for Claude to confirm.
On Team and Enterprise workspaces, owners decide whether members may let some actions through without a new prompt, and they can restrict what a connector does for the whole organization. Claude works with the rights of the person who connected it, and Tseha.io adds that access follows your organization and your role, re-checked on every request. The official per-tool read or write label only appears inside a connected account's settings.
Which Claude plans include it
None of the 819 sheets in the official directory shows availability by plan. Connector by connector, that answer is not published anywhere.
The published rule is general: remote connectors are open to all users on Claude, Cowork, Claude Desktop and mobile, and on Team and Enterprise an Owner or Primary Owner turns a connector on before members connect. Tseha.io's own subscription tiers are a separate matter and only affect two of its tools. For this connector's state, open its directory sheet.
Where the Claude Tseha.io connector stops
A connector is not an automation. Claude reads Tseha.io while it answers you; nothing fires when a component or a token is updated on the Tseha.io side.
A tool list made only of reads is an observed floor, not a guarantee: an admin can open actions that no public sheet shows. The directory's verification badge is not a security audit, and Anthropic says on every sheet that it does not decide a publisher's tools. Only Tseha.io documents this connector, in its own docs and tool descriptions; no Claude help article or Anthropic developer page covers it.
Need help connecting Tseha.io to Claude?
A person reads every message.
