asta-skill
Domain expertise for Ai2 Asta MCP tools (Semantic Scholar corpus). Intent-to-tool routing, safe defaults, workflow patterns, and pitfall warnings for academic paper search, citation traversal, and author discovery.
Agents365-ai · Static checks on file
Installation
Read the source and dependencies before running a command. Copying does not install or execute anything.
npx skills add Agents365-ai/365-skills --skill asta-skillAbout this skill
name: asta-skill description: Domain expertise for Ai2 Asta MCP tools (Semantic Scholar corpus). Intent-to-tool routing, safe defaults, workflow patterns, and pitfall warnings for academic paper search, citation traversal, and author discovery. license: MIT metadata: {"homepage":"https://github.com/Agents365-ai/asta-skill","compatibility":"Requires an MCP-capable host (Claude Code, Codex, Cursor, Windsurf, Hermes, OpenClaw/ClawHub) with the Asta MCP server registered at https://asta-tools.allen.ai/mcp/v1 using an x-api-key header. The skill does not make HTTP calls itself.","platforms":["macos","linux","windows"],"openclaw":{"requires":{"env":["ASTA_API_KEY"]},"emoji":"🔭","mcp":{"name":"asta","type":"http","url":"https://asta-tools.allen.ai/mcp/v1","headers":{"x-api-key":"${ASTA_API_KEY}"}}},"hermes":{"tags":["asta","semantic-scholar","academic","paper-search","citation","mcp"],"category":"research","requires_tools":["mcp"],"related_skills":["semanticscholar-skill","literature-review"]},"pimo":{"category":"research","tags":["asta","semantic-scholar","academic","paper-search","citation","mcp"]},"author":"Agents365-ai","version":"0.3.4"}
Asta MCP — Academic Paper Search
Asta is Ai2's Scientific Corpus Tool, exposing the Semantic Scholar academic graph over MCP (streamable HTTP transport). This skill tells agents which Asta tool to call for which intent, and how to compose them into useful workflows.
- MCP endpoint:
https://asta-tools.allen.ai/mcp/v1 - Auth:
x-api-keyheader (request key at https://share.hsforms.com/1L4hUh20oT3mu8iXJQMV77w3ioxm) - Transport: streamable HTTP
Prerequisite Check
Before invoking any tool, verify the Asta MCP server is registered in the host agent. Tool names will be prefixed by the MCP server name chosen at install time (commonly asta__<tool> or mcp__asta__<tool>).
If no Asta tools are visible, do not make raw HTTP calls or invent results. Tell the user to register https://asta-tools.allen.ai/mcp/v1 as a streamable HTTP MCP server with an x-api-key header, then restart/reload the host. Minimal setup hints:
- Codex CLI: add
[mcp_servers.asta] url = "https://asta-tools.allen.ai/mcp/v1"andenv_http_headers = { "x-api-key" = "ASTA_API_KEY" }to~/.codex/config.toml. - Claude Code: run
claude mcp add -t http -s user asta https://asta-tools.allen.ai/mcp/v1 -H "x-api-key: $ASTA_API_KEY". - Generic MCP clients: configure server URL
https://asta-tools.allen.ai/mcp/v1with header{ "x-api-key": "<YOUR_API_KEY>" }.
Tool Map — Intent → Asta Tool
| User intent | Asta tool | Notes |
|---|---|---|
| Broad topic search | search_papers_by_relevance | Supports venue + date filters |
| Known paper title | search_paper_by_title | Optional venues + publication_date_range filters |
| Known DOI / arXiv / PMID / CorpusId / MAG / ACL / SHA / URL | get_paper | Single-paper lookup |
| Multiple known IDs at once | get_paper_batch | Batch lookup — pass ids as a JSON array (not a comma-separated string, unlike snippet_search's paper_ids); prefer over N sequential get_paper calls; unresolvable IDs are silently dropped (no null/error), so reconcile returned paperIds against your input |
| Who cited paper X | get_citations | Forward citations, paginated; accepts publication_date_range but not venues; limit defaults to 100 |
| Find author by name | search_authors_by_name | Default fields="name" returns only name + authorId — explicitly request affiliations,paperCount,citationCount,hIndex,externalIds to get anything rankable; externalIds carries ORCID/DBLP (url/homepage are also selectable) |
| An author's publications | get_author_papers | Pass author id; field param is paper_fields (not fields); limit defaults to 1000 — set it explicitly |
| Find passages mentioning X | snippet_search | ~500-word excerpts (title/abstract/body, excludes captions & bibliography); see snippet-specific params below |
Most search/citation tools accept publication_date_range (format YYYY-MM-DD:YYYY-MM-DD; year shorthand like "2021:", ":2015-01", "2015:2020" is also accepted), venues, and fields for field selection — pass them whenever the user's intent constrains scope (e.g., "recent", "since 2022", "at NeurIPS"). venues matches Semantic Scholar's exact venue strings (comma-separated, e.g. "Nature,N. Engl. J. Med."); a casual name like "NeurIPS" may not match, so fall back to a date/keyword filter when a venue lookup returns empty.
Per-tool parameter exceptions (verified against the live server — getting these wrong yields a malformed or silently-ignored argument):
get_author_papersnames its field-selection parampaper_fields, notfields(passingfields=is silently ignored — you get titles only), and accepts apublication_date_rangebut novenuesfilter. Its date filter is applied after paging and can drop valid in-range papers (a well-known author's2024:2024returned[]), so for reliable results narrow by topic/venue and date client-side.get_citationsacceptspublication_date_rangebut notvenues.snippet_searchaccepts neitherfieldsnorpublication_date_range. Instead it has:inserted_before(date filter,YYYY-MM-DD/YYYY-MM/YYYY),paper_ids(comma-separated list of ≤100 IDs to restrict snippets to specific papers), andvenues.
⚠️ fields parameter — avoid context blowups
get_paper / get_paper_batch accept a fields string. Never request citations or references via fields — a single highly-cited paper (e.g. Attention Is All You Need) returns 200k+ characters and will overflow the agent's context window. Use the dedicated get_citations tool for forward citations (it paginates). Asta does not provide a dedicated get_references tool — to retrieve a paper's reference list, use get_paper with fields=references only f