api-errors

api-errors is a skill for Claude Code from cyanheads/workflows-mcp-server. It costs 54 tokens per session (15,756 once invoked), scanned A, a copy of api-errors, Apache-2.0.

A reference for handling errors in MCP servers built with @cyanheads/mcp-ts-core. MCP is a standard way for an AI agent to call tools and resources; the reference explains error types, error codes, and where errors should be handled.

In plain words
What is it for?
Use it when adding or reviewing MCP tools and resources, choosing an error code, declaring possible failure reasons, or deciding whether an error belongs in a handler or service.
Why use it?
It helps keep errors consistent between tool handlers and the services they call. This makes failures easier to report, log, and check in TypeScript.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the workflows-mcp-server plugin — 33 skills, 1 MCP server shipped together

Good fit Use it when adding or reviewing MCP tools and resources, choosing an error code, declaring possible failure reasons, or deciding whether an error belongs in a handler or service.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cyanheads/workflows-mcp-server/api-errors
Install

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.

Any agent
npx skills add cyanheads/workflows-mcp-server --skill api-errors
Clone the repo
git clone --depth 1 https://github.com/cyanheads/workflows-mcp-server

Made for: Claude Code.

Or install workflows-mcp-server, the plugin that ships this one along with the rest of its 33 skills, 1 MCP server.

Wrote 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.

agentmods badge for api-errors

README.md
[![agentmods](https://agentmods.dev/badge/skills/cyanheads/workflows-mcp-server/api-errors/github.svg)](https://agentmods.dev/skills/cyanheads/workflows-mcp-server/api-errors)
Your own site
<a href="https://agentmods.dev/skills/cyanheads/workflows-mcp-server/api-errors"><img src="https://agentmods.dev/badge/skills/cyanheads/workflows-mcp-server/api-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.

agentmods 80×15 button for api-errors

Your own site · 80×15
<a href="https://agentmods.dev/skills/cyanheads/workflows-mcp-server/api-errors"><img src="https://agentmods.dev/badge/skills/cyanheads/workflows-mcp-server/api-errors.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 15,756 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.15756
Opus 5.5 $0.00022 $0.06302
Sonnet 5.5 $0.00011 $0.03151
Haiku 4.5 $0.00005 $0.01576

Measured today against content hash 33715394f36d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 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.

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);
Origin

This is a copy

100% identical to api-errors — 7 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.

framework-skills/api-errors/SKILL.md · 597 lines

How it starts

The opening of the file, as written. The whole thing — 597 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';

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 };
  },
});

Read the full file on GitHub · 597 lines

Changes

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.

  1. today Changed · +2 lines 33715394f36d
  2. 18d ago Changed · +8 lines 19047ca1133d
  3. 1mo ago Changed · +53 lines 5fd057c0d5b3
  4. 1mo ago Changed · +2 lines c6d47b2125fb
  5. 1mo ago Changed · +3 lines 8ea5eb027af4
  6. 1mo ago First seen · 529 lines · 54 tokens per session scan A 140957b2714f

Subscribe to this mod's changes

api-errors is a skill published in the GitHub repository cyanheads/workflows-mcp-server (31 stars, last pushed today), licensed Apache-2.0. It adds 54 tokens to every session and 15,756 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to api-errors, differing in 7 lines, and is treated as a copy.

Related

Other skills, from other repositories

n8n-docs-assistant

Answers n8n product, setup, credential, node, hosting, API, and usage questions from current n8n docs. Use when the user asks how to configure, set up, troubleshoot, or understand n8n behavior, especially credential setup questions — including which OAuth scopes or permissions a provider app needs.

n8n-io/n8n · 71 tokens

orchardcore-diagnostics

Skill for configuring Orchard Core diagnostics error handling. Covers custom error pages, status code pages, DiagnosticsStartupFilter, IConfigureOptions integration, error shapes, alternate shape names, the 429 Too Many Requests page, Problem Details for Api and SkipStatusCodePages responses, and production exception…

CrestApps/CrestApps.AgentSkills · 193 tokens

diagnose-connectivity

Work out why a 3x-ui client cannot connect, in the order that finds the cause fastest — scope the outage, check the core, the inbound, the client's own limits, routing and outbounds, then the node. Use whenever someone reports "it stopped working", a client cannot connect, a site is unreachable through the proxy, or…

pyworkload/3x-ui-mcp · 83 tokens

dev-tasks

Guides for common development tasks like adding facet fields, file format support, STDIO debugging, and performance tuning. Use when working on specific development recipes.

mirkosertic/MCPLuceneServer · 35 tokens

keycloak-migration-doctor

Preflight a Keycloak export, import or migration on a Skycloak-managed cluster against the known blockers, and diagnose a job that already failed by reading the failure reason the API records but the dashboard notice does not show. Use when an export or import fails, a migration stalls, or before moving realm data in…

sky-cloak/skycloak-mcp · 72 tokens

api-errors

McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.

cyanheads/mcp-ts-core · 54 tokens