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 cyanheads/orcid-mcp-server --skill orcid-guidegit clone --depth 1 https://github.com/cyanheads/orcid-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/cyanheads/orcid-mcp-server/orcid-guide)<a href="https://agentmods.dev/skills/cyanheads/orcid-mcp-server/orcid-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/orcid-mcp-server/orcid-guide/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/cyanheads/orcid-mcp-server/orcid-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/orcid-mcp-server/orcid-guide.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 | $0.00073 | $0.02275 |
| Opus 5.5 | $0.00029 | $0.00910 |
| Sonnet 5.5 | $0.00015 | $0.00455 |
| Haiku 4.5 | $0.00007 | $0.00228 |
Grade A, and why
orcid-guide 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 yesterday.
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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope
ORCID is an identity registry that researchers curate, not a bibliography or citation index. A record holds what the researcher and member organizations (publishers through Crossref, employers' research systems, funders, review services) added and left public, and it says who asserted each item. Use it to pin an author to a persistent iD and to read affiliations, funding, peer review, and provenance. It carries no citation counts and no full text, and its works list is often partial; use a citation index or Crossref/PubMed for those. Keyless; the anonymous Public API allows 25,000 reads per day per IP address, shared by every caller of a hosted deployment, so fetch what the task needs rather than whole records by reflex.
Identifiers
| Identifier | Comes from | Pass to |
|---|---|---|
ORCID iD (0000-0002-1825-0097; the last character is a check digit, X allowed) |
orcidId on resolver and search results, on every record response, and on linked contributors in work detail |
orcid_id on every record tool |
| Work put-code | putCode on orcid_get_works |
put_codes on orcid_get_work_detail, with the same orcid_id |
| Funding put-code | putCode on an orcid_get_funding summary (the preferred deposit of a grant group) |
put_code on orcid_get_funding |
| Proposal put-code | putCode on an orcid_get_research_resources summary |
put_code on the same tool, which item paging requires |
nextStart |
orcid_search_researchers |
start, same query |
nextOffset |
orcid_get_works, orcid_get_peer_reviews |
offset, same filters |
nextItemOffset |
research-resource detail | item_offset, same put_code |
deferredPutCodes |
orcid_get_work_detail |
put_codes on the next call |
ROR URL (https://ror.org/05gq02987) |
organization.disambiguatedId on an affiliation whose disambiguationSource is ROR |
ror_id on orcid_search_researchers |
Funder ID (http://dx.doi.org/10.13039/100000001) |
funder.disambiguatedId on funding, source FUNDREF |
raw query as fundref-org-id:"…" |
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.
- yesterday First seen · 81 lines · 73 tokens per session scan A aaf5e096f4fd
orcid-guide is a skill published in the GitHub repository cyanheads/orcid-mcp-server (6 stars, last pushed 2d ago), licensed Apache-2.0. It adds 73 tokens to every session and 2,275 once invoked, about $0.0003 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
open-meteo-guide
Tool choice, gates, and workflows for the openmeteo weather tools, covering threshold odds from the ensemble, frost, anomalies against a normal, 2050 projections, surf spots, river flood outlooks, and air quality for a set hour. Use before answering a weather, climate, marine, river, or air-quality question from…
ensembl-guide
Gates and identifier chains for the ensembl tools. Covers checking a coordinate's assembly before you pass it in, finding a gene's counterpart in another species through homology, reading multi-allelic and capped VEP results, and which Ensembl object holds the UniProt, RefSeq, GO, and PDB references. Use when an…
noaa-spaceweather-guide
Judgment for the noaaspaceweather tools — turning SWPC Kp, storm scales, solar wind, flares, and alerts into answers about aurora visibility tonight, coming geomagnetic storms, radio blackouts, and impacts on HF radio, GPS, satellites, and power grids. Use before answering an aurora or space-weather question with…
openchargemap-guide
Assess EV charging options with openchargemap tools. Use when recommending a compatible, accessible charger, checking conflicting reliability evidence, or deciding whether a station search covers the requested area.
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.clientCapabilities, ctx.enrich, ctx.content), and when to use each.
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.