Marvin MCP
This server exposes a minimal read-only MCP interface for Marvin CMS, limited to capability discovery and workspace information.
Describe Marvin MCP capabilities and summarize the SDK capability inventory.
Retrieve basic workspace information and site settings.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Marvin MCP list entries in the blog collection"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Marvin MCP
Official Model Context Protocol server for Marvin CMS.
marvin-mcp is the LLM-facing adapter for Marvin. It talks directly to @inneropen/marvin-sdk; it does not shell out to marvin-cli and it does not recreate Marvin API behavior.
MCP Client
↓ stdio
marvin-mcp
↓
@inneropen/marvin-sdk
↓ HTTPS
Marvin APIProject Relationship
marvin-cli ──┐
├──> marvin-sdk ──> Marvin API
marvin-mcp ──┘marvin-cli is for humans and shells. marvin-mcp is for MCP-compatible AI clients. marvin-sdk remains the canonical programmatic Marvin client.
Related MCP server: Directus MCP Server
Installation
After publication:
npx -y @inneropen/marvin-mcpFor local development:
npm install
npm run devConfiguration
Required (each can instead come from ~/.marvin/credentials.json, see below):
MARVIN_API_URL
MARVIN_SITE_CLIENT_TOKEN
MARVIN_WORKSPACE_SLUGOptional:
MARVIN_USER_TOKEN
MARVIN_MCP_LOG_LEVEL=silent|error|warn|info|debug
MARVIN_MCP_READ_ONLY=true|falseCredentials from the Marvin CLI
If you have logged in with the Marvin CLI, the server reads ~/.marvin/credentials.json and no extra env vars are needed. In particular, you do not need to pass MARVIN_USER_TOKEN: the CLI login is enough to enable the authoring (platform) tools.
Setting | Resolution order (first match wins) |
Workspace |
|
API URL |
|
Site token |
|
User token |
|
Stored tokens take precedence over env vars so a fresh marvin login takes effect even if the MCP client has an old token cached in its env config. Set MARVIN_USER_TOKEN only for CI/automation without a credentials file.
Default: MARVIN_MCP_READ_ONLY is true. Current SDK-backed mutation tools are not implemented, so write tools are absent either way in this first release.
Logs go to stderr. Tokens are never printed intentionally and are redacted from structured logs/errors.
Tools
Self-description:
Tool | Purpose |
| Describe Marvin MCP capabilities and SDK capability support |
Read tools:
Tool | Purpose |
| Get workspace info and site settings |
| List entries with |
| Get one entry by slug |
| List collections |
| Get one collection by slug |
| Get entries in a collection |
| List asset metadata |
| List reusable resources |
| Get one resource by slug |
No destructive or generic API proxy tools are exposed.
Assets and resources are no longer served by Marvin's site-facing publishing API, so everything asset/resource related (marvin_list_assets, marvin_get_asset, marvin_list_resources, marvin_get_resource, marvin://resources, marvin://resources/{slug}, review_assets, review_resources) is read through the authenticated platform API and is offered only when a user token is configured. Without one these are absent; entries still carry their assets and resources inline.
Resources
URI | Purpose |
| Capability and SDK inventory |
| Workspace info |
| Public site settings |
| Entry types inferred from listed entries |
| Collection summaries |
| Resource summaries |
| Entry details |
| Collection details |
| Resource details |
Prompts
Prompt | Purpose |
| Inspect structure and recommend non-destructive improvements |
| Guide drafting a page without automatic publishing |
| Draft a release/update content item |
| Audit entries, collections, resources, and site settings |
| Review collection organization |
| Review asset metadata quality |
| Review reusable resources |
Capabilities
Marvin MCP is organized by Marvin capability under src/capabilities/*. Each capability owns its tools, resources, and prompts.
Capability | MCP Surface |
Workspace |
|
Entries |
|
Entry Types |
|
Collections | collection tools, |
Assets |
|
Resources | resource tools, |
Capability |
|
The SDK capability inventory and architecture review are documented in docs/CAPABILITY_INVENTORY.md.
