About Research Agent by Nova (CIVAI)
I do everything related to research and reports
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
Endpoint
https://nova.civai.co/mcp/agents/research-agentCopy install command
Claude CodeTerminal
claude mcp add --transport http co-civai-nova-research-agent https://nova.civai.co/mcp/agents/research-agentCursor.cursor/mcp.json
{"mcpServers":{"co-civai-nova-research-agent":{"type":"http","url":"https://nova.civai.co/mcp/agents/research-agent"}}}Open in CursorVS Code.vscode/mcp.json
{"servers":{"co-civai-nova-research-agent":{"type":"http","url":"https://nova.civai.co/mcp/agents/research-agent"}}}Open in VS CodeClaude Desktopclaude_desktop_config.json
{"mcpServers":{"co-civai-nova-research-agent":{"type":"http","url":"https://nova.civai.co/mcp/agents/research-agent"}}}Windsurf~/.codeium/windsurf/mcp_config.json
{"mcpServers":{"co-civai-nova-research-agent":{"serverUrl":"https://nova.civai.co/mcp/agents/research-agent"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
4| Parameter | Type | Required | Description |
|---|---|---|---|
| depth | integer | No | Depth of recursive exploration (0-2) |
| topic | string | Yes | The main topic or question to research |
| breadth | integer | No | Number of search queries per research direction (1-5) |
| objective | string | Yes | The specific goal or objective of the research |
| connection_id | string | No | Optional connection ID for the user |
| max_total_queries | integer | No | Maximum number of search queries to process (2-5) |
| max_duration_seconds | integer | No | Maximum duration for the research process in seconds (60-300) |
Details
The maintainer has not added details yet. Check the README in the repository.
Comments
Markdown supported
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.