Steep MCP MCP server
The Steep MCP server allows AI agents to connect to a Steep workspace via the Model Context Protocol. It enables agents to read and query the semantic model, browse the metric catalog, and explore workspace data using the same trusted, governed metrics as the rest of the organization. Authentication is handled via OAuth, ensuring agents only see data the user has access to.
Endpoint and access
OAuth sign-in: the first time you connect, your client opens the vendor's own authorization prompt in a browser.
https://mcp.steep.app/mcpWhat you can do with it
- Query metrics and targets in a Steep workspace
- Browse the metric catalog
- Explore workspace data through a semantic model
- Connect AI models like Claude or Cursor to Steep
Connect from your client
Each snippet registers the same endpoint; pick the client you use.
Claude Code
claude mcp add --transport http steep-mcp https://mcp.steep.app/mcpCodex
codex mcp add steep-mcp --url https://mcp.steep.app/mcpCursor
{
"mcpServers": {
"steep-mcp": {
"url": "https://mcp.steep.app/mcp"
}
}
}Cline
{
"mcpServers": {
"steep-mcp": {
"type": "streamableHttp",
"url": "https://mcp.steep.app/mcp",
"disabled": false
}
}
}VS Code
{
"servers": {
"steep-mcp": {
"type": "http",
"url": "https://mcp.steep.app/mcp"
}
}
}Gemini CLI
gemini mcp add --transport http steep-mcp https://mcp.steep.app/mcpClaude Desktop
{
"mcpServers": {
"steep-mcp": {
"url": "https://mcp.steep.app/mcp"
}
}
}Windsurf
{
"mcpServers": {
"steep-mcp": {
"serverUrl": "https://mcp.steep.app/mcp"
}
}
}Other data and analytics servers
Do you run Steep MCP?
Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.