MCP server · Coactive AI

coactive-docs

Coactive operates an official remote MCP server for its DOCUMENTATION, exposed by its Mintlify docs platform at https://docs.coactive.ai/_mcp/server and advertised in /llms.txt for AI client integration (Claude Code, Cursor, etc.). This is a documentation-retrieval MCP server (search/fetch the docs), not a full operational wrapper of the REST API. No first-party MCP server that invokes the Coactive REST operations (ingestion/search/concepts) was found at fetch time; the candidate_tools[] below are DERIVED from marquee OpenAPI operations as a starting point for such a server, not something Coactive ships.

Open endpoint → Coactive AI 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: Coactive AI Type: Hosted endpoint Transport: http Host: docs.coactive.ai

Endpoint

https://docs.coactive.ai/_mcp/server

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": { "coactive-ai": { "url": "https://docs.coactive.ai/_mcp/server" } } }

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

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

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.coactive.ai/_mcp/server \ -H "Content-Type: application/json" -H "Accept: application/json, text/event-stream" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Tools

search_text_to_image — Semantic text-to-image search across an ingested dataset.
search_text_to_video — Natural-language search returning matching videos.
agentic_chat — Conversational agentic search over multimodal content.
create_dataset — Create a dataset to index images and video.
ingest_from_bucket — Ingest assets into a dataset from a cloud storage bucket.
create_concept — Create a visual concept to tag and retrieve content.

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.