← Rivul AI Research

Rivul Atlas · Beta

Rivul Atlas: API and MCP for research agents

A technical guide to bringing normalized scholarly metadata into software through REST and into compatible AI agents through MCP.

InterfacesREST API + MCP server
AccessBrowser sign-in or dedicated key
OutputMetadata + source locations
Rivul Atlas browser authorization, dedicated-key access, setup flow, and coming-soon capabilities.

A research workflow often starts in one tool and needs evidence in another. A developer may need paper metadata in a service; a researcher may want an AI client to search for relevant work without leaving the conversation. Rivul Atlas gives both workflows a shared, read-only scholarly search layer while keeping access and usage attached to a Rivul workspace.

Atlas is currently available in beta to verified Pro and Ultimate accounts. The initial scope is deliberately narrow: search scholarly records, return useful identifiers and source locations, and report the current usage balance. Atlas does not host publishers' full text, judge whether a paper is correct, or replace reading the original source.

One capability, two interfaces

The REST API and MCP server reach the same normalized search capability, but they serve different callers. Treating them as separate interfaces keeps each setup understandable and avoids asking an AI client to imitate an application integration, or the reverse.

Software

REST API

For backends, scripts, and automations that make explicit requests and process structured responses.

AI clients

MCP server

For compatible clients that discover named tools and decide when to call them during a task.

The Model Context Protocol overview describes the common host, client, and server roles. Atlas acts as a remote MCP server. Its first tool, search_papers, returns scholarly records; the second, usage_status, reports the workspace's current MCP-credit balance. The model receives only the tool contract and result needed for that interaction, not Rivul's internal search infrastructure.

Two ways to authorize an MCP connection

MCP support does not mean every client presents the same setup screen. Atlas therefore offers two access paths and shows the relevant one inside each client guide.

Personal use

Browser authorization

The client opens Rivul, where the user signs in, chooses a workspace, reviews access, and approves the connection.

Managed use

Dedicated MCP key

A revocable key is created for a script or managed environment and stored in that client's secret configuration.

Browser authorization is the preferred personal flow when a client supports it. A dedicated key remains useful for managed environments and clients whose current setup requires manual credentials. Rivul never asks a user to give an AI client their Rivul password.

Official MCP references by client

These are the vendors' own MCP references. They explain each client's current configuration and behavior; the Rivul Atlas console supplies the matching Atlas-specific values. Listing a client here identifies a setup path. It does not claim a partnership, endorsement, marketplace listing, or universal OAuth certification.

Whether you work in Claude Code, OpenAI Codex, Cursor, Google Antigravity, or Muse Code, the Atlas side stays the same: one Streamable HTTP endpoint at https://rivul.ai/mcp, two read-only tools (search_papers andusage_status), and either browser sign-in or a dedicated MCP key.

For example, use the Claude Code MCP guide for Claude's connection commands, the Codex MCP guide for OpenAI's current client behavior, the Google Antigravity MCP guide for Google's setup, the Cursor MCP guide for Cursor's configuration, and the Muse Code MCP guide for Meta's settings shape. Those pages can change as the clients evolve, so Rivul links to them instead of copying vendor-specific instructions into a permanent claim.

What Atlas returns

A useful search result needs enough structure to identify, compare, and open a work. Atlas normalizes provider records into a bounded response instead of passing a provider-specific payload straight through to the caller.

  • IdentityTitle, authors, publication year, venue, DOI, and stable record identifiers when available.
  • Discovery contextWork type, citation count, topic, field, and a bounded abstract excerpt when available.
  • Source locationsPublisher, repository, DOI, and open-access links when the underlying record supplies them.
  • PaginationTotal matches, page size, offset, and whether another page is available.

Metadata availability varies by publication. A missing DOI or open-access URL should be treated as missing data, not inferred. The original publication is always the authority for the paper's text and findings.

Worked example: testing an agent search

After connecting Atlas, ask the client: “Use Rivul Atlas to search for Attention Is All You Need. Return the title, authors, year, venue, work type, DOI when available, topics, field, open-access status, and source URL.”Confirm that the client calls search_papers, returns structured metadata, and preserves the source links. Then ask it to callusage_status so you can confirm that the connection is bound to the expected workspace and plan period.

A literal query may rank books or chapters above journal articles. Refine the request when the research question needs a particular work type, date range, citation threshold, or open-access constraint. The model can help formulate that request, but the researcher still evaluates relevance and evidence quality.

The public contract and its boundaries

Atlas documents what a customer needs to connect, search, inspect usage, and revoke access. Internal provider credentials, infrastructure addresses, credential formats, security controls, and operational thresholds are not part of the public integration contract. That separation keeps the documentation useful without turning implementation detail into a promise or an attack map.

Beta capabilities and coming-soon work are labeled separately. Deterministic record lookup, richer open-access resolution, related-paper discovery, and Rivul Intelligence reporting are product direction until they are implemented and verified. Read the Rivul Atlas product page for the current customer-facing capability summary, then open Atlas for the exact setup guide supported by your client.

Start researching for freeExplore Rivul Atlas