helix.mcp: Skill for Claude Code

.squad/skills/mcp-strict-param-rejection/SKILL.md

mcp-strict-param-rejection is a skill for Claude Code, Codex from lewing/helix.mcp. It costs 39 tokens per session (1,778 once invoked), scanned A, original, MIT.

A rule set for MCP tool calls that rejects parameter names a tool does not support and can suggest the correct name for misspellings. MCP is a standard way for AI clients to call tools provided by another program.

In plain words
What is it for?
Use it when configuring MCP servers to validate incoming arguments and return clear errors or “did you mean” suggestions.
Why use it?
It prevents misspelled or invented parameters from being silently ignored, which could lead to incomplete or incorrect tool actions.

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-strict-param-rejection/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-strict-param-rejection

README.md
[![agentmods](https://agentmods.dev/badge/skills/lewing/helix.mcp/mcp-strict-param-rejection/github.svg)](https://agentmods.dev/skills/lewing/helix.mcp/mcp-strict-param-rejection)
Your own site
<a href="https://agentmods.dev/skills/lewing/helix.mcp/mcp-strict-param-rejection"><img src="https://agentmods.dev/badge/skills/lewing/helix.mcp/mcp-strict-param-rejection/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 mcp-strict-param-rejection

Your own site · 80×15
<a href="https://agentmods.dev/skills/lewing/helix.mcp/mcp-strict-param-rejection"><img src="https://agentmods.dev/badge/skills/lewing/helix.mcp/mcp-strict-param-rejection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,778 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 $0.00039 $0.01778
Opus 5 $0.00019 $0.00889
Sonnet 5 $0.00008 $0.00356
Haiku 4.5 $0.00004 $0.00178

Measured 10d ago against content hash 37401825178e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-strict-param-rejection 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 10d 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-strict-param-rejection/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context

Use when adding strict unknown-parameter rejection so callers receive a structured McpException instead of silent data loss when they pass a hallucinated or misspelled parameter name.

Two complementary layers — deploy both for best UX + safety:

  • Stage A — SDK-level UnmappedMemberHandling.Disallow (stopgap; no hints)
  • Stage BAddUnknownParameterFilter CallToolFilter (polished UX with "did you mean" hints)

Stage A — SDK Strict Rejection (Stopgap)

SDK Mechanism

Microsoft.Extensions.AI.Abstractions 10.5.2 (shipped with MCP 1.3.0+) includes a strict check in ReflectionAIFunction.InvokeCoreAsync:

if (SerializerOptions.UnmappedMemberHandling == Disallow && !HasCustomParameterBinding)
    throw ArgumentException(paramName: "arguments",
        message: "The arguments dictionary contains an unexpected key 'X' that does not correspond to any parameter of 'Y'.");

HasCustomParameterBinding is true only when a tool parameter has a non-null BindParameter callback (DI injection). Plain value-type and string params have HasCustomParameterBinding = false → strict check fires.

How to Enable

Pass a JsonSerializerOptions with UnmappedMemberHandling = Disallow and TypeInfoResolver = new DefaultJsonTypeInfoResolver() to WithToolsFromAssembly:

using System.Text.Json.Serialization.Metadata;

.WithToolsFromAssembly(typeof(MyTools).Assembly, new JsonSerializerOptions
{
    UnmappedMemberHandling = JsonUnmappedMemberHandling.Disallow,
    TypeInfoResolver = new DefaultJsonTypeInfoResolver(),  // ← required companion; see below
})

Apply to both HTTP and stdio transport registrations if both are used.

Why TypeInfoResolver is required

AIFunctionFactory.GetOrCreate (in Microsoft.Extensions.AI.Abstractions) calls MakeReadOnly() on the passed JsonSerializerOptions before the tool descriptor is constructed. The constructor then calls AIJsonUtilities.CreateFunctionJsonSchemaCreateJsonSchemaCore, which contains:

Read the full file on GitHub · 161 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. 10d ago First seen · 161 lines · 39 tokens per session scan A 37401825178e

Subscribe to this mod's changes

mcp-strict-param-rejection is a skill published in the GitHub repository lewing/helix.mcp (4 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 1,778 once invoked, about $0.0002 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 2026-08-31.