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.
curl -O https://raw.githubusercontent.com/WYRE-AI/avanan-legacy-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/WYRE-AI/avanan-legacy-mcpWrote 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.
[](https://agentmods.dev/instructions/wyre-ai/avanan-legacy-mcp/claude-md)<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.
<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>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 | $0.01185 | $0.01185 |
| Opus 5 | $0.00593 | $0.00593 |
| Sonnet 5 | $0.00237 | $0.00237 |
| Haiku 4.5 | $0.00119 | $0.00119 |
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 2d 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.
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.tspins the live-verified auth contract. Do not "correct" thex-av-dateformat back to the guide's.000Z; the API rejects it.- Rebuild
src/generated/tenant-card-html.tswithnpm run build:uiafter editingui/. - 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.jsonwithdescriptionlonger 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 withpython3 -c 'import json;print(len(json.load(open("server.json"))["description"]))'. -
The SmartAPI returns HTTP 500
{"message":"Internal Server Error"}on every path whenx-av-dateends inZ. This looked like a broken signature for a long time; it is the date. Sendnew 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"}= nox-av-*headers reached the authorizer;{"message":"Forbidden"}= signature wrong (usually the path was left out); aresponseEnvelopewith403 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 scopemt-prod-3:wyretechnology, i.e. a tenant key./v1.0/scopesand/v1.0/event/querywork with it; all/msp/*tools are blocked until an MSP-level key is generated from the MSP portal. -
List endpoints take
scrollId/MSPIdas a JSON body onGET. WHATWGfetchthrows on that, hence the smallnode:httpswrapper insrc/utils/transport.ts. -
The
/authresponse body is the raw JWT (Cognito access token), not JSON. It carriesexp(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/querycapsrecordsNumberat 10000. -
scopes(array) goes on/event/queryand/search/query;scope(single string) goes on/action/eventand/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'ssrc/proxy/s2s.ts). The guard sits beforeextractCredentialsFromHeaderson purpose;tests/s2s.test.tsboots the real HTTP handler and asserts the transport mock is never touched on a rejected request.index.tsauto-starts only when it is the entry point. -
With a new key, run
avanan_test_connectionfirst. 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 forsmart-api-production-1-us. -
No Avanan or Check Point secrets exist in cortex-secret as of 2026-09-09, and the
cortex-secretCLI 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
euw2UK andaps1India regions and themsp/msppartners-extendedcreate endpoint; the old create-partner endpoint was slated for deprecation June 2025).
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.
- 2d ago First seen · 63 lines · 1,185 tokens per session scan A ac8ca893c32b
avanan-legacy-mcp CLAUDE.md is an instructions file published in the GitHub repository WYRE-AI/avanan-legacy-mcp (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 1,185 tokens to every session, about $0.0059 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 2026-09-10.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).