Nova Research (CIVAI)

Deep research and report generation over live web search. Requires a Nova account; tools/list is open, tool calls need OAuth or an API key. 4 tools. Docs

Live Answered an MCP handshake without credentials and listed 4 tools.

Category: Search & discovery
Transport: http
Source: https://github.com/civai-technologies/research-agent-mcp-by-nova-civai
Endpoint: https://nova.civai.co/mcp/agents/research-agent
MCP Registry: co.civai.nova/research-agent
Reports itself as: Research Agent by Nova (CIVAI) 1.0.0
Protocol: 2025-06-18
Tools: 4
Context cost: about 496 tokens for the tool definitions (estimated at four characters per token)
Tool definitions last changed: no change seen since first check
Handshake time: 137 ms
Repository: 0 stars · last push 2026-11-02 · MIT
Last checked: 2026-11-03 16:10:50 UTC
Listed since: 2026-11-03

Health and compatibility

Endpoint reachable	Verified	Responded in 137 ms
MCP handshake (initialize)	Verified	Completed without credentials
Tool discovery (tools/list)	Verified	4 tools listed
Authentication	Verified	None needed to connect
Protocol version	Verified	2025-06-18
Transport	Verified	Streamable HTTP
Capabilities declared	Verified	experimental, resources, tools

Last checked 2026-11-03 16:10:50 UTC. Verified means the check saw it happen; it says nothing about whether the server is safe.

Recent history

1 daily check so far. Green answered, violet asked for auth, red did not answer.

Set up in your client

Claude Code

Run this in a terminal:

claude mcp add --transport http nova-research https://nova.civai.co/mcp/agents/research-agent

Claude Desktop

Open Settings → Connectors → Add custom connector and paste this URL:

https://nova.civai.co/mcp/agents/research-agent

Or bridge it through mcp-remote in claude_desktop_config.json (needs Node.js):

{
  "mcpServers": {
    "nova-research": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://nova.civai.co/mcp/agents/research-agent"
      ]
    }
  }
}

Cursor

Add to Cursor

Or add it to ~/.cursor/mcp.json (or .cursor/mcp.json in a project):

{
  "mcpServers": {
    "nova-research": {
      "url": "https://nova.civai.co/mcp/agents/research-agent"
    }
  }
}

VS Code

Add to VS Code

Or add it to .vscode/mcp.json:

{
  "servers": {
    "nova-research": {
      "type": "http",
      "url": "https://nova.civai.co/mcp/agents/research-agent"
    }
  }
}

Or from a terminal:

code --add-mcp '{"name": "nova-research", "type": "http", "url": "https://nova.civai.co/mcp/agents/research-agent"}'

Windsurf

Add it to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "nova-research": {
      "serverUrl": "https://nova.civai.co/mcp/agents/research-agent"
    }
  }
}

Other clients

Most clients accept this shape. The endpoint is:

https://nova.civai.co/mcp/agents/research-agent

{
  "mcpServers": {
    "nova-research": {
      "type": "http",
      "url": "https://nova.civai.co/mcp/agents/research-agent"
    }
  }
}

If it does not connect

Restart the client after editing a config file, and keep keys out of files you commit.
If the tools do not appear, open the client's MCP log: a 401 means the credentials were not accepted, and a timeout means the server did not answer.

Tools 4

Names, descriptions and input schemas exactly as the server returned them on 2026-11-03. This is the server author's own text. Nothing is run from this page. Raw JSON

research__conduct-deep-researchConduct deep, iterative research on a topic by generating multiple search queries, processing the results, …

Conduct deep, iterative research on a topic by generating multiple search queries, processing the results, and recursively exploring new research directions.

Parameter	Type		Description
`topic`	string	required	The main topic or question to research
`objective`	string	required	The specific goal or objective of the research
`breadth`	integer	optional	Number of search queries per research direction (1-5)
`depth`	integer	optional	Depth of recursive exploration (0-2)
`max_total_queries`	integer	optional	Maximum number of search queries to process (2-5)
`max_duration_seconds`	integer	optional	Maximum duration for the research process in seconds (60-300)
`connection_id`	string	optional	Optional connection ID for the user

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "research__conduct-deep-research",
    "arguments": {
      "topic": "...",
      "objective": "..."
    }
  }
}

research__generate-research-reportGenerate a comprehensive research report from existing research data.

Generate a comprehensive research report from existing research data.

Parameter	Type		Description
`research_data`	string	required	The research data and findings to include in the report
`objective`	string	required	The specific goal or objective of the report

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "research__generate-research-report",
    "arguments": {
      "research_data": "...",
      "objective": "..."
    }
  }
}

search__converseReply conversationally when the request is ambiguous or needs clarification.

Reply conversationally when the request is ambiguous or needs clarification.

Parameter	Type		Description
`reply_hint`	string	optional	Optional hint for the conversational reply.

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "search__converse",
    "arguments": {}
  }
}

search__searchRun live Google search and summarize results.

Run live Google search and summarize results.

Parameter	Type		Description
`query`	string	required

Example call (required arguments only, placeholder values):

{
  "method": "tools/call",
  "params": {
    "name": "search__search",
    "arguments": {
      "query": "..."
    }
  }
}

Badge

Maintain this server? Put its live status in your README:

[![MCP status](https://mcp.aianytime.net/badge/nova-research.svg)](https://mcp.aianytime.net/s/nova-research/)

Edit this entry · Report a problem

More in Search & discovery

Checks record what a server answered, not whether it is safe. A listing is not a security audit; read a server's source and permissions before you connect it. Add a server · JSON · llms.txt · llms-full.txt

Browse: Agents, IDEs & developer tools · Search & discovery · Knowledge, memory & context · Media & generation · Security · Finance & markets · Marketing, content & social · Cloud, ops & data · Commerce, travel & logistics · Work & productivity · No account needed · Local servers