Audit
Two-week diagnostic. We map your data, your agent surface, and where MCP earns its keep.
From $8k →We design, build, and deploy MCP servers on your infrastructure — so Claude, Gemini, and your in-house agents can reach BigQuery, your DSP, and your CDP.
No pitch deck. No follow-up drip. We tell you if MCP isn't the answer.
All engagements are fixed-fee and time-boxed. We scope, you approve, we ship.
Two-week diagnostic. We map your data, your agent surface, and where MCP earns its keep.
From $8k →Production MCP servers deployed on your infrastructure. Auth, logging, evals, and CI from day one.
From $35k →Fractional senior MCP engineer for new connectors, agent evolution, and a Slack channel.
$12k / mo →Hands-on workshops for your engineering team. We leave with the bus factor at zero.
Custom →Auth, observability, evals, and CI are engineered in from day one. The interesting part is what you wire it to.
No black boxes. Typed inputs, scoped auth, and a repo your engineers can grep.
~ uvx --from [email protected] serve
→ registered tools: top_creatives, spend_breakdown
→ auth: oidc:google (scopes: bq:read, ads:read)
→ ready · listening on stdio
claude top creatives last 7d for acme
→ tool: top_creatives(account="acme") 218ms
→ 10 rows · sorted by roas desc
Every tool call carries the human identity through the MCP gateway. Audit logs are real. Permissions are real.
| Who | Tool | Scopes | |
|---|---|---|---|
| marek@acme | top_creatives | bq:readads:read | ✓ 218ms |
| jenna@acme | audience_overlap | bq:read | ✓ 92ms |
| j.doe@acme | spend_breakdown | bq:read | denied |
| ops@acme | pacing_check | ads:read | ✓ 410ms |
Four scenarios we see most often. Whichever shape your team is in, we have usually shipped this one before.
We design the architecture, ship the first two connectors, and leave your team with a roadmap they can run.
We wire your warehouse, CDP, and ad platforms into the agents your team already uses.
We replace glue with typed, owned MCP connectors, often paying for itself in vendor savings.
We build the gateway pattern: one MCP front door, central observability, and team handoff.
Most teams are still drawing that bridge on whiteboards. We build the production ones with the boring, important things engineered in: per-user auth, eval harnesses, structured logs, and CI.
We host a single MCP gateway per environment. Every connector is just a server behind it.
Boring on purpose. Typed inputs, scoped auth per user, structured logs, and an eval harness in the repo.
from mcp.server import Server
from .auth import scoped_bq_client
# A read-only window into the campaigns warehouse.
server = Server("campaigns", version="1.4.0")
@server.tool()
async def top_creatives(account_id: str, window: str = "7d"):
"""Return the top 10 creatives by ROAS over a window."""
async with scoped_bq_client() as bq:
rows = await bq.run(QUERY_TOP_CREATIVES, account_id, window)
return render(rows)
import { Server } from "@modelcontextprotocol/sdk";
import { scopedBQ } from "./auth";
const server = new Server({ name: "campaigns", version: "1.4.0" });
server.tool("top_creatives", {
description: "Top 10 creatives by ROAS",
input: z.object({ accountId: z.string(), window: z.string() }),
handler: async ({ accountId, window = "7d" }) => {
const bq = await scopedBQ();
const rows = await bq.run(Q_TOP, accountId, window);
return { content: [{ type: "text", text: render(rows) }] };
}
});
mcpServers:
campaigns:
command: "uvx"
args: ["--from", "[email protected]", "serve"]
env:
MCP_GATEWAY_URL: "https://mcp.acme.corp"
MCP_AUTH: "oidc:google"
scopes: ["bq:read", "ads:read"]
audit: true
evals: "campaigns/evals.yaml"
Don't see yours? Most MCP connectors are a day or two of focused work.
Internal dev tools, ad-ops, and analytics reachable from one agent surface.
Marketers query segments in plain English while engineering keeps moving.
Optimization agents that read spend from the source instead of guessing.
We host a tiny demo MCP at playground.mcpbuilders.dev with three read-only tools over open MarTech datasets.
$ claude mcp add playground https://playground.mcpbuilders.dev
→ connected · 3 tools registered
claude show me top campaigns from the demo dataset
→ tool: campaigns.top_creatives 218ms
→ tool: campaigns.spend_breakdown 92ms
Top 3 creatives by ROAS over the last 7 days:
1. video_demo_v2 — ROAS 4.8, $12k spend
2. carousel_holiday — ROAS 3.9, $8k spend
3. static_v7 — ROAS 3.2, $14k spend
Army veteran. Ten years shipping infra and data systems for MarTech and AdTech. Spent the last year putting production MCP servers in front of agents that actually have to earn their compute.
When teams hire mcpbuilders, you are not getting handed off to a junior. You work directly with me, end to end.
Thirty-minute call. We map your stack, name the first connector to ship, and give you a fixed quote by Friday. If MCP isn't the answer, we tell you.