What is mcp-idempotent CLAUDE.md?

Development instructions for an MCP idempotency proxy. Idempotency means recognizing a repeated request so an action, such as creating a ticket or charging a card, happens only once.

Use them when designing or implementing a proxy that deduplicates ordinary MCP tool calls using idempotency keys, rather than only preventing duplicate task creation.

A retry can repeat a side effect when the first request may already have succeeded. These instructions describe the problem, existing approaches, and the intended project context.

How krish-shahh/mcp-idempotent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to krish-shahh/mcp-idempotent. 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/krish-shahh/mcp-idempotent/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/krish-shahh/mcp-idempotent

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/instructions/krish-shahh/mcp-idempotent/claude-md/github.svg)](https://agentmods.dev/instructions/krish-shahh/mcp-idempotent/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/krish-shahh/mcp-idempotent/claude-md"><img src="https://agentmods.dev/badge/instructions/krish-shahh/mcp-idempotent/claude-md/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/instructions/krish-shahh/mcp-idempotent/claude-md"><img src="https://agentmods.dev/badge/instructions/krish-shahh/mcp-idempotent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,943 This file is loaded in full into every session.

When invoked 1,943 The same file — it is already loaded in full.

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	$0.01943	$0.01943
Opus 5.5	$0.00777	$0.00777
Sonnet 5.5	$0.00389	$0.00389
Haiku 4.5	$0.00194	$0.00194

Measured 2mo ago against content hash 5662b1ab0d38, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-idempotent CLAUDE.md 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.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec: MCP Idempotency Proxy

Context / Prior Art

A retried MCP tool call can re-execute a side effect (double charge, duplicate ticket, etc.). This has been checked against the current landscape and is a real, unclaimed gap:

MCP core spec: SEP-1686 ("Tasks", Final, Oct 2025) adds an idempotency mechanism, but scoped narrowly to task creation — a client-generated task ID lets the server reject a duplicate with an error, so a retried task-augmented request can't spawn a second task. It says nothing about an ordinary tools/call, which is the common case (most tool calls aren't tasks). There is also an idempotentHint tool annotation, but it's a static declaration ("this tool happens to be idempotent"), not an enforcement mechanism — nothing in the protocol checks it or acts on it.
Existing OSS MCP gateways (IBM/mcp-context-forge, microsoft/mcp-gateway, MikkoParkkola/mcp-gateway, aws/mcp-proxy-for-aws): ship auth, rate limiting, observability, and in one case circuit breakers. None ship idempotency-key deduplication of tool calls.
DIY precedent: found blog-post-level Redis middleware snippets solving this per-project, for tools a team already owns. No packaged, reusable, transport-level version exists.

(An earlier draft of this doc cited an arXiv paper as "closest prior art" describing caller-supplied idempotency keys for tool calls. That citation was checked against the actual paper and was wrong — the paper exists but covers a different topic entirely. Removed rather than replaced with an unverified substitute.)

The gap, specifically: an open-source, MCP-transport-aware proxy that adds idempotency-key deduplication generically, in front of any existing, unmodified MCP server. That combination doesn't exist yet.

Objective

A retried MCP tool call should never re-execute a side effect. This proxy sits transparently in front of any existing, unmodified MCP server and adds Stripe-style idempotency-key deduplication to tools/call. If the same logical call is seen twice, the second call returns the cached result instead of hitting the tool again.

Read the full file on GitHub · 157 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 · 157 lines · 1,943 tokens per session scan A 5662b1ab0d38

Subscribe to this mod's changes

mcp-idempotent CLAUDE.md is an instructions file published in the GitHub repository krish-shahh/mcp-idempotent (0 stars, last pushed 3mo ago), licensed MIT. It adds 1,943 tokens to every session, about $0.0078 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.

Backend and APIs ai-agents gateway idempotency idempotent llm-tools mcp

mcp-idempotent CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-idempotent CLAUDE.mdkrish-shahh/mcp-idempotent	Instructions file	0	3mo ago	MIT	A	1,943	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp-idempotent: Instructions file for Claude Code