Make Me An MCP
[ MAKE ME AN MCP ]WAITLIST OPENby Think North

Your APIs already work. Now make agents able to use them.

Make Me An MCP turns the APIs you already have into an agent-ready MCP — without building a gateway by hand. Register a platform, bundle endpoints into groups, set tiers, rate limits and pricing, then let it read each endpoint’s output and auto-draft the “yellow pages” an AI reads to decide which API to call and why. Ship it internal, enterprise, or public — behind keys.

// register · bundle · price · publish — the manifest writes itself
GET /mcp/m/acme-payments.json · what the agent reads
# the auto-generated agent "yellow pages" { "name": "Acme Payments", "visibility": "enterprise", "auth": { "type": "api_key", "scheme": "Bearer" }, "groups": [{ "name": "Refunds", "when_to_use": "reverse or partially reverse a charge", "endpoints": [{ "method": "POST", "path": "/v1/refunds", "output_signature": { "id": "string", "status": "enum[pending,done]", "amount": "int", "currency": "string" } }] }], "tiers": [{ "name": "Pro", "included_volume": 5000, "per_use_fee": "0.002", "period": "month" }] } › agent picks the right call, with the shape it gets back
[ 001 ]
The gap

Agents can’t use an API they don’t understand.

{ }

MCPs are hand-built

Wrapping each API as an agent tool — schemas, auth, descriptions — is fiddly, repetitive work that goes stale the moment the API changes.

?

Agents guess blindly

Without a clear description of what each endpoint returns, an agent can’t reliably decide which one to call — or what to do with the response.

$

No control or metering

Opening APIs to agents means tiers, rate limits, keys and per-use billing. Building that gateway is its own project.

[ 002 ]
How it works

Four steps from APIs to a live MCP.

Point it at the APIs you already run. It handles the agent-facing surface — discovery, pricing, access, and the manifest agents read.

1

Register

Add a platform and its endpoints — or import them. Group them into bundles that map to real capabilities.

2

Price & gate

Set tiers by audience, with rate limits, a per-use or subscription fee, free included volume, and an upper cap per period.

3

Read signatures

It reads each endpoint’s output JSON/XML signature, so the manifest can tell agents exactly what comes back.

4

Publish

It drafts the agent “yellow pages.” Edit it, publish, hand out keys — internal, enterprise, or public.

[ 003 ]
What you get

An MCP control plane for your APIs.

bundling

API groups

Bundle endpoints into capability groups agents reason about — Refunds, Search, Provisioning — instead of a flat list of routes.

monetisation

Tiers & pricing

Per-use or subscription fees, free included volume, and a hard cap per period — set per audience tier.

discovery

Output-signature reading

It reads the shape of each endpoint’s response so the manifest describes exactly what an agent gets back.

agent-facing

Editable AI “yellow pages”

An auto-drafted manifest you can edit — the description agents read to choose which API to invoke and why.

control

Access scopes & keys

Internal, enterprise, or public. Every consumer connects with a key scoped to a tier, with rate limits enforced.

roadmap

Usage & billing SOON

Metered usage per key and endpoint, rolled up to invoices — so per-use and subscription pricing just works.

0 servers
to build by hand
1 manifest
agents read to decide
3 scopes
internal · enterprise · public
keys
scoped, rate-limited, metered
[ 004 ]
Who it’s for

Built for teams whose APIs should be doing more.

A good fit

  • Platforms that want agents and partners building on their APIs
  • Teams exposing internal tools to their own AI agents
  • API products that need tiers, keys and per-use billing
  • Anyone who’d rather not hand-write and maintain an MCP server

What it replaces

  • Hand-rolled MCP servers that drift from the real API
  • Tool descriptions copy-pasted into every agent
  • A separate gateway for keys, rate limits and metering
  • Docs that humans read but agents can’t act on
[ 005 ]
Questions

The short version.

What is an MCP?

An MCP (Model Context Protocol server) is a standard way to expose tools and APIs to AI agents so they can discover and call them. Make Me An MCP turns your existing APIs into one — you don’t build the server by hand.

Do I have to rewrite my APIs?

No. Register the APIs you already have, bundle them into groups, and it reads each endpoint’s output signature and generates the agent-facing manifest for you.

How do I control who uses it?

Every consumer connects with a key scoped to a tier. You decide whether a platform is internal-only, limited to named enterprise accounts, or public — and set rate limits and pricing per tier.

How do agents decide which API to call?

They read the manifest — the auto-drafted, editable “yellow pages” that describes each group and endpoint, when to use it, and the shape of what it returns.

[ 006 ]

Get early access to Make Me An MCP.

We’re onboarding platforms gradually. Tell us about your APIs and we’ll reach out.

No spam. We email you when your slot opens.