Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/forayconsulting/make_mcp/claude-mdgit clone --depth 1 https://github.com/forayconsulting/make_mcpWhat 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 | $0.01102 | $0.01102 |
| Opus 5 | $0.00551 | $0.00551 |
| Sonnet 5 | $0.00220 | $0.00220 |
| Haiku 4.5 | $0.00110 | $0.00110 |
Grade A, and why
make_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 — 106 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.
Project Overview
This is a fork of the official Make.com MCP (Model Context Protocol) server. It exposes Make.com on-demand scenarios as callable tools for AI assistants. The goal of this fork is to extend capabilities beyond running scenarios to include full scenario lifecycle management (create, edit, delete).
Commands
npm install # Install dependencies (also runs build via prepare script)
npm run build # Compile TypeScript to build/
npm run watch # Watch mode for development
npm test # Run all tests
npm run inspector # Launch MCP Inspector for debugging
Run a single test:
npx jest test/server.spec.ts -t "Should get list of scenarios"
Architecture
Core Flow
index.ts (MCP Server)
↓
make.ts (Make API Client)
↓
Make.com REST API (https://{zone}/api/v2/...)
Source Files
-
src/index.ts- MCP server entry point. Registers two handlers:ListToolsRequestSchema- Returns static management tools + dynamicrun_scenario_{id}toolsCallToolRequestSchema- Dispatches to appropriate scenario method based on tool name
-
src/make.ts- Make API client withScenariosclass for API calls:list(teamId)- Get all scenarios for a teamlistOrganization(organizationId)- Get all scenarios for an organizationinterface(scenarioId)- Get input/output schema for a scenariorun(scenarioId, body)- Execute scenario in responsive modeget(scenarioId)- Get full scenario detailscreate(request)- Create a new scenarioupdate(scenarioId, request)- Update scenario metadata/blueprintdelete(scenarioId)- Delete a scenario (with confirmation)clone(scenarioId, request)- Clone an existing scenarioactivate(scenarioId)- Activate scenario via/startendpointdeactivate(scenarioId)- Deactivate scenario via/stopendpointgetBlueprint(scenarioId, options)- Get scenario blueprintsetInterface(scenarioId, request)- Set scenario input interfacegetIncompleteExecutions(scenarioId)- Get DLQ entries
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 · 106 lines · 1,102 tokens per session scan A 4ac0db7cdb46
make_mcp CLAUDE.md is an instructions file published in the GitHub repository forayconsulting/make_mcp (0 stars, last pushed 7mo ago), licensed MIT. It adds 1,102 tokens to every session, about $0.0055 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 2026-09-01.
Other instructions, from other repositories
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).
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.