# Sitegpt MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.sitegpt%2Fsitegpt
Registry id: `mcp-registry/io.github.sitegpt/sitegpt`
Status: auth-required (checked 2026-10-27T03:35:47.648Z)

## Verdict

Sitegpt MCP server answered 100% of Glimind's liveness checks over 30 days, better than 42% of MCP servers, with 165 ms median handshake and 0 outages in 90 days. Its agent-readiness grade is A (97/100) across 17 tools, costing an agent about 4,254 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 100% | 42% of MCP servers |
| Median handshake latency | 165 ms | 75% of MCP servers |
| p95 handshake latency | 396 ms | — |
| Checks in 30 days | 211 | — |
| Outages, 90 days | 0 | — |
| Median recovery | — | — |
| Agent-readiness score | 97/100 (A) | 91% of MCP servers |
| Tools | 17 | — |
| Tool-list size for an agent | ~4,254 tokens | 40% of MCP servers |
| Days observed | 27 | — |

## Install

```json
{
  "mcpServers": {
    "sitegpt-mcp-server": {
      "type": "http",
      "url": "https://sitegpt.ai/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http sitegpt-mcp-server https://sitegpt.ai/mcp
```

## Tools (17)

- `authorize_knowledge_source`: Get a fresh browser authorization URL for an existing knowledge source connection (for example one still pending OAuth). Uses POST /api/v2/chatbots/{chatbotId}/
- `create_knowledge_source`: Create a new OAuth knowledge source connection (Notion, Google Drive, Dropbox, OneDrive, Box, SharePoint, or Confluence) and get the browser authorization URL t
- `execute_read`: Run read-only SiteGPT API v2 calls (GET only) using JavaScript code. Targets the SiteGPT API v2 (spec: https://sitegpt.ai/api/v2/openapi.json, docs: https://sit
- `execute_write`: Create, update or delete SiteGPT API v2 resources (POST, PUT, PATCH or DELETE only) using JavaScript code. Targets the SiteGPT API v2 (spec: https://sitegpt.ai/
- `get_chatbot_analytics`: Get chatbot analytics for the inline analytics card: message counts and feedback split, training/knowledge state (from the chatbot dashboard endpoint), account-
- `get_chatbot_appearance`: Read the chatbot widget appearance (colors, launcher position and shape, title, welcome message, placeholder, tooltip) plus its starter questions, for the inlin
- `get_conversation`: Read one conversation with its transcript (visitor questions and chatbot/system answers, capped at 2000 characters per message). Renders as the transcript panel
- `get_onboarding_status`: Get the live status of an agent-first onboarding workspace: workspace and claim state, the setup checklist (knowledge crawl/training, persona, starters, …), the
- `list_conversations`: List a chatbot conversation inbox with filters (open/resolved status, escalated-only) and cursor pagination, projected to compact rows with a last-message snipp
- `list_escalations`: List the open conversations that are escalated to a human and waiting — the queue behind the inline escalations view — with cursor pagination for queues longer 
- `list_knowledge_sources`: List a chatbot connector data sources (Notion, Google Drive, Confluence, …) with their sync state, plus document counts by ingestion status. Renders as the inli
- `list_leads`: List the leads a chatbot collected (name, email, phone, received time, starred/archived flags) with search, status filter, and cursor pagination. Renders as the
- `preview_chatbot`: Render a live, interactive preview of a SiteGPT chatbot directly in the conversation (MCP Apps extension). Call it after creating or inspecting a chatbot, passi
- `search`: Search the SiteGPT API v2 OpenAPI spec. Targets the SiteGPT API v2 (spec: https://sitegpt.ai/api/v2/openapi.json, docs: https://sitegpt.ai/docs/api-reference/v2
- `send_chat_message`: Send a visitor message to a SiteGPT chatbot and get its answer — the data lane behind the inline chatbot preview's built-in chat. The first call (no threadId) c
- `update_chatbot_appearance`: Update the chatbot widget appearance: title, welcome message, placeholder, tooltip, brand/launcher/link colors (#rrggbb), and launcher position. Only the provid
- `upload_knowledge_file`: Upload one file (base64-encoded, max 1500000 bytes decoded — about 1.5 MB; the MCP transport caps request bodies, larger files go through the dashboard) as chat

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.