Connect
Optimize
Secure
The #1 agentic semantic tool search: 91.6% first-try accuracy on S1 Search Bench • Explore Tool Discovery →
Connect your AI agent to StackOne's Sanity MCP server and give it 34 MCP tools out of the box. Auth, tool execution, and security all managed.
Coverage
Create, read, update, and delete across Sanity — and extend your agent's capabilities with custom actions.
Authentication
Per-user OAuth in one call. Your Sanity MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →Security
Every Sanity tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →Performance
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Sanity call.
Tools Discovery →A Sanity MCP server lets AI agents read and write Sanity data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Sanity MCP server ships with 34 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
Every action from Sanity's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Query documents with GROQ
Get a document by ID
Create a dataset
Copy a dataset
Export all documents in a dataset
List datasets
Update a dataset
Delete a dataset
List projects
Get a project by ID
Update a project
Create a project tag
Update a project tag
Delete a project tag
List users and their roles
Get a user and their roles
List available permissions
Get a permission by name
List assignable roles
Get a role by name
Invite a user to a resource
List invites for a resource
Upload an image asset
Upload a file asset
Get the revision history of a document
List dataset copy jobs
List tags assigned to a dataset
List access requests for the project
Remove a tag from a dataset
Create, update, patch or delete documents
Link a Media Library asset into a dataset
Assign a tag to a dataset
Replace the set of roles assigned to a user
Revoke an invite
One endpoint. Any framework. Your agent is talking to Sanity in under 10 lines of code.
Agent Frameworks
{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}134+ actions
101+ actions
96+ actions
95+ actions
92+ actions
80+ actions
67+ actions
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.
12 min
MCP wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.
14 min read
origin_owner_id.All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.