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 skills add surendranb/find-research-papers-mcp --skill interpreting-errorsgit clone --depth 1 https://github.com/surendranb/find-research-papers-mcpWrote 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/surendranb/find-research-papers-mcp/interpreting-errors)<a href="https://agentmods.dev/skills/surendranb/find-research-papers-mcp/interpreting-errors"><img src="https://agentmods.dev/badge/skills/surendranb/find-research-papers-mcp/interpreting-errors/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/surendranb/find-research-papers-mcp/interpreting-errors"><img src="https://agentmods.dev/badge/skills/surendranb/find-research-papers-mcp/interpreting-errors.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00025 | $0.00796 |
| Opus 5.5 | $0.00010 | $0.00318 |
| Sonnet 5.5 | $0.00005 | $0.00159 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
interpreting-errors 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 today.
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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interpreting errors from find-research-papers-mcp
Factual guide to every error shape this server produces, and the recovery move for each. Errors here are structured data, not crashes — read them.
search_papers
A search never hard-fails on a single source. Failures appear in skipped:
{"source": ..., "reason": "key_required", "hint": ...}— that source needs an API key the user has not configured. Recovery: proceed with the hits you got (other sources answered); mention the hint's env var only if the user asks for that specific source's coverage.{"source": ..., "reason": "error", "detail": ...}— the source's API failed (timeout, 429, 5xx). Semantic Scholar 429s on the shared pool without a key — this is normal, not a bug. Recovery: use the remaining hits; retry later only if that source is essential to the question.
The call itself raises (protocol isError: true) only for bad arguments:
sort must be one of: relevance, citations, date— fix thesortvalue.unknown source(s): ... Known: ...— fix thesourceslist to names fromlist_sources.
hits: [] with nothing skipped means the query genuinely matched nothing:
broaden keywords; do not invent results.
get_paper
Error-shaped results are dicts with an error key:
unknown id_type '...'— fixid_typeto one of: doi, arxiv, pmid, openalex, s2 (or use "auto").paper not found via <Source> (id_type=..., identifier=...)— the owning source has no record; the message carries its own numbered recovery steps. Retrying the same identifier will not help: check it for typos; if it was guessed byid_type: auto, pass the correctid_typeexplicitly; or search_papers for the title instead.
Successful results can still carry degraded legs, reported in notes:
references unavailable: .../citations unavailable: ...— that leg's API failed; the paper itself is valid.<Source> does not expose a public reference list— arXiv and PubMed have no public reference graph; this is a source limit, not a failure.citing works not available from this source (OpenAlex fallback applies when the work is indexed there)— empty citations may mean "not indexed", never "never cited".
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.
- today First seen · 71 lines · 25 tokens per session scan A cd435342d596
interpreting-errors is a skill published in the GitHub repository surendranb/find-research-papers-mcp (6 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 796 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-28.
Other skills, from other repositories
citeguard-verify
Verify citations in scientific or technical writing against scholarly sources. Use when a user asks to check whether papers exist, audit bibliographic metadata, validate DOI/arXiv identifiers, inspect a bibliography or reference list, verify citations suggested by an agent, or assess whether cited papers support…
citeguard-maintain
Maintain and release the CiteGuard repository. Use only when working inside a CiteGuard source checkout on support-evaluation datasets, human-review packets, calibration, release gates, package smoke tests, MCP registry metadata, or CiteGuard contributor workflows. Do not use for ordinary citation verification.
arxiv-mcp-server
Use when finding, comparing, reading, or monitoring arXiv papers, including requests for abstracts, citation graphs, original LaTeX, section-level technical details, or literature reviews.
nature-academic-search
An academic-paper search skill finds and checks research papers, preprints, clinical-trial records, and citations across sources such as PubMed, arXiv, Crossref, and OpenAlex. It can also work with identifiers such as DOI, PMID, and trial IDs.
research-agent
Project-first Research pipeline with live gates, source/PDF evidence, claim boundaries, compute and publication controls; includes an optional PubMed/arXiv standard-library helper.
arxiv-guide
Resolve citations to arXiv IDs, find an author's papers, follow a paper's versions, and read long papers section by section with the arxiv tools. Use when a task needs arXiv preprints found by citation (author-year, CoRR abs/ refs, arXiv DOIs), author, category, or date, or needs a paper's full text.