How Sanity Context & MCP Supercharged AI Customer Support in Basegent & Bucket Space

A developer built Basegent, an AI customer support platform, and integrated it with Sanity's Context MCP and Knowledge Base beta to replace traditional vector-search RAG with structured, live-queried policy documents. The integration uses a SanityContextSourceAdapter that calls Sanity's hosted MCP endpoint via JSON-RPC during chat sessions, paired with a multi-provider BYOK inference engine, and was piloted on the developer's Bucket Space bookmarking app.

This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content https://dev.to/challenges/sanity-2026-09-16 Over the past few months, I have been building Basegent https://basegent.space , a modern AI customer support and operations platform. Basegent gives developers and SaaS teams an intelligent chat assistant that can resolve real customer problems, cite official documentation, and escalate smoothly to human operators when confidence drops. At the same time, I run Bucket Space https://mybucket.space —a modern web application built for smart bookmarking, content capture, and personal library organization. Naturally, I wanted Bucket to be the proving ground for Basegent. But as anyone who has deployed AI support bots in production knows, traditional Retrieval-Augmented Generation RAG has a dirty secret: Traditional vector search treats company documentation like a bag of text chunks. It slices policies into arbitrary paragraphs, calculates similarity embeddings, and hopes the LLM can resolve contradictions on the fly. In real-world customer support, this naive approach fails catastrophically: Free vs. Pro , geographical market US vs. EU , or deployment type standard vs. custom . Similarity search has no concept of conditional logic. When Sanity announced the Sanity Context MCP and Knowledge Base beta in Sanity Labs, it clicked immediately. Sanity wasn't just offering another vector database; it was treating context as a managed, structured, verifiable source of truth with built-in conflict resolution and an open protocol Model Context Protocol - MCP . I set out to connect the entire loop: SanityContextSourceAdapter directly into Basegent that talks to Sanity's hosted MCP endpoint, paired with a multi-provider Bring-Your-Own-Key BYOK inference engine. @basegent/react chat widget into Here is the story of how it works, how Sanity Context solved our hardest policy dilemmas, and how you can implement this pattern in your own stack. production . @basegent/client Instead of copying periodic data dumps or storing duplicate content, Basegent queries Sanity Context live during the chat conversation via MCP JSON-RPC: Customer on Bucket Space mybucket.space │ Authenticated Query + Signed Token ▼ @basegent/react Chat Widget │ ▼ SSE / WebSocket Basegent Platform basegent.space │ ┌─────────────┴──────────────────────────┐ │ Multi-Provider BYOI / BYOK Engine │ │ Groq / OpenAI / Anthropic / Google │ └─────────────┬──────────────────────────┘ │ 1. Discover Outline /initial-context 2. Select Virtual Paths 3. Live MCP Tool Call knowledge base read ▼ Sanity Context MCP Endpoint api.sanity.io │ ┌─────────────────┴──────────────────────────┐ │ Sanity Knowledge Base kb3NuTkXw21o │ │ - Reconciled Structured Policies │ │ - Durable Standing Instructions │ │ - Canonical Documentation Citations │ └────────────────────────────────────────────┘ │ ▼ Streamed Answer with Citations & 1-Click Human Escalation To power support for Bucket, I created a dedicated project in Sanity Labs under organization Miracle Onyenma oL4FZOkGh with project ID jk662cms and dataset production . Support policies shouldn't be plain blobs of text. In Sanity Studio, we modeled supportPolicy documents with explicit schema constraints: js // schemas/supportPolicy.ts import { defineType, defineField } from "sanity"; export const supportPolicy = defineType { name: "supportPolicy", title: "Support Policy & Guide", type: "document", fields: defineField { name: "policyKey", type: "string", title: "Policy Key" } , defineField { name: "title", type: "string", title: "Title" } , defineField { name: "claim", type: "text", title: "Core Claim / Rule" } , defineField { name: "appliesTo", type: "object", title: "Applies To", fields: { name: "plans", type: "array", of: { type: "string" } }, { name: "markets", type: "array", of: { type: "string" } }, { name: "productIds", type: "array", of: { type: "string" } }, , } , defineField { name: "effectiveFrom", type: "datetime", title: "Effective From" } , defineField { name: "effectiveUntil", type: "datetime", title: "Effective Until" } , defineField { name: "priority", type: "number", title: "Precedence Priority 0-100 " } , defineField { name: "authority", type: "string", options: { list: "canonical", "legacy", "advisory" }, } , defineField { name: "supersedes", type: "reference", to: { type: "supportPolicy" } } , defineField { name: "sourceUrl", type: "url", title: "Canonical Source URL" } , , } ; We populated this dataset with real Bucket documentation alongside intentional edge cases: