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 helena-bioinformatics/noodle-mcp --skill noodle-biomedical-literature-discoverygit clone --depth 1 https://github.com/helena-bioinformatics/noodle-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/helena-bioinformatics/noodle-mcp/noodle-biomedical-literature-discovery)<a href="https://agentmods.dev/skills/helena-bioinformatics/noodle-mcp/noodle-biomedical-literature-discovery"><img src="https://agentmods.dev/badge/skills/helena-bioinformatics/noodle-mcp/noodle-biomedical-literature-discovery/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/helena-bioinformatics/noodle-mcp/noodle-biomedical-literature-discovery"><img src="https://agentmods.dev/badge/skills/helena-bioinformatics/noodle-mcp/noodle-biomedical-literature-discovery.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 | $0.00105 | $0.00816 |
| Opus 5.5 | $0.00042 | $0.00326 |
| Sonnet 5.5 | $0.00021 | $0.00163 |
| Haiku 4.5 | $0.00011 | $0.00082 |
Grade A, and why
noodle-biomedical-literature-discovery 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 1mo 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Noodle Biomedical Literature Discovery MCP
Use the public read-only Noodle endpoint for source-linked biomedical literature discovery, including citation and semantic neighborhoods, instead of relying on model memory for bibliographic facts or related-paper claims.
Boundary
- Send only public, non-sensitive research questions and publication identifiers.
- Never send patient, private case, clinical-record, uploaded-file, credential, or other sensitive data.
- Search rank, semantic similarity, citation proximity, co-mention, and graph distance are discovery signals. They do not establish causality, validity, diagnosis, or treatment.
- Preserve publication identifiers, source URLs, match reasons, edge types, graph version, corpus provenance, and limitations returned by the service.
- Verify material scientific conclusions in the linked primary publications and distinguish author claims from established evidence.
Route the task
- Call
search_biomedical_literaturefor a natural-language biomedical question or any PMID, DOI, or PMCID. Include every known identifier in the query so exact anchors can be applied. - Call
get_publication_detailswhen the user supplies a PMID or selects a result with a PMID. - Call
get_work_detailswhen the user supplies or selects a Noodle work identifier, including records without a PMID. - Call
get_publication_neighborhoodto traverse citation and semantic neighbors from a PMID. - Call
get_work_neighborhoodto traverse from a Noodle work identifier or continue a path throughfrom_work_id. - Call
get_corpus_summaryfor corpus size, sources, freshness, coverage, or active graph metadata. - Call
support_helenaonly after the user explicitly asks how to support Helena. It is separate opt-in information and never changes scientific results.
Traverse the graph
- Begin with a resolved PMID or work ID; do not invent an anchor.
- Request one bounded neighborhood at a time.
- Report every returned edge using its exact type and endpoints.
- Use
from_work_idwhen continuing from a displayed neighbor so the service can preserve traversal context. - Keep a visited-ID set in the response workflow, avoid loops, and state the number of hops actually traversed.
- Do not describe an unreturned direct edge, shortest path, causal relationship, or complete graph.
- If the next node has no returned neighborhood, stop and report the boundary instead of guessing.
What ships with it
1 file 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.
- 1mo ago First seen · 52 lines · 105 tokens per session scan A 4a9383fc7f8a
noodle-biomedical-literature-discovery is a skill published in the GitHub repository helena-bioinformatics/noodle-mcp (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 105 tokens to every session and 816 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
mitiq-error-mitigation
A local experiment runner for testing four ways to reduce errors in sampled quantum circuits: zero-noise extrapolation, readout correction, probabilistic error cancellation, and Clifford data regression. It compares noisy and mitigated results under the same sampling budget.
quantum-ground-state
A narrowly defined quantum solver for the ground-state energy of a two-quantum-bit Pauli Hamiltonian in a specified one-excitation sector. It uses a noiseless statevector VQE and checks the result against an exact calculation; VQE is a method that searches for a low-energy quantum state.
qmclaw-workbench
A local simulator for superconducting quantum-bit experiments, including measurements used to study and tune a qubit. It produces bounded synthetic results without connecting to laboratory hardware or quantum cloud services.
sqd-chemistry
A small quantum-chemistry calculation for an H2 molecule using the STO-3G basis, a simplified representation of atomic orbitals. It samples a reduced space, estimates its energy, and compares it with full configuration interaction, an exact calculation within the same small model.
quantum-advection
A local workflow for simulating one-dimensional advection, the movement of a quantity through space, with a quantum circuit. It supports constant speed, periodic boundaries, and a finite-difference approximation.
quantum-amplitude-amplification
A local Qiskit workflow for amplitude amplification, a quantum method that increases the chance of measuring selected answers. It can explain the method, build a circuit, or run calculations on a simulator.