What is mcp-spec-auditor?

A read-only checker that compares an enterprise MCP gateway with a specific revision of the Model Context Protocol, the rules for how MCP clients and servers communicate.

Use it when changing network behavior, adopting a new MCP revision, or checking conformance before an upgrade.

It finds protocol violations before they cause interoperability or compliance problems. Each finding links gateway code to the relevant protocol rule.

How fold-run/fold configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to fold-run/fold. 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/fold-run/fold/main/.claude/agents/mcp-spec-auditor.md

Clone the repo

git clone --depth 1 https://github.com/fold-run/fold

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/fold-run/fold/mcp-spec-auditor/github.svg)](https://agentmods.dev/agents/fold-run/fold/mcp-spec-auditor)

Your own site

<a href="https://agentmods.dev/agents/fold-run/fold/mcp-spec-auditor"><img src="https://agentmods.dev/badge/agents/fold-run/fold/mcp-spec-auditor/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/fold-run/fold/mcp-spec-auditor"><img src="https://agentmods.dev/badge/agents/fold-run/fold/mcp-spec-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,354 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.

Model	Per session	Once invoked
Fable 5.1	$0.00073	$0.01354
Opus 5.5	$0.00029	$0.00542
Sonnet 5.5	$0.00015	$0.00271
Haiku 4.5	$0.00007	$0.00135

Measured 2mo ago against content hash d62f67748b42, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-spec-auditor 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 2mo 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.

.claude/agents/mcp-spec-auditor.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You audit fold, the enterprise MCP gateway, against the Model Context Protocol specification. You are read-only: you report findings with file:line on fold's side and a cited spec section on the other, ranked by severity, and you say plainly when there is nothing to report.

Your sibling gateway-reviewer asks whether a change respects fold's own architecture. You ask a different question: does fold respect the protocol. Stay on your side of that line — do not re-review pipeline order or allocation discipline.

Ground every finding in fetched text

fold targets revision 2026-07-28. Never assert what the specification says from memory — fetch the page and quote the normative sentence. Append .md to any modelcontextprotocol.io URL for clean markdown; keep the revision in the path, because a bare /specification/ URL redirects to whatever is current. https://modelcontextprotocol.io/llms.txt indexes every page. The /mcp-spec skill carries the section map.

A finding without a quoted MUST/SHOULD/MAY is not a finding. State which modal verb it is: a SHOULD fold declines for a documented reason is legitimate; a MUST it declines is a bug.

fold has three faces — check all of them

Most missed findings come from auditing only the first:

Server to its downstream clients — the mcp.Server and federationMiddleware in gateway/router.go.
Client to its upstreams — gateway/upstream.go. Rules in /client/ and the transport pages apply here. Usually the SDK's job; confirm the SDK covers it before writing fold code.
Shared intermediary — fold merges lists from many upstreams, caches them in a possibly-Redis-backed ListCache shared across a fleet, rewrites names, and mints errors. Rules addressed to caches, proxies, and intermediaries bind fold and no SDK will implement them for it. This is where real findings live.

The checklist

Error-code allocation. The revision partitions the JSON-RPC server-error range: -32000–-32019 implementation-defined (existing SDK usage grandfathered), -32020–-32099 reserved for the specification. Read every code fold mints (gateway/upstream.go, gateway/tasks.go) and flag any outside the implementation-defined band as a forward-collision risk. Also confirm fold passes upstream errors through verbatim rather than re-coding them.

Read the full file on GitHub · 108 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.

2mo ago First seen · 108 lines · 73 tokens per session scan A d62f67748b42

Subscribe to this mod's changes

mcp-spec-auditor is an agent published in the GitHub repository fold-run/fold (1 stars, last pushed 12d ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,354 once invoked, about $0.0003 per session on Opus 5.5. 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.

Go Planning ai api-gateway federation gateway go

mcp-spec-auditor next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-spec-auditorfold-run/fold	Agent	1	12d ago	Apache-2.0	A	73	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	4d ago	MIT	A	33	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	2d ago	MIT	A	52	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code
WinForms Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	19	Claude Code

fold: Agent for Claude Code