priority: 100 , authority: canonical , effective 2026 . priority: 10 , authority: legacy , expired end of 2025 . priority: 90 . Next, in Sanity Context Lab, we built the Basegent Support Policies Knowledge Base kb3NuTkXw21o . This is where Sanity Context shines. Instead of silently averaging out conflicting statements, Sanity actively parsed the documents, analyzed the domain boundaries, and flagged critical ambiguities in the Issues Review dashboard. Sanity flagged a direct conflict between the custom deployment exception 7 days and the legacy global rule 14 days regarding custom products: Sanity highlighted that while the new policy claims to supersede the legacy policy, its applicability was strictly scoped to the US Pro tier, leaving free and non-US tiers potentially ambiguous: With one click in the Sanity interface, we resolved the issue by selecting the source-backed canonical claim. Sanity compiled this decision into a durable standing instruction that automatically survives future dataset rebuilds Once verified, we generated an organization-level Context Viewer token and pointed Sanity's hosted Context MCP endpoint https://api.sanity.io/v1/context/organizations/oL4FZOkGh/mcp/context to this Knowledge Base. In Basegent, every customer support environment lives in an isolated tenant called a Workspace . We created the dedicated Bucket workspace slug: bucket at basegent.space/Account : In Basegent's Sources dashboard /sources/new , we added Sanity Context as a first-party knowledge source, supplying: kb3NuTkXw21o Basegent's core runtime defines a provider-neutral ContentSourceAdapter . To query Sanity live, we implemented SanityContextSourceAdapter : /initial-context When Basegent compiles its retrieval registry, it asks Sanity Context for its virtual outline: // lib/sources/sanity-context-adapter.ts export interface SanityContextConfig { mcpUrl: string; knowledgeBaseId: string; organizationToken: string; } export async function fetchKnowledgeIndex config: SanityContextConfig, connectionId: string, : Promise<string { const url = new URL config.mcpUrl ; url.pathname = ${url.pathname.replace /\/$/, "" }/initial-context ; url.searchParams.set "mode", "knowledge base" ; url.searchParams.set "knowledgeBases", config.knowledgeBaseId ; const response = await fetch url, { headers: { Authorization: Bearer ${config.organizationToken} }, signal: AbortSignal.timeout 15 000 , } ; if response.ok { throw new Error Sanity Context discovery failed with HTTP ${response.status} ; } const initialContext = await response.text ; const entries = parseKnowledgeBaseEntries initialContext, config.knowledgeBaseId ; return Sanity Context Knowledge Base ${config.knowledgeBaseId} , "Available virtual outline paths for live retrieval:", ...entries.map entry = - sanity-context/${connectionId}/${config.knowledgeBaseId}/${entry.path} , , .join "\n" ; } When a customer asks a question, Basegent selects relevant virtual paths and executes the knowledge base read tool live over HTTP: export async function callKnowledgeBaseRead config: SanityContextConfig, path: string, : Promise<string { const response = await fetch config.mcpUrl, { method: "POST", headers: { Authorization: Bearer ${config.organizationToken} , "Content-Type": "application/json", Accept: "application/json, text/event-stream", }, body: JSON.stringify { jsonrpc: "2.0", id: basegent-${Date.now }-${path} , method: "tools/call", params: { name: "knowledge base read", arguments: { knowledgeBase: config.knowledgeBaseId, paths: path , }, }, } , signal: AbortSignal.timeout 20 000 , } ; if response.ok { throw new Error Sanity MCP call error: HTTP ${response.status} ; } const payload = await response.json ; if payload.error throw new Error payload.error.message ; // Extract clean text content from the MCP response const textContent = payload.result?.content ?.filter part: any = part.type === "text" .map part: any = part.text .join "\n" ; return textContent || JSON.stringify payload.result?.structuredContent, null, 2 ; } Customer support agents cannot afford downtime or regional API rate limits. Basegent features a Bring Your Own Intelligence BYOI / BYOK engine that lets teams connect API keys from multiple providers with automatic fallbacks: js // lib/ai/provider-resolver.ts export const SUPPORTED PROVIDERS = "groq", "openai", "anthropic", "google" as const; export const PROVIDER DEFAULT MODELS = { groq: { normal: "openai/gpt-oss-120b", budget: "llama-3.3-70b-versatile" }, openai: { normal: "gpt-4o", budget: "gpt-4o-mini" }, anthropic: { normal: "claude-3-5-sonnet-latest", budget: "claude-3-5-haiku-latest" }, google: { normal: "gemini-2.0-flash", budget: "gemini-1.5-flash" }, }; export async function executeWithFallback<T candidates: Array<{ provider: string; apiKey: string; modelId: string } , action: model: any = Promise<T , : Promise<T { let lastError: unknown; for const candidate of candidates { try { const model = initModel candidate.provider, candidate.apiKey, candidate.modelId ; return await action model ; } catch err: any { lastError = err; if isRateLimitOrQuotaError