impactdotcom-mcp: Instructions file for Claude Code

CLAUDE.md

impactdotcom-mcp CLAUDE.md is an instructions file for Claude Code from gblush/impactdotcom-mcp. It costs 1,192 tokens per session, scanned B, original, MIT.

Project instructions for a local MCP server that wraps Impact.com’s partner API. Impact.com is a platform for managing partner and affiliate marketing, including clicks, actions, and revenue.

In plain words
What is it for?
Use them when diagnosing tracking funnels, running the server, checking its TypeScript and lint rules, inspecting API behaviour, or checking for exposed secrets.
Why use it?
They document how to build, configure, inspect, test, and protect the server while investigating cases where clicks do not produce revenue.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is gblush/impactdotcom-mcp's own configuration. It tells Claude Code how to work on impactdotcom-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 impactdotcom-mcp configures →

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/gblush/impactdotcom-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/gblush/impactdotcom-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,192 This file is loaded in full into every session.
When invoked 1,192 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.01192 $0.01192
Opus 5.5 $0.00477 $0.00477
Sonnet 5.5 $0.00238 $0.00238
Haiku 4.5 $0.00119 $0.00119

Measured 2mo ago against content hash 88b7c43322dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

impactdotcom-mcp CLAUDE.md scanned grade B with 1 finding 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.

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

This repo is public. Real `IMPACT_ACCOUNT_SID` / `IMPACT_AUTH_TOKEN` live **only** in the gitignored `.env`. Never put real credentials or PII in any tracked file (`.env.example`, `.mcp.json`, docs use placeholders). Run
CLAUDE.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

A local stdio MCP server wrapping the Impact.com partner REST API. Built because Impact.com's hosted MCP can't be used from Claude Code (its OAuth server has no Dynamic Client Registration). Primary purpose: diagnose publisher tracking problems — specifically "clicks but no revenue" — by exposing the click → action → revenue funnel.

Commands

  • npm run build — compile TypeScript to dist/.
  • npm run dev — watch-mode run via tsx.
  • npm run inspect — build + open the MCP Inspector against the server (primary manual test loop).
  • npm run typecheck / npm run lint — must pass; lint enforces no stray console.log.
  • npm run check:secrets — run before every commit. Fails if any tracked file contains a real Account SID/Auth Token.

Architecture

  • src/index.ts — entry; loads .env, validates config, registers tools, connects stdio.
  • src/config.ts — env validation; computes basePath and Basic-auth header.
  • src/client.ts — the only module that talks HTTP (impactGet, impactGetAll, impactWrite, runAsyncJob). Add new endpoints here, not ad-hoc fetch in tools.
  • src/diagnostics.ts — encodes Impact's attribution rules + reversal codes; powers diagnose_tracking.
  • src/tools/* — one file per domain; each exports a register* function. tools/index.ts wires them up and gates writes.

Non-obvious rules (get these wrong and it breaks)

  • stdout is reserved for JSON-RPC. Never console.log. Log via src/logger.ts (log.info/warn/error → stderr, with secret redaction).
  • Persona prefix: all paths are under /{IMPACT_ACCOUNT_TYPE}/{AccountSID} (default Mediapartners). If every call 403s/404s, the account type is probably wrong (Mediapartners vs Advertisers).
  • JSON, not XML: the API defaults to XML; the client always sends Accept: application/json. Don't remove that header.
  • Tool inputs are YYYY-MM-DD, but date encoding differs by endpoint (verified live): the /Actions endpoint rejects bare dates — it needs full ISO‑8601 datetimes (2026-05-27T00:00:00Z), so the Actions tools convert via toStartOfDayIso/toEndOfDayIso. Reports take bare YYYY-MM-DD. The /Actions endpoint also has max 45-day range, ~3-year-back limit, default last 7 days, no Page/PageSize (paginate via @nextpageuri), and no OrderId filter — trace an order via find_action_by_order.
  • Report params differ per report (verified live): Performance by Brand = partner_performance_by_program (filters START_DATE/END_DATE); Advanced Action Listing = mp_action_listing_sku (filters Start Date/End Date, with spaces). Don't assume a uniform param name — call get_report_metadata first.
  • get_account hits the persona root (/Mediapartners/{SID}), not /Accounts — the latter is 403 for scoped Mediapartner tokens. Similarly the single /Clicks/{id} resource may be 403 for a scoped token even when ClickExport works.
  • Writes are gated: create_tracking_link and impact_api_request only register when IMPACT_ENABLE_WRITES=true. create_tracking_link/TrackingLinks path casing is the one write not yet exercised live.
  • Rate limits are real: the API has an hourly quota and exports (ClickExport, ReportExport) are expensive — bursting parallel exports exhausts it (retry-after can be hours). The client caps concurrency (IMPACT_MAX_CONCURRENCY, default 4) and fails fast on a 429 whose reset is >30s out (reset time included in the error) instead of hanging. Don't loop exports across many days without spacing.

Read the full file on GitHub · 48 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. 2mo ago First seen · 48 lines · 1,192 tokens per session scan B 88b7c43322dc

Subscribe to this mod's changes

impactdotcom-mcp CLAUDE.md is an instructions file published in the GitHub repository gblush/impactdotcom-mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 1,192 tokens to every session, about $0.0048 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

impactdotcom-mcp CLAUDE.md compared with instructions from other repositories

impactdotcom-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
impactdotcom-mcp CLAUDE.mdgblush/impactdotcom-mcpInstructions file04mo agoMITB1,192Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot