Affiliate Networks MCP server
online · 93% uptimeai.agenticaffiliate/affiliate-networks-mcp·v0.19.0·7 starsAffiliate network reporting in your AI client. Bring your own keys. Most adapters experimental.
7 stars85 downloads/wk
Reviews
Write oneNobody has reviewed Affiliate Networks MCP yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Affiliate Networks MCP tools
Tool list not cached yet. `describe` through the gateway fetches it live.
Public scan report
scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it
- Code scan926 source files scanned25/25
- Live reliabilityremote reachable in 3603ms (auth required)17/20
- –Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
- Auth qualityOAuth resource metadata advertised on 40115/15
- Maintenancelast push 44 days ago12/15
- Maintainer identitynamespace and repository owner differ; GitHub account older than a year; website matches verified namespace7/10
How Affiliate Networks MCP compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 89/100
- higher than 80% of 48,255 servers
- Uptime
- 93%
- of our recent checks; the typical remote server answers 100%
- Response time
- 211 ms
- faster than 62% of 30,031 servers
- GitHub stars
- 7
- more than 86% of 28,688 servers
- Downloads a week
- 85
- more than 59% of 12,191 servers with a package
Install Affiliate Networks MCP in Claude Code, Cursor or VS Code
claude mcp add --transport http affiliate-networks-mcp https://mcp.agenticaffiliate.ai/mcp
What the publisher says
From the Affiliate Networks MCP repository's README, as published. We do not edit it. Read it on GitHub
affiliate-mcp
Integrate your affiliate networks with Claude or Codex.
Network operators: most adapters are community-built and experimental. Adoption gives your team ownership and a verification path; promotion to partial or production still requires current evidence and maintainer review. Find your network's issue under the adopt-this-network label.
Affiliate networks have two sides — and neither has a first-class AI workspace integration.
Publishers earn commissions from the programmes they join. Brands (and the agencies who manage them) run those programmes and pay the commissions out. I wanted to chat to my own affiliate data in the AI workspace I already use; none of the networks had shipped an integration for either side, so I built a broad beta set that covers both publisher and advertiser-side work.
If you're a publisher, you can ask:
"What did I earn across all networks last month?"
"Which programmes have transactions still pending after 90 days?"
"Compare my earnings month on month."
If you're on the brand side — running a programme, or an agency managing several — you can ask:
"How is Acme's programme doing this quarter?"
"Show me revenue across all my clients this week."
"Any anomalies in the affiliate data?"
Your AI workspace figures out which networks to call, fetches the data live from their APIs, and gives you the answer. You can use Claude or Codex to turn it into a sheet, an artifact, an email to your boss, whatever you want.
Free and open source. MIT licensed. Bring your own keys. For the product philosophy, read the AI-native affiliate data manifesto.
Who this is for
This tool serves two audiences. Pick the one that fits — or both, if you wear both hats.
You're a publisher. You earn commissions from affiliate programmes, your dashboards can't keep up with how fast you can think, and you want one conversation that spans every network you're on.
You're on the brand side. You run an affiliate programme — or you're an agency managing several brands' programmes. You want one question that fans out across networks and brands, and surfaces what the dashboards bury: publishers trending down, reversal spikes, dead links, programmes drifting toward zero.
Either way, you do not need to know what an API is or write code. The non-technical Claude Desktop track needs:
- Your existing logins to the affiliate networks you already work with.
- Claude Desktop installed.
The technical track uses a terminal, Node.js 20 or newer, and Claude Desktop, Claude Code, Codex, or another compatible local stdio MCP client; check the support states below before relying on an untested client journey.
And if you work for an affiliate network, this is also for you. The bundled adapters are placeholders until each network adopts its own. See CONTRIBUTING.md under "Adopting your network".
Why bother?
One question, every network and every brand. "Show me earnings by programme" hits your configured publisher networks in parallel. On the brand side, "show me revenue across all my clients this week" fans out across every brand and network pair you've registered.
Plain English, not filters. No more clicking through date pickers and saved views. "Last quarter, status pending, sorted by amount" is the whole prompt.
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Affiliate Networks MCP: common questions
- Is Affiliate Networks MCP server safe?
- Yes, by our scan: it is graded A (89/100). Read the Affiliate Networks MCP safety report
- How do I install Affiliate Networks MCP?
- It runs remotely at mcp.agenticaffiliate.ai. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does Affiliate Networks MCP need an API key?
- No key to paste: it signs you in with OAuth when your client connects.
- Is Affiliate Networks MCP maintained?
- The last commit was 85 days ago (2026-08-11). The latest release is v0.19.0.
- Is Affiliate Networks MCP up?
- 93% of our last 28 checks got an answer. We check remote servers about four times a day.
- How does Affiliate Networks MCP compare with other MCP servers?
- safety score 89/100 (higher than 80% of 48,255 servers); uptime 93% (of our recent checks; the typical remote server answers 100%); response time 211 ms (faster than 62% of 30,031 servers). Full comparison.