helix.mcp: Skill for Claude Code

.squad/skills/mcp-error-surfacing/SKILL.md

mcp-error-surfacing is a skill for Claude Code, Codex from lewing/helix.mcp. It costs 0 tokens per session (2,840 once invoked), scanned A, original, MIT.

An error-handling component for MCP tools that makes selected detailed errors visible to clients. MCP is a standard way for AI applications to call external tools.

In plain words
What is it for?
Surfacing invalid tool arguments, intercepting parameter-binding failures, and returning clearer errors across the protected MCP tools.
Why use it?
It replaces vague tool-failure messages with useful details when argument binding or tool invocation fails, helping developers find the cause.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is lewing/helix.mcp's own configuration. It tells Claude Code and Codex how to work on helix.mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything helix.mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lewing/helix.mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lewing/helix.mcp/main/.squad/skills/mcp-error-surfacing/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lewing/helix.mcp

Made for: Claude Code, Codex.

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 mcp-error-surfacing

README.md
[![agentmods](https://agentmods.dev/badge/skills/lewing/helix.mcp/mcp-error-surfacing.svg)](https://agentmods.dev/skills/lewing/helix.mcp/mcp-error-surfacing)
Your own site
<a href="https://agentmods.dev/skills/lewing/helix.mcp/mcp-error-surfacing"><img src="https://agentmods.dev/badge/skills/lewing/helix.mcp/mcp-error-surfacing.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,840 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.02840
Opus 5 $0.00000 $0.01420
Sonnet 5 $0.00000 $0.00568
Haiku 4.5 $0.00000 $0.00284

Measured 8d ago against content hash 1f42340a445f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mcp-error-surfacing 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 8d 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.

.squad/skills/mcp-error-surfacing/SKILL.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Error Surfacing via McpException

Updated: 2026-05-28 (CallToolFilters middleware implemented + schema audit findings captured)

Core Strategy

The MCP SDK deliberately suppresses inner exception messages as a security boundary. Our strategy is NOT to bypass this; it's to use McpException as the designated channel where we want clients to see detail. The MCP SDK's CallToolFilters middleware pipeline provides a clean interception point for SDK parameter binding failures.

Three Layers of MCP Error Handling

Layer 1: SDK Parameter Binding — FIXED via CallToolFilters (v0.7.5)

  • Exception source: Microsoft.Extensions.AI.AIFunctionFactory during reflection-based parameter marshalling
  • Observable: Exception logged to stderr, generic "An error occurred invoking 'X'." sent to client before the fix
  • McpExceptionHandler reached? ❌ No (method not invoked)
  • Our fix:CallToolFilters middleware — intercept ArgumentException where ParamName == "arguments", convert to McpException
  • Scope: All 25 tools automatically protected from both MCP startup paths
  • Example: Agent uses buildIdOrUrl on a Helix tool expecting jobId (parameter binding fails)

Layer 2: MCP Server Error Formatting (Infrastructure)

  • Exception source: MCP Server's unhandled-exception handler
  • Observable: Full exception logged to stderr, generic response to client
  • Our lever: custom middleware only if the current CallToolFilters approach proves insufficient

Layer 3: Application Layer — COVERED via PR #64 (Runtime Exceptions)

  • Exception source: Service layer, API client, or application code
  • McpExceptionHandler reached? ✅ Yes (caught inside RunServiceCallAsync)
  • Our fix: ✅ PR #64 (complete)
  • Example: HttpRequestException, TaskCanceledException, ArgumentException from business logic

CallToolFilters Pattern (Class A Fix — v0.7.5)

Register cross-cutting CallToolFilters middleware through an extension method on McpServerOptions, shared by both startup paths. The ModelContextProtocol 1.3.0 API path is McpServerOptions.Filters.Request.CallToolFilters; this repo scopes the catch to ArgumentException with ParamName == "arguments" via a named constant so ordinary tool-body ArgumentExceptions are not mislabeled as binding failures.

Read the full file on GitHub · 237 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. 8d ago First seen · 237 lines · 0 tokens per session scan A 1f42340a445f

Subscribe to this mod's changes

mcp-error-surfacing is a skill published in the GitHub repository lewing/helix.mcp (4 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,840 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 2026-08-31.

Related

Other skills, from other repositories

printing-press-amend

Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…

mvanhorn/cli-printing-press · 222 tokens

debug

Systematic 4-phase debugging with escalation protocol. Use when saying "debug", "investigate bug", "find root cause", "why is this failing", or "fix this bug".

anton-abyzov/specweave · 38 tokens

runtime-admin-api

Call the Mendix M2EE admin API on port 8090 directly — OQL, runtime info, and the rest, with curl examples. Use when querying a running app from a script, or when debugging connectivity to the admin port.

mendixlabs/mxcli · 53 tokens

csharp-dotnet

Use when writing, reviewing, testing, or shipping C# / .NET code — ASP.NET Core APIs (minimal APIs vs controllers), EF Core data access, async correctness, solution layout in .cs/.csproj/.sln. NOT a Java/Spring backend (that is spring-boot), NOT a Node/TypeScript backend (that is nestjs), NOT framework-neutral REST…

ericrisco/rsc-harness · 89 tokens

doris-debug-deployment

Use for Doris FE/BE startup failures, port conflicts, prioritynetworks misrouting, metadir corruption, and ADD/DROP BACKEND issues.

apache/doris-skills · 36 tokens

argot-refresh

Refresh Argot's committed fit snapshot safely — first diagnose why maintenance is recommended, re-audit corpus scope and structural path changes, review stale mutes and policy entries with the user, then fit locally, verify, and prepare the reviewed .argot/ update. Use when argot status, argot check, MCP, or CI…

get-tmonier/argot · 136 tokens