# Asta Agents/MCP Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/asta-agents-mcp
> Markdown URL: https://aitinkerers.org/technologies/asta-agents-mcp.md
> Technology record last updated: 2026-04-04T21:31:11Z
> Generated: 2026-09-23T05:40:20Z

Asta Agents (Ai2) is an open-source AI research assistant ecosystem: it uses the Model Context Protocol (MCP) to access and synthesize evidence from a 200M+ scientific corpus.

Asta Agents, developed by the Allen Institute for AI (Ai2), is a robust, open-source AI research assistant designed to accelerate scientific discovery. It acts as a transparent, source-cited collaborator, executing complex, multi-step tasks like literature review, evidence synthesis, and data analysis (in beta). The core functionality leverages the Model Context Protocol (MCP) to provide agents with standardized, real-time access to external resources; this includes the Scientific Corpus Tool, an MCP extension of the Semantic Scholar API that indexes over 200 million papers. The full Asta ecosystem also features AstaBench (a rigorous benchmarking suite with 11 benchmarks) and Asta Resources (a developer toolkit), ensuring trustworthy and verifiable scientific AI performance.

- Official technology site: https://allenai.org/asta
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [AI2's Asta is Accelerating Research](https://seattle.aitinkerers.org/talks/rsvp_JHzEM_VI0oA)

Using AI2's Asta Agents/MCP to streamline scientific literature extraction, enhancing throughput for laboratory applications. I'll briefly discuss the project I'm working on as a student researcher at Seattle Children's, an agentic AI genomics target selection pipeline that finds promising drug targets proposed in literature and flags them for study. It uses Asta agents to perform the iterative literature search, as finding promising papers necessitates self-reflection, changing queries, and dynamic analysis, which would be difficult without Asta agents. I will discuss how I implemented this workflow, show how it runs, and discuss its performance with some open-source LLMs. I'll also mention how implementing this same workflow from scratch in June with PydanticAI was a complete pain and Asta simplified it by leaps and bounds. Main message: It's great how a student researcher like myself can have access to these amazing tools and have an actual impact. LLMs will only become more accessible from here, which is cool.

- Event context: Frontier Builds Demo Night: Experiments at the Edge of AI — 2025-11-13 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_JHzEM_VI0oA

## Related Technologies

- [LangGraph](https://aitinkerers.org/technologies/langgraph) ([Markdown](https://aitinkerers.org/technologies/langgraph.md)) — 68 public demos
- [PydanticAI](https://aitinkerers.org/technologies/pydanticai) ([Markdown](https://aitinkerers.org/technologies/pydanticai.md)) — 8 public demos