Skip to main content

The #1 agentic semantic tool search: 91.6% first-try accuracy on S1 Search Bench • Explore Tool Discovery →

Live 24 Actions

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.

Start Free Book Demo Read Docs →
Prismic logo
Prismic MCP Server
Built by StackOne StackOne
DrataGPLocalyzeFlipMindtoolsScreenloop

Coverage

24 Agent Actions

Create, read, update, and delete across Prismic — and extend your agent's capabilities with custom actions.

MCP Actions → Build 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.

MCP Clients

Claude Desktop setup guide
Claude Code setup guide
Cursor setup guide
Goose setup guide

Agent Frameworks

Claude Desktop
{
  "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

Confluence

133+ actions

Lokalise

101+ actions

ClickUp

95+ actions

Liferay

92+ actions

Google Shopping

80+ actions

Discourse

67+ actions

Contentful

58+ actions

All Documents & Knowledge MCP Servers →

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

Prismic MCP Server FAQ

Does StackOne have a Prismic MCP server?
Yes. StackOne offers a hosted Prismic MCP server with 24 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.
Prismic MCP server vs direct API integration — what's the difference?
A Prismic MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Prismic. A Prismic MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Prismic at runtime. StackOne provides both.
How does Prismic authentication work for AI agents?
Prismic authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Prismic account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are Prismic MCP tools vulnerable to prompt injection?
Yes — Prismic MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Prismic agent and how do I avoid it?
Context bloat happens when Prismic tool schemas and API responses eat your Prismic agent's memory, preventing it from reasoning effectively. A single Prismic query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Prismic agent can access?
Yes — you can limit which actions your Prismic agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Prismic MCP server?
Yes — you can create custom agent actions for your Prismic MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Prismic's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Prismic MCP server?
Skip a Prismic MCP server if your integration is purely software-to-software — direct Prismic API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Prismic actions at runtime.
What AI frameworks and AI clients does the StackOne Prismic MCP server support?
The StackOne Prismic MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

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.

Start Free Book Demo