GatedBook a call
── MCP security, end to end

Your internal knowledge, accessible to AIwithout the leaks.

Agents ship fast. Security reviews don’t. Gated audits the MCP servers, tools, and integrations your agents reach into, so the data they surface is the data you meant to expose.

~/probe scan mcp.internal.acme
session
$ probe scan mcp.internal.acme --auth bearer
→ Authorization verified · acme-corp.com
→ Enumerated 34 tools, 12 resources, 6 prompts
→ Running 147 checks...
✕ HIGH tool query_customer_notes returns PII without caller verification
✕ HIGH indirect prompt injection via resources/tickets://*
⚠ MED no rate limit on search_wiki (500 rps observed)
⚠ MED tool description leaks internal schema naming
Report → probe.sh/r/8af3-2201 · 4 more findings

Probe is our scanner for MCP servers and agent-facing APIs. It behaves like a polite attacker: enumerates tools, probes auth boundaries, and checks the things developers forget — unlogged admin paths, mislabeled resources, a tool that returns more than its docstring suggests.

When the findings need more than a patch, our consulting team steps in: threat models, architecture fixes, and an authorization layer you can actually reason about.

10k+
Tools probed
11
Avg findings
< 2 min
Time to first
── The scale of the new surface
97M+
MCP SDK downloads
npm · registry weekly rollup
80%+
F500 deploying agents
Gartner, 2026 Q1
34
Avg tools per server
Gated telemetry · scanned fleet
11%
Teams with a threat model
Gated pre-engagement survey
The problem

Agents are cheap to build. The blast radius isn’t.

Three patterns we see in every pre-engagement audit. None of them are exotic. All of them ship to production.

01pattern

Scatter

Tools, resources, and prompts ship in five different repos with five different owners. No one can answer what the agent is allowed to see, because no one has the whole picture.

02pattern

Silence

MCP servers rarely emit audit logs anyone reviews. A misbehaving tool returns PII to a third-party model provider and the first signal is a support ticket, weeks later.

03pattern

Shadow

A developer spins up a local MCP against prod data for a demo. It works. It stays. Six months later it's behind a customer-facing chat and no one remembers it exists.

Consulting · How it works

Four steps. No surprise invoices.

Every engagement is fixed-scope with a written deliverable. If we can't tell you up front what you're getting, we haven't done the work to earn the engagement.

  1. 0130 min · free

    Readiness Call

    Thirty minutes, free. We look at your MCP surface, ask where the agents go, and tell you honestly whether an engagement makes sense.

  2. 02week 1

    Scope + Threat Model

    We inventory every tool, resource, and integration. We write down the adversaries worth worrying about, and the ones that aren't.

  3. 03weeks 1–4

    Audit + Fix

    Manual review backed by Probe. Every finding comes with a reproduction, a severity, and a concrete remediation. For Sprints, we ship the fix with you.

  4. 04week 4+

    Harden + Hand-off

    Authorization invariants, logging, CI checks, and a living threat model your team can extend. We leave behind a system, not a PDF.

Why Gated

Security is the first question, not the last.

We only scan what you own

Every Probe scan begins with a written authorization scope. We verify domain ownership and require a scoped, revocable token. No drive-by scans, ever.

We treat prompts as untrusted input

If your agent ingests a ticket, a doc, or a webhook body, we test it as an injection vector. The threat model we ship assumes the model is a confused deputy — because it is.

We write defense, not dashboards

Our deliverable is an authorization layer, a set of invariants, and tests that enforce them. You leave with something your engineers can maintain after we're gone.

We're skeptical on purpose

We won't tell you your agent is safe because it passed a scan. Scans find classes of problems. Threat models find the rest. We do both.

Consulting · Engagements

Three ways in. One standard of work.

Start with a Readiness Call. Most teams don't know whether they need an Audit or a Sprint until we've looked at the surface together.

Readiness Call
Free
30 minutes

A working call, not a sales call. We review your MCP surface, flag the top risks, and tell you whether you need an engagement at all.

  • Live screen-share review
  • Written summary within 24h
  • No deck, no SDR, no chase
── Most common
Audit
$5,000
fixed-fee · ~2 weeks

Structured review of one MCP surface. Threat model, manual testing backed by Probe, a written report, and a 45-minute fix-planning session.

  • Covers one server or integration
  • Ranked findings with reproductions
  • Report is yours to share internally
Sprint
from $20,000
embedded · 2–6 weeks

We ship the fix with you. Authorization redesign, logging, CI checks, and whatever else the audit turned up. One senior engineer, full-time, zero handoff.

  • Scoped and priced after Audit
  • Shared Slack + daily pairing
  • Fixed-fee, not T&M
FAQ

Straight answers. No fine print.

Missing a question? Ask it on the Readiness Call — we'd rather answer it on video than edit this list.

Yes. We have a mutual NDA on file you can counter-sign in one minute, or we'll use yours. Nothing from the call leaves the call.
Yes, and we recommend it. Probe only scans targets you've authorized in writing, and staging gives us more liberty to stress tool-level rate limits.
One Gated engineer, full-time, in your Slack and your repo. We pair, we ship PRs, we run the threat model as a living doc. No decks, no status meetings that aren't working sessions.
Often — this is the best time. Designing the authorization layer before an agent is in production is about ten times cheaper than retrofitting it later.
Pentests find broken authentication and SQLi. We find broken authorization and prompt injection. We care specifically about the failure modes that MCP and agent tooling introduce — which most pentest firms still don't have a playbook for.
A small team of security engineers who spent the last decade shipping authorization systems at places that care about getting it right. We started Gated because the MCP wave was going to need the exact work we already know how to do.
── Get started

Find out what your agent can actually see. In under five minutes.