MCP server · Decart

decart-api-platform-docs

Decart publishes a hosted, remote MCP server on its documentation host. It is a documentation-knowledge server, not a wrapper over the Decart REST API: its three tools search and query the Decart API Platform docs and OpenAPI specs and submit docs feedback. None of the tools call api.decart.ai, so an agent can learn how to use Decart through MCP but must still call the REST API directly to generate or edit media.

Open endpoint → Decart provider profile

One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.

Provider: Decart Type: Hosted endpoint Transport: http Host: docs.platform.decart.ai

Endpoint

https://docs.platform.decart.ai/mcp

Hosted endpoint · transport http

Connect

This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):

# mcp client config (e.g. .mcp.json / mcp settings) { "mcpServers": { "decart": { "url": "https://docs.platform.decart.ai/mcp" } } }

For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:

# Add to claude_desktop_config.json { "mcpServers": { "decart": { "command": "npx", "args": ["-y", "mcp-remote", "https://docs.platform.decart.ai/mcp"] } } }

If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:

curl -i -X POST https://docs.platform.decart.ai/mcp \ -H "Content-Type: application/json" -H "Accept: application/json, text/event-stream" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Tools

search_decart_api_platform — Search across the Decart API Platform knowledge base to find relevant information, code examples, API references, and guides.
query_docs_filesystem_decart_api_platform — Run a read-only shell-like query against a virtualized, in-memory filesystem rooted at / that contains only the Decart API Platform documentation pages and OpenAPI specs.
submit_feedback — Report a problem with this documentation site so the docs team can fix it.

About MCP

The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.

Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.