Prismic MCP Server
for AI Agents
Connect your AI agent to StackOne's Prismic MCP server and give it 24 MCP tools out of the box. Auth, tool execution, and security all managed.
StackOne 
Coverage
24 Agent Actions
Create, read, update, and delete across Prismic — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Prismic MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Prismic tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Prismic call.
Tools Discovery →What is the Prismic MCP Server?
A Prismic MCP server lets AI agents read and write Prismic data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Prismic MCP server ships with 24 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.
All Prismic MCP Tools
Every action from Prismic's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Documents
- Create Document
Create a new document as a draft via the Migration API
- Search Documents
Query and search documents with filters, sorting, pagination, and field selection
- Update Document
Update an existing document via the Migration API
Custom Types
- Create Custom Type
Insert a new custom type into the repository
- List Custom Types
Retrieve all custom types in the repository
- Get Custom Type
Retrieve a specific custom type by its API ID
- Update Custom Type
Update an existing custom type in the repository
- Delete Custom Type
Delete a custom type from the repository
Shared Slices
- Create Shared Slice
Insert a new shared slice into the repository
- List Shared Slices
Retrieve all shared slices in the repository
- Get Shared Slice
Retrieve a specific shared slice by its API ID
- Update Shared Slice
Update an existing shared slice in the repository
- Delete Shared Slice
Delete a shared slice from the repository
Assets
- Upload Asset
Upload a new asset to the media library
- List Assets
Retrieve assets from the media library with filtering and cursor-based pagination
- Update Asset
Update metadata of an existing asset
- Delete Asset
Delete an existing asset from the media library
Asset Tags
- Create Asset Tag
Create a new tag for organizing assets in the media library
- List Asset Tags
Retrieve all asset tags from the media library
Repositorys
- Get Repository
Get repository metadata including refs, types, languages, and configuration
Tags
- List Tags
Retrieve all tags from the repository
Push Integration Items
- Push Integration Items
Push or update items in an integration field catalog
Reset Integration Catalogs
- Reset Integration Catalog
Clear all items from an integration field catalog
Integration Items
- Delete Integration Items
Delete specific items from an integration field catalog
Set Up Your Prismic MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Prismic in under 10 lines of code.
Agent Frameworks
JSON{
"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>"
]
}
}
}Check More Documents & Knowledge MCP Servers
134+ actions
101+ actions
96+ actions
95+ actions
92+ actions
80+ actions
80+ actions
Platform Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
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
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
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
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
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: Architecture, Security, and When to Use Each
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 vs API: What 200+ Connector Builds Taught Us
MCP wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.
14 min read
Prismic MCP Server FAQ
Does StackOne have a Prismic MCP server?
Prismic MCP server vs direct API integration — what's the difference?
How does Prismic authentication work for AI agents?
origin_owner_id.Are Prismic MCP tools vulnerable to prompt injection?
What is the context bloat of a Prismic agent and how do I avoid it?
Can I limit which actions my Prismic agent can access?
Can I create custom agent actions for my Prismic MCP server?
When should I NOT use a Prismic MCP server?
What AI frameworks and AI clients does the StackOne Prismic MCP server support?
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.