Plasmic MCP server

Connect Plasmic to Claude, ChatGPT, Cursor, Claude Code, Codex, Gemini, GitHub Copilot and any other MCP client, for your whole team. Metorial adds security, governance, and tracing, and gives everyone one Magic MCP URL to connect.

What you can do with the Plasmic MCP server

Ask your agent in plain language. Each of these maps to a real tool on the server.

  • Use the count cms items tool in Plasmic
  • Use the query cms items tool in Plasmic
  • Use the get project model tool in Plasmic
  • Use the publish cms item tool in Plasmic
  • Use the delete cms item tool in Plasmic
  • Use the create cms item tool in Plasmic

Supported Tools

count_cms_items

Count CMS Items

Count the number of items in a Plasmic CMS model, optionally filtered by field conditions. Uses the same query syntax as the Query CMS Items tool but returns only the count.

query_cms_items

Query CMS Items

Query items from a Plasmic CMS model with optional filtering, pagination, and ordering. Supports a JSON-based query syntax with logical operators (`$and`, `$or`, `$not`) and conditional operators for filtering by field values. Can load draft or published versions and localized content.

get_project_model

Get Project Model

Retrieve the full JSON representation of a Plasmic project structure via the Model API. Returns all components, pages, design tokens, metadata, A/B tests, custom targets, and scheduled content. The response includes element trees (TplNodes) for each component.

publish_cms_item

Publish CMS Item

Publish a draft content entry in a Plasmic CMS model, making it publicly visible. Requires the CMS secret token.

delete_cms_item

Delete CMS Item

Permanently delete a content entry from a Plasmic CMS model. This action cannot be undone. Requires the CMS secret token.

create_cms_item

Create CMS Item

Create a new content entry in a Plasmic CMS model. The item can optionally be published immediately upon creation. Requires the CMS secret token.

render_component

Render Component

Render a Plasmic-designed page or component as HTML via the Render API. Returns plain HTML that can be embedded anywhere. Supports rendering in preview, published, or versioned mode, with optional JavaScript hydration for interactivity. Component props and global variants can be customized.

update_project

Update Project

Programmatically create or update components, pages, and design tokens in a Plasmic project via the Write API. Components can be matched by UUID, name, or path for updating. Design tokens support colors, spacing, fonts, shadows, and other styling values. **Requires a project secret token (enterprise only).**

update_cms_item

Update CMS Item

Update an existing content entry in a Plasmic CMS model. Only the specified fields will be modified. The item can optionally be published after updating. Requires the CMS secret token.

list_cms_models

List CMS Models

List models and their field definitions in the connected Plasmic CMS database. Use each model identifier as modelId in CMS content tools.

get_cms_item

Get CMS Item

Retrieve one Plasmic CMS item using a field filter such as a unique slug. Call list_cms_models to discover model identifiers and fields. Returns null when no item matches.

create_cms_items

Create CMS Items

Create multiple content entries in a Plasmic CMS model in one request, optionally publishing them immediately. Call list_cms_models to find model identifiers and field definitions. Requires the CMS secret token.

Connect Plasmic to your AI client

Every client uses the same Magic MCP URL, and so does any other MCP client. Add it once and sign in with SSO.

  1. Enable Plasmic in Metorial. In your Metorial portal, enable the Plasmic MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
  2. Add a custom connector. Open Customize, then Connectors. Select Add, then Custom, then Web.
  3. Paste your Metorial MCP URL. Name it Metorial, paste your Magic MCP URL (<your-magic-mcp-url>) and continue.
  4. Sign in. Select Add and sign in to load Plasmic tools.

Run Plasmic through the Metorial gateway

One governed layer for every app your agents reach, not a separate connector per tool.

  • Give Plasmic and every other app to your whole team through one MCP gateway, behind your SSO.
  • Scope which teams and agents can use Plasmic tools with role-based access control, and trace every call.
  • Prefer to run it yourself? Metorial is open source and self-hostable.

