AI Agent Index
ByHeather MacAvelia·Independently reviewed·Published Mar 18, 2026·Updated Sep 24, 2026
Independently verified against live vendor data on Sep 24, 2026.

Academic search engine over 220M+ peer-reviewed papers, with a Consensus Meter, Deep Search and a Research Agent. MCP server and API. Free tier, Pro from $12/mo billed annually (USD).

How we scored it

Autonomy

4/5

Integrations

5/5

Pricing clarity

4/5

Evidence

4/5

Setup

5/5

The facts

Consensus is an academic search engine that finds, ranks and summarizes peer-reviewed research and returns answers with inline citations. It searches over 220 million papers indexed from sources including Semantic Scholar, OpenAlex, PubMed and publisher feeds, with licensed full text from publishers including Wiley, Taylor & Francis, Sage, ACS Publications, the American Psychological Association, De Gruyter Brill and AAAS. Consensus was founded in 2021 by Christian Salem and Eric Olson. Over 170 university libraries partner with Consensus for student and faculty access, and its homepage names institutions including Michigan, Rice, Virginia, Carnegie Mellon, Kansas, Texas A&M, William & Mary, Vanderbilt, McGill, Cardiff, Lucerne and Virginia Tech. The Consensus Meter answers a yes-or-no research question by showing how far the evidence agrees or disagrees, classifying each paper as supporting, refuting or mixed. Deep Search builds its own search strategy, expanding key terms, identifying conflicting arguments and exploring the citation graph to produce a literature review. The Research Agent plans and runs multi-step research tasks with tools such as semantic search, DOI look-up and citation graph traversal, and shows a trace of each step. Medical Mode narrows results to about 50,000 clinical guidelines and 8M articles from the top 1,000 medical journals, and Citation Grounding maps every AI citation to an exact quote from the paper. Consensus publishes an MCP server at mcp.consensus.app/mcp, which its documentation calls the recommended surface for any LLM client, naming Claude, Claude Code, Cursor, OpenAI Codex and ChatGPT, and a REST API with the same primitives. It is available as an app inside ChatGPT and Claude, and since September 2026 inside Microsoft 365 Copilot through the Microsoft Marketplace. Zotero libraries can be imported into the Consensus Library, which also takes uploaded documents and supports shared collections, and citations export as BibTeX, RIS and EndNote. Pricing is in US dollars, and the pricing page has a monthly and annual toggle with Individual and Team and Enterprise tabs, showing annual prices by default. Free includes basic paper search, 10 Pro messages and up to 3 Deep reviews per month. Pro is $12 per month billed annually ($144 a year) or $20 month to month, with unlimited Pro messages, 15 Deep reviews and 500 API and MCP uses a month. Deep is $45 per month billed annually ($540 a year) or $65 month to month, with 200 Deep reviews and 2,000 API and MCP uses. Teams is $20 per seat per month billed annually or $30 month to month, for up to 200 seats, with 50 Deep reviews, centralized billing and 500 API and MCP uses. Enterprise is priced by quote and adds SAML single sign-on, library integration and dedicated support. Students and faculty with a school email and US healthcare professionals with an NPI number can get up to 40% off. API and MCP use beyond the included amount costs $0.05 per use, up to 1,000 uses a month on Pro and Teams and 10,000 on Deep. Deep review volume separates the plans: 3 a month on Free, 15 on Pro, 50 on Teams and 200 on Deep. Consensus suits researchers, students and clinicians who want answers drawn from the peer-reviewed literature, and university libraries providing that access to students and faculty. Researchers running a full systematic review with screening and data extraction should also look at Elicit, those checking how later papers cite a specific finding should look at Scite.ai, and those whose questions reach beyond academic papers should look at Perplexity AI. Current state Q3 2026: Consensus added a Research Agent, Citation Grounding and shared Library collections during summer 2026, opened its API and MCP server to all users, and launched an app for Microsoft 365 Copilot in September 2026. It announced a content partnership with AAAS in September 2026. Its privacy policy states that it does not use customer data to train AI models, its own or any third party's, and names OpenAI, Anthropic, Google and Baseten as service providers that process content. The same policy states that Consensus is not subject to the California Consumer Privacy Act. Consensus publishes no third-party security certification.

Pricing

freemium · $12/mo annual

View pricing ↗

Segment

both

Setup

easy

Verified

Sep 24, 2026

Transparency

Mostly Public

Contract

Monthly or Annual

Data training

Not Trained

Human in loop

Not required

Capabilities

deep-researchcitationsdata-analysissystematic-review

Pros & Limitations

Editorial assessment

Pros

  • ✓Answers are drawn from the peer-reviewed literature with inline citations, and Citation Grounding shows the exact quote behind every AI citation.
  • ✓The Consensus Meter shows how far studies agree on a yes-or-no question, and Deep Search and the Research Agent run multi-step literature research.
  • ✓An MCP server and REST API come with paid plans, and Consensus runs as an app inside ChatGPT, Claude and Microsoft 365 Copilot.
  • ✓Over 170 university libraries partner with Consensus, and it licenses full text from publishers including Wiley, Sage, Taylor & Francis and AAAS.

Limitations

  • ⚠Searches the academic literature rather than the open web, news or company reports, and its default index excludes grey literature.
  • ⚠Deep review volume is capped by plan, from 15 a month on Pro to 200 on Deep, and API and MCP use past the included amount costs $0.05 per use.
  • ⚠Consensus publishes no third-party security certification, and its privacy policy states it is not subject to the CCPA.
  • ⚠The corpus is English-first, and search ranking and summaries are optimized for English queries.

Technical Details

Deployment
web
Model architectureModels operated by OpenAI, Anthropic, Google and Baseten (named as processing providers in the privacy policy, August 2026) over a 220M+ paper index built from Semantic Scholar, OpenAlex, PubMed and publisher feeds
Autonomous rateDeep Search builds its own search strategy across the citation graph, and the Research Agent plans and runs multi-step research tasks with tools, showing a trace of each step, without per-step approval. Consensus publishes no autonomous completion rate.
Integrations
ChatGPTClaudeZoteroChrome ExtensionSemantic ScholarOpenAlexPubMedWileyTaylor & FrancisSageACS PublicationsAmerican Psychological AssociationDe Gruyter BrillAAASMicrosoft 365 CopilotOxford University Press

Similar agents

Rating

4.3/ 5
★★★★★

Editorial score

How we score this →

Recognition

MCP Server VerifiedListed 2026
Embed these on your site →

Industries

EducationHealthcareResearch

Built for

B2BEnterpriseSaaS

Leave a review

Never displayed publicly.

Agent Stacks

See workflow stacks that feature Consensus.

Compare

Related Content

Is this your tool?

Claim this listing free to get your embeddable badges, a review collection link, and the Claimed badge on your listing.

Claim listing →

Free · Every Two Weeks

AI Agent Price & Rating Tracker

Price changes, new agent launches, acquisitions, and rating updates across the AI agent market. Verified against live vendor data, not vendor marketing.

No spam. Unsubscribe anytime. We never share your email.