Sanity MCP

CALL ANY TOOL

API token scoped per editor. Every GROQ query and document mutation attributed to the authorizing user.

sanity_query

Query dataset

Execute a GROQ query against a Sanity dataset to retrieve documents, filter by type, and project specific fields.

Parameters

Name

Type

Required

Description

query

string

Required

GROQ query string (e.g. *[_type == 'post'] | order(publishedAt desc))

params

object

Optional

GROQ query parameter bindings

sanity_document_get

Get document

sanity_document_patch

Patch document

sanity_document_create

Create document

sanity_assets_upload

Upload asset

Build your Agent

Drop the toolkit in, point it at the authorized editor, and your agent can query and update structured content in Sanity from the first run.

Copied

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["contentfulmcp"], toolNames: ["contentful_entries_search", "contentful_entry_get", "contentful_entry_publish"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

Copied

import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["contentfulmcp"], toolNames: ["contentful_entries_search", "contentful_entry_get", "contentful_entry_publish"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["contentfulmcp"], toolNames: ["contentful_entries_search", "contentful_entry_get", "contentful_entry_publish"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

Copied

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/contentfulmcp",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your content agent to start querying and updating structured content in Sanity MCP.

Search & recall

Copy the prompt

Copied

List all published blog posts in the [dataset] dataset from the last 30 days.

Copy the prompt

Copied

Get the full document for [document ID] including all references.

Copy the prompt

Copied

Run GROQ query: *[_type == "product" && inStock == true]

Create & update

Copy the prompt

Copied

Create a new blog post draft with title: [title] and body: [content].

Copy the prompt

Copied

Update the [field name] field on document [ID] to [new value].

Copy the prompt

Copied

Publish all documents of type [type] that are in draft status.

SEE HOW AUTH WORKS

Editors authorize Sanity once. Their API token stays vaulted, every mutation runs under their identity, and every change is logged.

1

Authorize

Your user connects

Sanity MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

2

Store

Their

Sanity MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

3

Resolve

When your agent calls a

Sanity MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

4

Audit

Every

Sanity MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

Same per-user auth pattern across other CMS and content management connectors.

No items found.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

One vault for every CMS connector. Sanity today, Webflow and Notion tomorrow.

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.

// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Sanity MCP today. Others tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent use a shared Sanity token or per-editor tokens?

Per-editor tokens. Each team member provisions their own Sanity API token and Scalekit vaults it under their identity. Document mutations are attributed to that editor, not a shared bot credential.

Where is the Sanity API token stored?

In Scalekit's AES-256 vault, namespaced per tenant. Keys resolve at request time and never appear in prompts, logs, or LLM completions.

Can I limit the agent to read-only Sanity access?

Yes. Use a read-only Sanity API token and/or listScopedTools to allow GROQ queries and document retrieval but block mutations for users who should not write to the dataset.

What happens when an editor's Sanity token is revoked?

The next tool call fails closed for that user. Other editors in the team remain unaffected. Revocation is logged with a timestamp.

Can the agent publish to Sanity and trigger a Webflow or Vercel deploy in one workflow?

Yes. A single agent can patch Sanity documents and trigger a Webflow CMS publish or a Vercel deploy hook in one workflow. Each connector resolves under the same editor identity with its own vaulted credential.

Tools your content agent reaches for on Sanity, scoped per editor.