# Consensus — how to use (mcp.ai)

Connect your Consensus account and use 1 tools for artificial intelligence straight from your AI agent. Connect with your own API key. Consensus provides evidence-based search across scientific research papers.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_consensus?ms=1787291520000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `consensus_search_papers`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/consensus`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/consensus/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/consensus/search/papers` — Search Consensus for relevant research papers with study, publication, and access filters. Returns one result page and an optional continuation cursor. Search calls are billed; pagination beyond the f
  - body: { human?: boolean, query: string, country?: string, domains?: string[], sjr_max?: integer, sjr_min?: integer, year_max?: integer, year_min?: integer, month_max?: integer, month_min?: integer, page_size?: integer, controlled?: boolean, next_cursor?: string, open_access?: boolean, study_types?: string[], citation_min?: integer, duration_max?: integer, duration_min?: integer, journal_name?: string, medical_mode?: boolean, publisher_name?: string, sample_size_min?: integer, exclude_preprints?: boolean, clinical_guideline?: boolean, include_semantic_score?: boolean, include_full_text_chunks?: boolean }

## Example prompts
- "What can I do in Consensus?"
- "Show me a summary of my Consensus account"

## More
- Page: https://mcp.ai/consensus
- Agent spec (llms.txt): https://mcp.ai/consensus/llms.txt
- Postman collection: https://mcp.ai/consensus/postman.json