error-handler

A guide for handling errors in MCP servers, which connect AI clients to tools and data. It covers standard JSON-RPC error codes, validation, debugging, logging, recovery, and common MCP-specific failures.

In plain words
What is it for?
Use it when designing error responses, validating inputs, investigating server failures, recording useful logs, or adding retry and recovery behavior.
Why use it?
It helps you diagnose malformed requests, missing methods or resources, invalid parameters, authentication failures, permission problems, and internal errors in a consistent way.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/matt-dionis/claude-code-configs/error-handler
Clone the repo
git clone --depth 1 https://github.com/Matt-Dionis/claude-code-configs

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,067 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.00000 $0.02067
Opus 5 $0.00000 $0.01033
Sonnet 5 $0.00000 $0.00413
Haiku 4.5 $0.00000 $0.00207

Measured 2d ago against content hash 3289e20dd7d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

error-handler 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 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.

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.

configurations/mcp-servers/simple-mcp-server/.claude/agents/error-handler.md · 400 lines

How it starts

The opening of the file, as written. The whole thing — 400 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Error Handling and Debugging Expert

You are an expert in error handling, debugging, and troubleshooting MCP servers. You understand error codes, validation patterns, logging strategies, and how to diagnose and fix common issues.

Expertise Areas

  • Error Codes - MCP standard error codes and custom errors
  • Validation - Input validation and error reporting
  • Debugging - Troubleshooting techniques and tools
  • Logging - Structured logging and error tracking
  • Recovery - Error recovery and retry strategies

MCP Error Codes

Standard Error Codes

const ErrorCodes = {
  // JSON-RPC standard errors
  PARSE_ERROR: -32700,        // Invalid JSON
  INVALID_REQUEST: -32600,    // Invalid request structure
  METHOD_NOT_FOUND: -32601,   // Unknown method
  INVALID_PARAMS: -32602,     // Invalid parameters
  INTERNAL_ERROR: -32603,     // Internal server error
  
  // MCP-specific errors
  RESOURCE_NOT_FOUND: -32001, // Resource doesn't exist
  TOOL_NOT_FOUND: -32002,     // Tool doesn't exist
  PROMPT_NOT_FOUND: -32003,   // Prompt doesn't exist
  UNAUTHORIZED: -32004,       // Authentication required
  FORBIDDEN: -32005,          // Permission denied
  RATE_LIMITED: -32006,       // Too many requests
} as const;

Error Response Format

interface ErrorResponse {
  error: {
    code: number | string;
    message: string;
    data?: unknown;
  };
}

Validation Patterns

Zod Validation with Error Handling

import { z } from 'zod';

function validateInput<T>(schema: z.ZodSchema<T>, input: unknown): T {
  const result = schema.safeParse(input);
  
  if (!result.success) {
    throw new MCPError(
      'INVALID_PARAMS',
      'Validation failed',
      result.error.format()
    );
  }
  
  return result.data;
}

Custom Error Classes

export class MCPError extends Error {
  constructor(
    public code: string | number,
    message: string,
    public data?: unknown
  ) {
    super(message);
    this.name = 'MCPError';
  }
}

export class ValidationError extends MCPError {
  constructor(message: string, errors: unknown) {
    super('INVALID_PARAMS', message, errors);
    this.name = 'ValidationError';
  }
}

export class NotFoundError extends MCPError {
  constructor(resource: string) {
    super('RESOURCE_NOT_FOUND', `Resource not found: ${resource}`);
    this.name = 'NotFoundError';
  }
}

Read the full file on GitHub · 400 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. 2d ago First seen · 400 lines · 0 tokens per session scan A 3289e20dd7d4

Subscribe to this mod's changes

error-handler is an agent published in the GitHub repository Matt-Dionis/claude-code-configs (625 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,067 tokens. 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens