mcp-spec-compliance

mcp-spec-compliance is a skill for Codex from Agent-Hellboy/mcp-runtime. It costs 148 tokens per session (4,117 once invoked), scanned C, original, Apache-2.0.

An audit of MCP Runtime against the Model Context Protocol specification, the shared rules for MCP clients and servers.

In plain words
What is it for?
Use it to check protocol behavior, detect drift when the specification changes, and confirm findings with live requests.
Why use it?
It finds differences in version negotiation, message formats, HTTP transport, sessions, errors, and advertised capabilities.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: positional $N argument; mentions Codex.

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 skills/agent-hellboy/mcp-runtime/mcp-spec-compliance
Any agent
npx skills add Agent-Hellboy/mcp-runtime --skill mcp-spec-compliance
Clone the repo
git clone --depth 1 https://github.com/Agent-Hellboy/mcp-runtime

Made for: 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-spec-compliance

README.md
[![agentmods](https://agentmods.dev/badge/skills/agent-hellboy/mcp-runtime/mcp-spec-compliance.svg)](https://agentmods.dev/skills/agent-hellboy/mcp-runtime/mcp-spec-compliance)
Your own site
<a href="https://agentmods.dev/skills/agent-hellboy/mcp-runtime/mcp-spec-compliance"><img src="https://agentmods.dev/badge/skills/agent-hellboy/mcp-runtime/mcp-spec-compliance.svg" alt="Measured on agentmods" height="20"></a>
Per session 148 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,117 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 5.1 $0.00148 $0.04117
Opus 5 $0.00074 $0.02058
Sonnet 5 $0.00030 $0.00823
Haiku 4.5 $0.00015 $0.00412

Measured 5d ago against content hash 92ebc3d69b55, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

mcp-spec-compliance scanned grade C with 2 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 5d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

trap 'rm -rf "$MCP_SPEC_TMP"' EXIT

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

[ -s "$out" ] || curl -fsSL "$url" -o "$out"
.codex/skills/mcp-spec-compliance/SKILL.md · 359 lines

How it starts

The opening of the file, as written. The whole thing — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Spec Compliance Audit

Overview

This skill audits MCP Runtime — the proxy/gateway, example servers, agent adapters, and the CLI probe — against the upstream Model Context Protocol specification at https://github.com/modelcontextprotocol/modelcontextprotocol. The spec is versioned (2024-11-05, 2025-03-26, 2025-06-18, draft); the runtime currently pins 2025-06-18 (see internal/agentadapter/config.go: DefaultProtocolVersion).

Goals:

  • Confirm the runtime correctly implements the spec revision it claims to support — protocol-version negotiation, Streamable HTTP, JSON-RPC 2.0 envelope, tools/resources/prompts/sampling shapes, session semantics, error codes, and capability advertisement.
  • Detect drift from the upstream schema (fields renamed, fields removed, required-fields changes) when bumping pinned revision.
  • Surface relevant merged SEPs and open SEP PRs that affect runtime behavior.
  • Distinguish "spec says X, runtime does X" from "spec says X, runtime does Y" from "spec is silent, runtime does Y by choice."

Regression evidence contract: static schema/code checks are only half of this skill. For protocol-affecting changes, run live initialize, positive tools/call, and malformed/unsupported-version negative cases against the Kind cluster. If upstream fetch or live transport checks cannot run, report the result blocked for that surface.

Non-goals:

  • Auth/grant/session policy enforcement → qa-e2e-security.
  • Operator/CLI/setup regressions → qa-e2e-operations.
  • Cluster RBAC/PSS hygiene → k8s-hardening-audit.

Step 1 — Pin the spec revision under audit

SPEC_REPO="${SPEC_REPO:-https://github.com/modelcontextprotocol/modelcontextprotocol}"
SPEC_REV="${SPEC_REV:-$(grep -oE '"20[0-9]{2}-[0-9]{2}-[0-9]{2}"' \
  internal/agentadapter/config.go | head -1 | tr -d '"')}"
SPEC_REF="${SPEC_REF:-main}"     # upstream branch or tag to fetch from
echo "Auditing runtime against MCP spec rev=$SPEC_REV @ ref=$SPEC_REF"

Read the full file on GitHub · 359 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 359 lines · 148 tokens per session scan C 92ebc3d69b55

Subscribe to this mod's changes

mcp-spec-compliance is a skill published in the GitHub repository Agent-Hellboy/mcp-runtime (6 stars, last pushed 3d ago), licensed Apache-2.0. It adds 148 tokens to every session and 4,117 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). 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

local-frontend-check

Smoke-test or verify UI behaviour on the local Jarvis Registry frontend running at http://localhost/gateway. Use for manual regression checks, bug-fix verification, and end-to-end confirmation of specific flows without running the automated test suite.

ascending-llc/jarvis-registry · 52 tokens

generate-server-card

Generate an MCP server card JSON (mcp-gateway-registry format) by analyzing server source code in a folder or GitHub URL. Studies code to detect server name, tools, transport, auth, and generates a registry-compatible config.

agentic-community/mcp-gateway-registry · 52 tokens

debug

Debug issues in the MCP Gateway Registry using first-principles thinking. Invoke when something is broken, timing out, returning errors, or behaving unexpectedly. Forces structured root-cause analysis before any code change is proposed.

agentic-community/mcp-gateway-registry · 45 tokens

build-audit-logs

Build or review audit trails in TypeScript/JavaScript apps using evlog (pipelines, typed actions, denials, retention, compliance-style reviews). For application code, not for extending the evlog package.

activepieces/activepieces · 49 tokens

playwright-e2e-testing

Playwright modern end-to-end testing framework with cross-browser automation, auto-wait, and built-in test runner.

activepieces/activepieces · 29 tokens

triage-image-cves

Scan an Activepieces Docker image with grype for OS/base-image (deb) and application (npm) CVEs of High/Critical severity. Lists the 3 most-recent published tags and lets the user pick which to scan, validates each finding is real and reachable, and proves candidate fixes in an isolated git worktree (rebuild image +…

activepieces/activepieces · 136 tokens