Power your agent
The publisher's own URL. Not a PlugMCP endpoint.
Host a copy with our keys and logs.
https://mcp.savanto.ai/mcpThe Claude button above opens Claude with the name and URL filled in. You still confirm it there.
claude mcp add --transport http io.github.savantoai-mcp-server https://mcp.savanto.ai/mcpRun in a terminal.
{ "mcpServers": { "io.github.savantoai-mcp-server": { "command": "npx", "args": [ "-y", "mcp-remote", "https://mcp.savanto.ai/mcp" ] } }}claude_desktop_config.json
Remote URL or a command on your machine? How the two installs differ
Run on PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
LaunchFrom the publisher
A local Model Context Protocol server that exposes your Savanto AI workspace to Claude, ChatGPT, Cursor, and any other MCP-compatible client — so you can configure, populate, and operate your store's AI assistant by talking to your own AI, instead of clicking through a dashboard.
Manage your Savanto store from your AI: catalog, content, prompts, and analytics, by chat.
Once configured, your agent gains a curated set of tools that mirror the Savanto REST API, spanning the full configure → observe → refine loop:
Two things keep the surface safe and legible to clients:
/tenant/whoami and only registers tools your key can actually use. An agent is never shown a tool it would get a 403 for, and a publishable widget key sees almost nothing.readOnlyHint, destructiveHint, idempotentHint) so clients can auto-approve safe reads and flag destructive writes; deletes additionally require an explicit confirm: true.The server also exposes Skills (MCP prompts) — step-by-step playbooks for common multi-tool workflows:
onboard-store-end-to-end – create a workspace, ingest content, configure behaviour + branding, smoke-testonboard-wordpress / onboard-shopify – platform-specific onboarding walkthroughsconfigure-chat – tune persona, special instructions, and handoff rulesconfigure-custom-domain – wire a custom capability (order tracking, account lookup) to MCP servers / REST APIsaudit-and-improve – the observe→refine loop: find failing chats / zero-result searches / negative feedback and fix themdebug-empty-search – diagnose why a product search returns no hitsmigrate-from-competitor – bulk-import from another chat vendor's exportif_sk_…). Create one in the API Keys page of your dashboard.
Publishable keys (
if_pk_…) are client-side and cannot provision workspaces — the server will refuse to start with one.
No global install needed — run it with npx:
export SAVANTO_API_KEY=if_sk_your_key_here
npx -y @savantoai/mcp-server
Point to a non-production cloud (staging, local dev):
export SAVANTO_API_URL=http://localhost:3001
In addition to the local stdio server above, the same tool surface can run as a
hosted HTTP server so clients connect to a URL instead of spawning npx —
no local Node, no per-machine config. This is the path toward one-click
"Connect to Claude/ChatGPT" (OAuth) onboarding; today it accepts your secret key
as a Bearer token.
# Each client authenticates per-request — there is NO server-wide key.
SAVANTO_API_URL=https://api.savanto.ai PORT=8080 npx -y -p @savantoai/mcp-server savanto-mcp-http
The server mounts the MCP endpoint at /mcp and a liveness probe at /healthz.
Clients send their key as Authorization: Bearer if_sk_…; the tool surface is
scope-gated to that key's tenant, exactly as in the stdio server. Point an MCP
client that supports remote (Streamable HTTP) servers at
https://your-host/mcp with that bearer token.
Auth is currently the raw secret key. A future release replaces it with OAuth-issued, tenant-scoped tokens so customers can connect with zero key handling — the transport and tool layer are unchanged by that swap.
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"savanto": {
"command": "npx",
"args": ["-y", "@savantoai/mcp-server"],
"env": {
"SAVANTO_API_KEY": "if_sk_your_key_here"
}
}
}
}
Restart Claude Desktop. You should see a hammer/tool icon in the message bar; the Savanto tools are listed there.
In Cursor settings → Features → Model Context Protocol → Add new MCP server:
{
"savanto": {
"command": "npx",
"args": ["-y", "@savantoai/mcp-server"],
"env": { "SAVANTO_API_KEY": "if_sk_your_key_here" }
}
}
Add to the extension's MCP config (usually a JSON file under ~/.cline or similar):
{
"mcpServers": {
"savanto": {
"command": "npx",
"args": ["-y", "@savantoai/mcp-server"],
"env": { "SAVANTO_API_KEY": "if_sk_your_key_here" }
}
}
}
from openai import OpenAI
from mcp import StdioServerParameters
server = StdioServerParameters(
command="npx",
args=["-y", "@savantoai/mcp-server"],
env={"SAVANTO_API_KEY": "if_sk_your_key_here"},
)
npx @modelcontextprotocol/inspector npx @savantoai/mcp-server
The Inspector gives you a web UI to list tools, call them directly, and watch request/response payloads — great for confirming your key is wired correctly before handing the server to an agent.
Once the server is registered in your MCP client, try:
"Set up a new Savanto workspace for
acme-store, crawlhttps://acme.test, give it an outdoor-adventure tone, and brand the widget around#0a7d2c." (end-to-end onboarding)
"Look at
acme-store's last 30 days — what are visitors searching for that returns nothing, and which conversations went unresolved? Then add content to fix the top few." (the observe→refine loop)
"Add an order-tracking capability to
acme-storebacked by our MCP server athttps://mcp.acme.test/orders, validate it, and test it before enabling." (custom domain)
"Why did this conversation get a thumbs-down?" — pull
list_feedback, read the thread, and propose a fix.
The agent picks the right tools automatically (and clients can auto-approve the read-only ones). You can also invoke a Skill explicitly — e.g. in Claude Desktop, /onboard-store-end-to-end or /audit-and-improve kicks off that full playbook.
delete_workspace requires an explicit confirm: true parameter in the tool call — a safety gate against hallucinated destructive operations.From the repo root:
npm install
npm run build --workspace=@savantoai/mcp-server
SAVANTO_API_KEY=if_sk_… SAVANTO_API_URL=http://localhost:3001 node sdks/mcp/dist/stdio.js
Run the tests:
npm run test --workspace=@savantoai/mcp-server
MIT. See LICENSE.
© 2026 MCP Directory.
Manage your Savanto store from your AI: catalog, content, prompts, and analytics, by chat.
{ "mcpServers": { "io.github.savantoai-mcp-server": { "url": "https://mcp.savanto.ai/mcp", "headers": {} } }}Tools
No tool list yet. Remote servers get one after the first health check.
FAQ
Copy the http config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.
The publisher lists these environment variables: SAVANTO_API_KEY.
SavantoAI is reached over HTTP.
Last checked 2026-11-09. Manage your Savanto store from your AI: catalog, content, prompts, and analytics, by chat.