deploy.social MCP server
deploy.social's own hosted MCP server. It lets an assistant work in one Deploy workspace: list connected social accounts, bring in a video or photos, save a draft, publish it once the person agrees, and check results. Available on the Standard and Studio plans. A read-only connection only sees the read tools.
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.
Endpoint
Hosted endpoint · transport
Connect
This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):
For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:
If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:
Tools
list_destinations— Lists the social accounts connected to this workspace (platform, handle, status, the post fields each platform uses, video limits, and the settings a post can choose for it).add_media— Brings a video or photo into the workspace. For a local file it returns an upload command to run where the file is; online video must be a public HTTPS link to the file.get_media— Checks on a video or photo from add_media, including its orientation.create_post— Saves a post as a draft (kind video, photos with 1-35 items, or text).update_post— Changes a draft's fields, but not its kind.publish_post— Posts a draft, or moves a scheduled post to a new time. Instructs the assistant to confirm destinations, caption and time first.list_posts— Lists the workspace's posts, newest first, with each destination's state and live link.get_post— Shows one post in full, with per-destination status, link, and failure reason and remedy.cancel_post— Deletes a draft, or cancels a scheduled post.retry_post— Retries the destinations that failed and leaves the successful ones alone.
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.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.