More integrations teams use with Plasmic

Notion

Create, read, update, and archive pages and databases in a Notion workspace. Manage blocks (paragraphs, lists, headings, embeds, etc.) within pages. Query databases with filters and sorts across rich property types including text, numbers, dates, selects, relations, and formulas. Search across pages and databases by title. Add and read comments on pages and blocks. Upload files to pages. Manage workspace users and retrieve user profiles.

Google Sheets

Create, read, and update spreadsheets and their cell data. Read and write values to individual cells, ranges, or multiple ranges using A1 notation or named ranges. Apply cell formatting including text styles, backgrounds, borders, number formats, and conditional formatting. Manage sheets (tabs) within a spreadsheet—add, delete, copy, rename, and reorder them. Create and manage embedded charts, pivot tables, filter views, data validation rules, protected ranges, named ranges, and merged cells. Perform batch operations to apply multiple updates atomically.

Sharepoint

Manage SharePoint sites, document libraries, lists, and files. Create, read, update, and delete lists and list items with custom columns. Resolve site users to numeric Person/Group LookupId values. Upload, download, move, copy, and version files in document libraries. Search across sites, files, folders, lists, and list items using Microsoft Search. Manage permissions at site, list, and item levels with granular access control. Define and manage content types and site columns. Retrieve site properties and search for sites across Microsoft 365.

Google Drive

Upload, download, create, copy, move, rename, trash, and permanently delete files and folders in Google Drive. Search for files using complex queries filtering by name, MIME type, owner, modification date, labels, and other metadata. Share files and folders with specific users, groups, or domains with role-based permissions (owner, writer, commenter, reader). Manage shared drives and their members. Export Google Workspace files (Docs, Sheets, Slides) to standard formats like PDF, DOCX, and XLSX. Track file revision history and restore earlier versions. Create, read, update, and delete threaded comments and replies on files. Read label definitions and search files by label. Browse the Drive apps installed for your account. Store app-specific data in a hidden per-user folder.

Confluence

Create, read, update, and delete pages, blog posts, comments, and attachments in Confluence spaces. Manage spaces, permissions, labels, and content restrictions. Search content using Confluence Query Language (CQL). Upload and download file attachments with versioning. Manage users, groups, and group memberships. Create and manage whiteboards, databases, folders, and templates. View and update inline tasks. Access audit logs.

Google Slides

Create, read, edit, and delete Google Slides presentations. Create and manipulate slides with predefined or custom layouts. Insert, style, and replace text across slides, including bulk placeholder replacement for template-based generation. Add and position shapes, text boxes, lines, and images. Embed and refresh charts linked to Google Sheets. Manage speaker notes, duplicate or reorder slides, and perform batch updates combining multiple operations in a single call. Supports automated report and deck generation using templates with placeholder text and image substitution.

Technical notes for Plasmic

Render Plasmic-designed pages and components as HTML, access project models, and manage CMS content. Render components in preview, published, or versioned modes with customizable props and variants. Retrieve full project structures including components, pages, design tokens, and metadata. Programmatically create and update components, pages, and design tokens. Perform full CRUD operations on headless CMS content: query, count, create, update, delete, and publish items with filtering and localization support. Configure webhooks for project and CMS publish events.

Frequently asked questions

Common questions about connecting Plasmic to AI agents with Metorial.

  1. How many tools does the Plasmic MCP server have?
    The Plasmic MCP server exposes 12 tools, including Count CMS Items, Query CMS Items, Get Project Model. Each one is governed and traced through Metorial.
  2. Plasmic exposes tools your agents call on demand; it does not publish event triggers yet. Everything still runs through one governed MCP URL.
  3. Any MCP client, including VS Code, Windsurf, Zed, OpenCode and Grok. Each one reaches the Plasmic MCP server through the same Metorial URL.
  4. Use role-based access control to decide which teams, users, and agents can use Plasmic and which of its tools they can call.
  5. Yes. Metorial is open source, so you can run the Plasmic MCP server yourself or use the hosted gateway.

Connect Plasmic to production AI agents

See how Metorial gives your team governed access to Plasmic, with tracing and security controls built in.