Client Examples
Generic stdio MCP client:
{
"mcpServers": {
"marvin": {
"command": "npx",
"args": ["-y", "@inneropen/marvin-mcp"],
"env": {
"MARVIN_API_URL": "https://marvin.example.com",
"MARVIN_SITE_CLIENT_TOKEN": "${MARVIN_SITE_CLIENT_TOKEN}",
"MARVIN_WORKSPACE_SLUG": "example-workspace",
"MARVIN_MCP_READ_ONLY": "true"
}
}
}
}Claude Code and other clients use the same command/env shape, though exact config file locations differ by client.
Development
npm run dev
npm run build
npm run typecheck
npm run lint
npm testMCP Inspector:
npm run inspectIntegration tests are opt-in and read-only:
MARVIN_MCP_INTEGRATION_TESTS=true npm testThey also require MARVIN_API_URL, MARVIN_SITE_CLIENT_TOKEN, and MARVIN_WORKSPACE_SLUG.
Capability Matrix
Capability | SDK support | Authentication | MCP mapping | Read/write | Implemented | Limitations |
Workspace info/site settings |
| Site token | Tool and resources | Read | Yes | API credentials enforce access |
List/get entries | Publishing | Site token | Tools and | Read | Yes | SDK source does not send |
Collections | Publishing | Site token | Tools and resources | Read | Yes | Missing collections return |
Assets | Platform | User token |
| Read | Yes | Metadata only; no binary payloads |
Resources | Platform | User token | Tools and resources | Read | Yes | Publishing API no longer serves assets/resources; entries still carry them inline |
Entry types | Platform SDK has | Platform user auth |
| Read | Partial | Inferred from entries in first release |
Platform entries/assets/forms/etc. |
| User token/session | Future editor capabilities | Read/write | No | Requires auth, permission-aware registration, and mutation safety design |
Administration | Platform admin/user/workspace/API client/webhook/task modules | User token/session | Future admin capabilities | Read/write | No | High-impact/destructive and secret-adjacent operations are intentionally excluded |
SDK Capability Gaps
Current @inneropen/marvin-sdk 2.0.0-next.17 publishing client is read-focused. The installed declarations expose no create, update, add-to-collection, or publish entry methods, so this MCP server does not implement write tools and does not bypass the SDK with direct fetch() calls.
This prerelease returns null for missing entries and collections. The MCP server translates those results into structured not-found errors.
The SDK does not expose permission metadata for permission-aware discovery. First release behavior relies on MARVIN_MCP_READ_ONLY and Marvin API authorization failures.
Security
Security decisions:
Read-only mode defaults to
true.No arbitrary HTTP request, shell, SQL, migration, plugin, or secret-management tools.
No generic
marvin_api_request.Inputs are validated with Zod.
Outputs are normalized into JSON-safe structures.
Asset storage internals and tokens are not exposed.
Prompts never instruct automatic publishing.
Final authorization is enforced by Marvin API credentials.
Planned Streamable HTTP
The first transport is stdio. Server creation, capability registration, and transport connection are separated so Streamable HTTP can be added later without rewriting the tool/resource/prompt layer.
Available Tools
1 toolmarvin_describe_capabilitiesDescribe Marvin capabilitiesA
Explain the Marvin capabilities exposed by this MCP server and summarize the SDK capability inventory.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion between tools. The single tool has a clear, distinct purpose.
The sole tool name 'marvin_describe_capabilities' follows a clear verb_noun pattern in snake_case, so there is no inconsistency.
The server has only one tool, which is borderline for typical MCP servers. It could be acceptable if the server's sole purpose is introspection, but it feels thin for a general-purpose server.
The server only provides a single tool that describes capabilities, with no tools to actually perform any actions. This is severely incomplete for a functional MCP server.
Maintenance
Related MCP Connectors
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
A Model Context Protocol server for Wix AI tools
Official Fibery MCP server: query and update your workspace from any AI client via OAuth.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceThis server implements the Model Context Protocol to facilitate meaningful interaction and understanding development between humans and AI through structured tools and progressive interaction patterns.57-
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that allows AI tools to connect to and interact with your Directus API, enabling automated access to collections, items, and user data.17 npm27MIT

Contentfulofficial
AlicenseNot gradedqualityBmaintenanceA Model Context Protocol (MCP) server that provides AI assistants with comprehensive tools to interact with Contentful APIs.139 npm62MIT- AlicenseAqualityDmaintenanceThe official Model Context Protocol server for Skema CMS, enabling AI clients to interact with and manage CMS data. It provides tools for reading, creating, updating, and searching collections and items through natural language.1112 npmMIT