← Registry

Design

tseha.io

Provides access to a design system's projects, packages, and UI components, with detailed specifications, usage examples, and Figma references.

1 endpoint9 known toolsFirst detected August 23, 2026Last detected August 23, 2026

ENDPOINT 1

https://tseha.io/mcp

No auth detected

MCP server metadata

Name
tseha-mcp
Version
1.0.1
Capabilities
tools
Server instructions

You are talking to Tseha - a design system and development standards source of truth - but this request carried no credentials, so no tools can be called. ## What to do Tell the user, in your own words: 1. The Tseha MCP server is reachable and this client is compatible with it. 2. Nothing can be fetched until the connection is authenticated. Every tool requires a bearer token. 3. Connection instructions are at https://tseha.io/docs. 4. If they have no Tseha account yet, they can create one at https://tseha.io/login. Do not call any tool until the connection is authenticated - each one will refuse.

Known tools 9

list_projects

Lists the projects in this organization, each with its id, name, and framework.

Inferred read-only
list_packages

Lists the component packages assigned to a project, each with its name, version, and description, and marks which one is active.

Inferred read-only
list_components

Lists every UI component in the project's design system, each with its name, source package, import path, and a short note on its intended use.

Inferred read-only
get_component

Returns the full specification for one component: import path, props schema, usage example, anti-patterns, when-to-use and when-not-to-use notes, Figma spec, and dependencies.

Inferred read-only
search_components

Searches the components of every package assigned to the project by use case, behavior, or description, and returns up to 10 ranked matches with a relevance score.

Inferred read-only
get_style

Returns metadata for the project's active style: the style name, its Figma file key, when it was last synced, and a token count per available category (such as color, typography, spacing).

Inferred read-only
get_style_tokens

Returns the project's design tokens with their names, values, and token paths.

Inferred read-only
get_standards

Returns the organization's development standards: coding conventions, project structure, and framework-specific rules.

Inferred read-only
get_component_updates

Returns per-component breaking changes and a migration guide between an installed version of the project's active component package and the latest published version.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.tseha-mcp]
url = "https://tseha.io/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "tseha-mcp": {
      "type": "http",
      "url": "https://tseha.io/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: tseha-mcp
Remote MCP URL: https://tseha.io/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "tseha-mcp": {
      "url": "https://tseha.io/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "tseha-mcp": {
      "type": "http",
      "url": "https://tseha.io/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "tseha-mcp",
  "transport": "streamable-http",
  "url": "https://tseha.io/mcp"
}
MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.