What is markifact-mcp CLAUDE.md?

Instructions for using the Markifact MCP server, a service that connects AI agents to marketing, advertising, analytics, e-commerce, and customer-management tools.

Running marketing operations such as launching campaigns, editing advertising creatives, finding negative keywords, diagnosing underperforming campaigns, and moving files or media through the server.

They explain how to discover available operations, inspect their inputs, distinguish read-only actions from changes, and handle account selection and approval safely.

markifact-mcp CLAUDE.md — Instructions file by markifact

Install

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.

agentmods

npx agentmods add instructions/markifact/markifact-mcp/claude-md

Clone the repo

git clone --depth 1 https://github.com/markifact/markifact-mcp

Per session 273 This file is loaded in full into every session.

When invoked 273 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.00273	$0.00273
Opus 5	$0.00137	$0.00137
Sonnet 5	$0.00055	$0.00055
Haiku 4.5	$0.00027	$0.00027

Measured 2d ago against content hash 83b63a10a415, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

markifact-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.

CLAUDE.md · 21 lines

What it actually says

Markifact agent context

You're running inside a session that has access to the Markifact MCP server at https://api.markifact.com/mcp.

When the user asks anything about marketing, ads, analytics, e-commerce, or CRM, prefer the @performance-marketer agent. It has built-in knowledge of:

The 8-tool MCP surface (find_operations, get_operation_inputs, run_operation, run_write_operation, list_connections, get_file_url, read_file, upload_media).
The discover → inspect → run pattern, dispatched by the requires_approval flag from find_operations.
The four-step write-operation safety protocol.
Connection (OAuth login) vs. account (ad account) distinction — connections auto-resolve, accounts always need *_select_accounts.

Available slash commands:

/markifact:launch-google-search (write)
/markifact:launch-pmax (write)
/markifact:launch-meta-campaign (write)
/markifact:edit-meta-creative (write)
/markifact:rotate-creative (write)
/markifact:negative-keyword-sweep (write)
/markifact:diagnose-underperformer (read-only)

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.

2d ago First seen · 21 lines · 273 tokens per session scan A 83b63a10a415

Subscribe to this mod's changes

markifact-mcp CLAUDE.md is an instructions file published in the GitHub repository markifact/markifact-mcp (48 stars, last pushed 14d ago), licensed MIT. It adds 273 tokens to every session, about $0.0014 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 2026-08-30.

Analytics and metrics Debugging E-commerce ads-mcp claude-code-plugin claude-cowork claude-plugin claude-skills google-ads

uk-legal-plugins CLAUDE.md

Instructions for uk-agents/uk-legal-plugins, covering claude.md, target ecosystems, documentation index, layout and validation — run before opening a pr.

uk-agents/uk-legal-plugins · 2,219 tokens

magi-workflow CLAUDE.md

Instructions for howar31/magi-workflow, covering what this is, slash commands, subagents, project state model and project document tiers.

howar31/magi-workflow · 626 tokens

gengeo-agent-registry AGENTS.md

Instructions for warwickwood-cell/gengeo-agent-registry: GenGEO provides machine-readable merchant verification infrastructure for AI agents.

warwickwood-cell/gengeo-agent-registry · 142 tokens

agents copilot-instructions.md

Copilot instructions for commerce-atoms/agents, covering github copilot — @commerce-atoms/agents (kit authoring) and constraints for autocomplete in this repo.

commerce-atoms/agents · 357 tokens

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.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 6,785 tokens