Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/xwang20/semanticscholar-mcp-server/semantic-scholar-clinpx skills add XWang20/semanticscholar-MCP-Server --skill semantic-scholar-cligit clone --depth 1 https://github.com/XWang20/semanticscholar-MCP-ServerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/xwang20/semanticscholar-mcp-server/semantic-scholar-cli)<a href="https://agentmods.dev/skills/xwang20/semanticscholar-mcp-server/semantic-scholar-cli"><img src="https://agentmods.dev/badge/skills/xwang20/semanticscholar-mcp-server/semantic-scholar-cli.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00085 | $0.00989 |
| Opus 5 | $0.00043 | $0.00495 |
| Sonnet 5 | $0.00017 | $0.00198 |
| Haiku 4.5 | $0.00009 | $0.00099 |
Grade A, and why
semantic-scholar-cli scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Scholar CLI
Goal
Choose the narrowest correct Semantic Scholar operation, inspect its live schema, call it with a JSON object, and preserve the native response. Do not guess endpoint names or arguments.
The CLI and MCP server share the same 22 FastMCP tool definitions. Treat tools and schema output as authoritative when this skill and the installed version differ.
This is the low-level endpoint-routing skill. For evidence-led multi-paper answers, the separate $scholarqa-research skill can use scholarqa-cli or MCP and may be installed independently. Combine the two only when a ScholarQA run also needs precise graph traversal or another endpoint-level operation.
Workflow
-
Confirm
semanticscholar-cliis available. If working from this repository before installation, usepython semantic_scholar_cli.pyinstead. -
Translate the request into one or more bounded retrieval operations.
-
Select the operation using the routing rules below. Read references/operations.md completely for unfamiliar, filtered, paginated, or multi-stage tasks.
-
Inspect the operation before its first call:
semanticscholar-cli schema search_semantic_scholar_papers -
Pass arguments as one JSON object:
semanticscholar-cli call search_semantic_scholar_papers \ --params '{"query":"retrieval augmented generation","limit":5}' -
Inspect both the process exit status and a top-level
errorfield. Correct invalid parameters rather than retrying them unchanged. -
Preserve paper IDs, external IDs, pagination state, and evidence provenance for downstream synthesis.
Use --params-file FILE for complex input or --params - to read a JSON object from stdin. Use --compact when another program will consume the response.
Route to the correct operation
- Exact or near-exact title:
match_semantic_scholar_paper. - Partial title completion only:
autocomplete_semantic_scholar_papers; never use autocomplete output as evidence. - Ordinary topical paper discovery:
search_semantic_scholar_papers. - High-volume discovery or token pagination:
bulk_search_semantic_scholar_papers. - Passage-level evidence from available full text:
search_semantic_scholar_snippets. - One known paper or author: the corresponding
get_*_detailsoperation. - Many known IDs: a
batch_get_*operation instead of repeated single calls. - Works citing a paper:
get_semantic_scholar_paper_citations. - Works cited by a paper:
get_semantic_scholar_paper_references. - Similar papers: a recommendation operation, not citations or generic search.
- An author's publication list:
get_semantic_scholar_author_papers. - Dataset releases and download links: the four dataset operations.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 73 lines · 85 tokens per session scan A bb929f9a83dc
semantic-scholar-cli is a skill published in the GitHub repository XWang20/semanticscholar-MCP-Server (2 stars, last pushed 1mo ago), licensed MIT. It adds 85 tokens to every session and 989 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
patsnap-patent-literature-search
Search Patsnap's global patent and scientific literature databases together using natural-language, semantic, keyword, and BM25-based queries with multidimensional filters, then fetch patent or literature records as Markdown.
release-and-publish
Ship a release end-to-end across every registry the project targets (npm, MCP Registry, GitHub Releases for .mcpb bundles, GHCR). Runs the final verification gate, pushes commits and tags, then publishes to each applicable destination. Assumes git wrapup (version bumps, changelog, commit, annotated tag) is already…
design-mcp-server
Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.
add-tool
Scaffold a new MCP tool definition. Use when the user asks to add a tool, create a new tool, or implement a new capability for the server.
api-context
Canonical reference for the unified Context object passed to every tool and resource handler in @cyanheads/mcp-ts-core. Covers the full interface, its RequestContext base, all sub-APIs (ctx.log, ctx.state, ctx.requestInput, ctx.inputs, ctx.enrich, ctx.content), and when to use each.
api-linter
MCP definition linter rules reference. Use when bun run lint:mcp or bun run devcheck reports a lint error or warning (format-parity, schema-is-object, name-format, server-json-, etc.) and you need to understand the rule, its severity, and how to fix it. Every rule ID the linter emits has an entry in this doc.