avanan-legacy-mcp: Instructions file for Claude Code

CLAUDE.md

avanan-legacy-mcp CLAUDE.md is an instructions file for Claude Code from WYRE-AI/avanan-legacy-mcp. It costs 1,185 tokens per session, scanned A, original, Apache-2.0.

Project instructions for developing and releasing an MCP server that connects to Avanan's MSP SmartAPI. They document setup commands, authentication details, tests, UI rebuilding, and lessons learned from the release process.

In plain words
What is it for?
Use them when testing, type-checking, linting, building, editing the web interface, configuring API credentials, or preparing a registry release for this project.
Why use it?
They keep development and release work aligned with verified API behaviour and repository checks. They also warn about handling secrets, date formatting, and description-length limits that can break releases.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is WYRE-AI/avanan-legacy-mcp's own configuration. It tells Claude Code how to work on avanan-legacy-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 avanan-legacy-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to WYRE-AI/avanan-legacy-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/WYRE-AI/avanan-legacy-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/WYRE-AI/avanan-legacy-mcp

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.

agentmods badge for avanan-legacy-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/wyre-ai/avanan-legacy-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/wyre-ai/avanan-legacy-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/wyre-ai/avanan-legacy-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/wyre-ai/avanan-legacy-mcp/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.

agentmods 80×15 button for avanan-legacy-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/wyre-ai/avanan-legacy-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/wyre-ai/avanan-legacy-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,185 This file is loaded in full into every session.
When invoked 1,185 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01185 $0.01185
Opus 5.5 $0.00474 $0.00474
Sonnet 5.5 $0.00237 $0.00237
Haiku 4.5 $0.00119 $0.00119

Measured 1mo ago against content hash ac8ca893c32b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

avanan-legacy-mcp 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 1mo 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 · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

avanan-legacy-mcp

MCP server for the Avanan MSP SmartAPI. Configuration and the verified auth wire format are in README.md.

Development

  • npm test (vitest), npm run typecheck, npm run lint, npm run build.
  • tests/client.test.ts pins the live-verified auth contract. Do not "correct" the x-av-date format back to the guide's .000Z; the API rejects it.
  • Rebuild src/generated/tenant-card-html.ts with npm run build:ui after editing ui/.
  • Live checks need an MSP API key (AVANAN_CLIENT_ID / AVANAN_CLIENT_SECRET). Never commit one.

Learnings - 2026-09-09

  • The MCP Registry rejects server.json with description longer than 100 characters (422 expected length <= 100). That check runs only in the release job, after the GitHub release and GHCR push have already happened, so a long description costs a whole release number. Keep it under 100 and check with python3 -c 'import json;print(len(json.load(open("server.json"))["description"]))'.

  • The SmartAPI returns HTTP 500 {"message":"Internal Server Error"} on every path when x-av-date ends in Z. This looked like a broken signature for a long time; it is the date. Send new Date().toISOString().slice(0, -1).

  • x-av-sig = sha256(base64(reqId + appId + date [+ path?query] + secret)) hex. The path is included on data requests and omitted on /auth. Reference implementation: https://www.avanan.com/hubfs/MSP/documents/Smart-API-Documentation/parent_msp/client/client.py

  • Error triage by shape: {"message":"Unauthorized"} = no x-av-* headers reached the authorizer; {"message":"Forbidden"} = signature wrong (usually the path was left out); a responseEnvelope with 403 MSP endpoint, access denied = signature fine, the key is a customer-tenant key rather than an MSP key.

  • The WYRE key tested today (client id 473a…) has JWT scope mt-prod-3:wyretechnology, i.e. a tenant key. /v1.0/scopes and /v1.0/event/query work with it; all /msp/* tools are blocked until an MSP-level key is generated from the MSP portal.

  • List endpoints take scrollId / MSPId as a JSON body on GET. WHATWG fetch throws on that, hence the small node:https wrapper in src/utils/transport.ts.

  • The /auth response body is the raw JWT (Cognito access token), not JSON. It carries exp (one hour) but no region claim.

  • The tenant-security endpoints (/event/query, /search/query, /exceptions/*, /action/*, /task/*, /scopes) live on the same host with the same signing and accept a customer-tenant key. Verified live 2026-09-09 with the WYRE tenant key: 454 events in 24h, entity search, exception lists. /search/query caps recordsNumber at 10000.

  • scopes (array) goes on /event/query and /search/query; scope (single string) goes on /action/event and /action/entity. Exceptions take no scope field.

  • MSP API keys are not self-service. The guide says they are "received from Avanan Support"; WYRE customers who buy through Solutions Granted open the request there, and only direct Check Point customers go to Check Point. One key per region.

  • Conduit sidecars verify X-Gateway-S2S (src/s2s-verify.ts, port of conduit's src/proxy/s2s.ts). The guard sits before extractCredentialsFromHeaders on purpose; tests/s2s.test.ts boots the real HTTP handler and asserts the transport mock is never touched on a rejected request. index.ts auto-starts only when it is the entry point.

  • With a new key, run avanan_test_connection first. It prints the scopes and whether /msp/* is reachable, which is the whole diagnosis in one call.

  • The guide's "URLs and URL Base" section says smartapi-production-1-us.avanan.net (no hyphen). That host does not resolve; it is a typo for smart-api-production-1-us.

  • No Avanan or Check Point secrets exist in cortex-secret as of 2026-09-09, and the cortex-secret CLI is read-only here (list|get|env|run), so keys can't be stored from a session.

  • Current spec: 22 July 2026 guide, https://sc1.checkpoint.com/documents/Avanan_MSP_API_Reference/CP_Avanan_MSP_API_Reference_Guide.pdf (adds euw2 UK and aps1 India regions and the msp/msppartners-extended create endpoint; the old create-partner endpoint was slated for deprecation June 2025).

Read the full file on GitHub · 63 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. 1mo ago First seen · 63 lines · 1,185 tokens per session scan A ac8ca893c32b

Subscribe to this mod's changes

avanan-legacy-mcp CLAUDE.md is an instructions file published in the GitHub repository WYRE-AI/avanan-legacy-mcp (0 stars, last pushed 11d ago), licensed Apache-2.0. It adds 1,185 tokens to every session, about $0.0047 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 2026-09-10.

Related

avanan-legacy-mcp CLAUDE.md compared with instructions from other repositories

avanan-legacy-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
avanan-legacy-mcp CLAUDE.mdWYRE-AI/avanan-legacy-mcpInstructions file011d agoApache-2.0A1,185Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode