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/cyanheads/pubchem-mcp-server/api-errorsnpx skills add cyanheads/pubchem-mcp-server --skill api-errorsgit clone --depth 1 https://github.com/cyanheads/pubchem-mcp-serverWhat 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 | $0.00054 | $0.06958 |
| Opus 5 | $0.00027 | $0.03479 |
| Sonnet 5 | $0.00011 | $0.01392 |
| Haiku 4.5 | $0.00005 | $0.00696 |
Grade A, and why
api-errors scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const articles = await ncbi.fetch(input.pmids); This is a copy
100% identical to api-errors — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 529 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Error handling in @cyanheads/mcp-ts-core follows a strict layered pattern: tool and resource handlers throw McpError freely (no try/catch), the handler factory catches and normalizes all errors, and services use ErrorHandler.tryCatch for structured logging and wrapping.
Imports:
import { notFound, validationError, McpError, JsonRpcErrorCode } from '@cyanheads/mcp-ts-core/errors';
import { ErrorHandler } from '@cyanheads/mcp-ts-core/utils';
Type-Driven Error Contract (recommended)
The recommended path for new tools and resources. Declare failure modes as a const tuple under errors; the reason union flows into the handler's ctx.fail and TypeScript enforces that you can only fail with a declared reason:
import { tool, z } from '@cyanheads/mcp-ts-core';
import { JsonRpcErrorCode } from '@cyanheads/mcp-ts-core/errors';
export const fetchTool = tool('fetch_articles', {
description: 'Fetch articles by PMID',
input: z.object({ pmids: z.array(z.string()).describe('PMIDs') }),
output: z.object({ articles: z.array(z.unknown()).describe('Articles') }),
errors: [
{ reason: 'no_match', code: JsonRpcErrorCode.NotFound,
when: 'No requested PMID returned data',
recovery: 'Try pubmed_search_articles to discover valid PMIDs first.' },
{ reason: 'queue_full', code: JsonRpcErrorCode.RateLimited,
when: 'Local request queue is at capacity', retryable: true,
recovery: 'Wait 30 seconds and retry, or reduce batch size.' },
{ reason: 'ncbi_down', code: JsonRpcErrorCode.ServiceUnavailable,
when: 'NCBI E-utilities unreachable after retries', retryable: true,
recovery: 'NCBI is degraded; retry in a few minutes.' },
],
async handler(input, ctx) {
const articles = await ncbi.fetch(input.pmids);
if (articles.length === 0) {
throw ctx.fail('no_match', `None of ${input.pmids.length} PMIDs returned data`);
}
// ctx.fail('typo') ← TypeScript error: 'typo' isn't in the contract
return { articles };
},
});
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.
- 2d ago First seen · 529 lines · 54 tokens per session scan A 140957b2714f
api-errors is a skill published in the GitHub repository cyanheads/pubchem-mcp-server (9 stars, last pushed 12d ago), licensed Apache-2.0. It adds 54 tokens to every session and 6,958 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to api-errors, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
pepflex
Use when working with PepFlex for in silico peptide screening and evolutionary optimization. Handles peptide population management, mutation, crossover, custom evaluation pipelines, and multi-round evolutionary simulation.
chem-brainstorm
Use at the start of any computational chemistry task to structure thinking, map available tools, and generate concrete hypotheses. Covers molecule evaluation, hypothesis building, reaction assessment, and pipeline design. Flexible guide — adapt depth to problem complexity.
generative-design
Use when designing or evaluating generative models for de novo drug/molecule design. Covers molecular generation theory and evaluation (MOSES/GuacaMol), SELFIES + language models, RL-based optimization with REINVENT 4, JT-VAE and graph-based generation, and structure-based 3D generation (DiffSBDD, Pocket2Mol…
homology-modeling
Use when building a 3D protein structure from sequence (no experimental structure available). Covers comparative homology modeling (MODELLER), AI-based prediction (AlphaFold2/ColabFold/ESMFold), model quality assessment (DOPE, pLDDT, Ramachandran), template search (HHblits, BLAST, Biopython), and structure preparation…
lit-rescue
Last-resort skill. Invoke when no obvious or coherent solution is available and hallucination risk is high. Searches peer-reviewed literature and validated sources (Perplexity, bioRxiv, PubMed) before attempting an answer. Generalist — applies to any domain.
uncertainty-qsar
Use when building QSAR/ML models that need calibrated uncertainty estimates. Covers epistemic vs aleatoric uncertainty theory, conformal prediction with MAPIE (guaranteed coverage), Gaussian processes with Tanimoto kernel, deep uncertainty (MC dropout, deep ensembles, Laplace), and applicability domain (AD)…