err { console.warn Basegent AI ${candidate.provider} exhausted, failing over... ; continue; } throw err; } } throw lastError ?? new Error "All configured AI providers failed." ; } Whether running lightning-fast inference on Groq , deep reasoning on Claude 3.5 Sonnet , or cost-efficient answers on Gemini 2.0 Flash , the underlying knowledge remains anchored in Sanity Context. mybucket.space With Sanity and Basegent connected, the final step was integrating the support assistant into mybucket.space https://mybucket.space . Basegent publishes pre-built React components and TypeScript clients directly to npm: npm install @basegent/react @basegent/client When a signed-in user opens the chat, Bucket issues an HMAC-signed customer token via an internal API route. This informs Basegent of the user's plan tier, market, and registration timestamp without exposing private customer data: js // components/shared/BasegentWidget.tsx "use client"; import { useEffect, useState } from "react"; import { BasegentProvider, BasegentChat } from "@basegent/react"; import { useAuth } from "@/components/providers/auth-provider"; export function BasegentWidget { const { user } = useAuth ; const customerToken, setCustomerToken = useState<string | undefined ; useEffect = { if user || user.isAnonymous return; // Retrieve signed JWT/HMAC token with verified plan & market attributes fetch "/api/support/basegent-token", { method: "POST" } .then res = res.json .then data = setCustomerToken data.token .catch err = console.error "Could not sign Basegent token:", err ; }, user ; return <BasegentProvider tenantId={process.env.NEXT PUBLIC BASEGENT TENANT ID } apiBase="https://basegent.space" customerToken={customerToken} <BasegentChat title="Bucket Support" placeholder="Ask about features, shortcuts, or refund policies..." className="bottom-20 sm:bottom-24" showFAB={false} // Hidden in favor of our custom mobile bar trigger / </BasegentProvider ; } On mobile screens, standard floating chat bubbles frequently block critical bottom navigation actions. We integrated a custom support trigger into Bucket's MobileBar.tsx , dynamically hiding the trigger when the user scrolls to the footer credits to preserve UI polish across iPhone, Android, and desktop viewports. The Customer's Situation: A customer who has been on the Pro plan in the United States for 21 days submits this inquiry: "I am on the Pro plan in the US and bought the standard product 21 days ago. Can I still request a full refund, and how long will it take?" What happens behind the scenes: knowledge base read on refund eligibility/standard windows and refund processing . plan: pro , market: US , purchase age: 21 days and confirms they are https://mybucket.space/settings and offers a one-click button to escalate to a human agent. The Customer's Inquiry: "How do I set up the iOS shortcut to bookmark links from Safari?" policy.bucket.guide.ios shortcut directly from Sanity Context. https://www.icloud.com/shortcuts/57316fdc574b4deb97f93b0ff322c685 https://mybucket.space/connect , configure the action sheet, and optionally assign the shortcut to the iPhone 15/16 Action Button. To allow anyone—including challenge judges—to verify live retrieval from our Sanity Context MCP endpoint without needing access to private codebases, here is a self-contained Node.js script: js // test-sanity-retrieval.mjs // Run with: node test-sanity-retrieval.mjs const MCP URL = "https://api.sanity.io/v1/context/organizations/oL4FZOkGh/mcp/context"; const KB ID = "kb3NuTkXw21o"; const TOKEN = process.env.SANITY CONTEXT API TOKEN; async function run { if TOKEN { console.error "Please export SANITY CONTEXT API TOKEN=<your org context token " ; process.exit 1 ; } console.log "1. Fetching Knowledge Base Outline via /initial-context..." ; const outlineRes = await fetch ${MCP URL}/initial-context?mode=knowledge base&knowledgeBases=${KB ID} , { headers: { Authorization: Bearer ${TOKEN} } }, ; if outlineRes.ok { throw new Error Failed to fetch initial context: ${outlineRes.status} ; } const outline = await outlineRes.text ; console.log "Discovered Knowledge Base Outline:\n" ; console.log outline.slice 0, 500 , "...\n" ; console.log "2. Executing MCP tool call 'knowledge base read'..." ; const toolRes = await fetch MCP URL, { method: "POST", headers: { Authorization: Bearer ${TOKEN} , "Content-Type": "application/json", Accept: "application/json", }, body: JSON.stringify { jsonrpc: "2.0", id: "verify-challenge-call", method: "tools/call", params: { name: "knowledge base read", arguments: { knowledgeBase: KB ID, paths: "refund eligibility/standard windows" , }, }, } , } ; const toolPayload = await toolRes.json ; console.log "Sanity Knowledge Base Response:\n" ; console.log toolPayload.result?.content?. 0 ?.text ; } run .catch console.error ; Building this integration fundamentally changed how I view AI customer support: If you are building an AI agent that touches real customers, stop slicing text into dumb chunks. Ground your agent in a real Sanity Knowledge Base—your customers and your support team will thank you.