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 pascalwhoop/medical-mcps --skill everycure-kggit clone --depth 1 https://github.com/pascalwhoop/medical-mcpsWrote 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/pascalwhoop/medical-mcps/everycure-kg)<a href="https://agentmods.dev/skills/pascalwhoop/medical-mcps/everycure-kg"><img src="https://agentmods.dev/badge/skills/pascalwhoop/medical-mcps/everycure-kg/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/pascalwhoop/medical-mcps/everycure-kg"><img src="https://agentmods.dev/badge/skills/pascalwhoop/medical-mcps/everycure-kg.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00152 | $0.05198 |
| Opus 5 | $0.00076 | $0.02599 |
| Sonnet 5 | $0.00030 | $0.01040 |
| Haiku 4.5 | $0.00015 | $0.00520 |
Grade A, and why
everycure-kg 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 11d 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 — 600 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Everycure Knowledge Graph Skill
Overview
The Everycure KG is a massive biomedical knowledge graph (9.2M nodes, 77M relationships) built on the Biolink Model. It integrates data on drugs, diseases, genes, proteins, pathways, and their relationships.
Key Challenge: The graph is extremely densely connected. Naive queries cause path explosion (~440x growth per hop).
Safety Built-In: The MCP server includes automatic safety checks:
- Warns on high-degree nodes (>1K edges)
- Blocks queries on super-hubs (>10K edges)
- Prevents path explosion before executing queries
- Handles schema quirks automatically in predefined metapaths
This skill teaches you to query effectively and work within the safety guardrails.
Quick Start
Finding Drug Repurposing Opportunities
Question: "Does Metformin treat Idiopathic Pulmonary Fibrosis?"
Step 1: Find node IDs
# Use execute_cypher to find nodes
result = execute_cypher("""
MATCH (d) WHERE d.name CONTAINS 'Metformin' AND 'biolink:Drug' IN labels(d)
RETURN d.id, d.name LIMIT 5
""")
# Result: CHEBI:6801
result = execute_cypher("""
MATCH (dis) WHERE dis.name CONTAINS 'pulmonary fibrosis' AND 'biolink:Disease' IN labels(dis)
RETURN dis.id, dis.name LIMIT 5
""")
# Result: MONDO:0800029
Step 2: Check direct treatment relationship (1-hop)
result = find_paths_by_metapath(
source_id="CHEBI:6801",
target_id="MONDO:0800029",
metapath_name="drug_to_disease_direct"
)
# Result: FOUND - Direct treatment relationship exists!
Step 3: Find mechanistic targets (2-hop)
result = find_paths_by_metapath(
source_id="CHEBI:6801",
target_id="MONDO:0800029",
metapath_name="drug_to_disease_via_target"
)
# Result: 50+ proteins including HDAC6 (AMPK pathway)
Core Principles
1. Always COUNT Before RETURN
Path explosion happens when you RETURN data before counting.
// WRONG (will hang on large results):
MATCH (d)-[r1]-(mid)-[r2]-(target)
WHERE d.id = $drug_id
RETURN d, mid, target LIMIT 100
// CORRECT (count first):
MATCH (d)-[r1]-(mid)-[r2]-(target)
WHERE d.id = $drug_id
RETURN COUNT(*) as path_count
// If path_count < 1000, then run:
// MATCH... RETURN d, mid, target LIMIT 100
What ships with it
5 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.
- 11d ago First seen · 600 lines · 152 tokens per session scan A f45173fcf984
everycure-kg is a skill published in the GitHub repository pascalwhoop/medical-mcps (23 stars, last pushed 9d ago), licensed MIT. It adds 152 tokens to every session and 5,198 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
pkpd-modeling
Pharmacokinetic and pharmacodynamic modelling and simulation - non-compartmental analysis, compartmental and population PK, PK/PD and exposure-response, TMDD, PBPK orientation, bioequivalence, allometric scaling and first-in-human dose, drug interaction prediction, and Bayesian therapeutic drug monitoring. Use when…
biopython
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
neuropixels-analysis
Analyze Neuropixels extracellular recordings end-to-end with SpikeInterface. Covers loading SpikeGLX/Open Ephys/NWB data, preprocessing, drift/motion correction, Kilosort4 (and CPU) spike sorting, quality metrics, and unit curation (threshold-based, model-based UnitRefine, and AI-assisted visual review). Use when…
onekgpd
Query the 1000 Genomes Project dataset (3,202 whole-genome-sequenced individuals, GRCh38) at the level of individual participants. Use when a question is about individuals or variants in the 1000 Genomes Project cohort: which individuals carry variants matching specific criteria in a gene or region, which individuals…
pydicom
Use pydicom to read, inspect, write, transform, and safely preflight local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.