CuratedMCP
Back to the assessment
This is a sample report. The findings below are illustrative — a realistic but fictional 12-machine engagement — so you can see exactly what the deliverable looks like before commissioning one. No real customer data appears here.

MCP Exposure Assessment

Northwind Engineering (sample)

Prepared 12 August 2026 · 12 developer machines · Claude Code and Cursor

Executive summary

We inventoried every Model Context Protocol server configured across 12 developer machines and 2 AI clients. We found 7 distinct servers in 33 configured instances. 3 are high-risk and 4 appear in no governed catalog, meaning nobody has reviewed what they can do. 9 of 12 machines carry at least one high-risk server today.

12

machines in scope

7

distinct servers

3

high-risk

4

unreviewed

Prioritized remediation

Ordered by blast radius, then by how many machines are affected. P1 items involve credential reach or unreviewed execution — start there.

  1. P1postgres-prodon 5 machines

    Rotate the credential, then remove or review the server's source before re-approving.

    Holds a long-lived credential in its environment and has not been reviewed by anyone. Treat the credential as already exposed.

  2. P1aws-toolkiton 3 machines

    Remove, or restrict to a scoped credential and re-review.

    Can read credentials from the system keychain. An unreviewed server with keychain access can reach every secret on the machine, not just the one it needs.

  3. P2filesystemon 5 machines

    Confirm which root path it is scoped to, and narrow it if that path is the home directory.

    Has filesystem access. A reviewed server is still only as constrained as the directory it is given.

  4. P2puppeteeron 3 machines

    Review the source, then allowlist a pinned version or remove.

    Not present in any governed catalog — nobody has checked what it does.

  5. P2scratch-runneron 2 machines

    Remove, or pin to a reviewed version with a restricted root path.

    Unreviewed code with filesystem access. Scope is whatever the AI client asks it to read or write.

  6. P3githubon 12 machines

    Keep. Pin the version so it can't change under you.

    Reviewed and known-good. Version pinning stops a future release silently changing behaviour.

  7. P3slackon 3 machines

    Keep. Pin the version so it can't change under you.

    Reviewed and known-good. Version pinning stops a future release silently changing behaviour.

Full inventory

Every distinct MCP server found, with the risk flags that applied and how widely it is deployed across the fleet.

ServerRiskMachinesFlags
postgres-prodClaude Code, CursorHIGH5Credential in environment · Network egress · Not in any governed catalog
aws-toolkitClaude CodeHIGH3Keychain access · Network egress · Not in any governed catalog
scratch-runnerCursor, Claude CodeHIGH2Filesystem access · Not in any governed catalog
filesystemCursor, Claude CodeMEDIUM5Filesystem access
puppeteerCursor, Claude CodeMEDIUM3Network egress · Not in any governed catalog
githubClaude Code, CursorVERIFIED12Network egress
slackCursor, Claude CodeVERIFIED3Network egress

Starter allowlist

The reviewed servers we recommend keeping. Adopting this as your allowlist means anything not on it stops being installable without a decision.

{
  "allowed": [
    "github",
    "slack"
  ]
}

Methodology & data handling

  • Each machine ran the open-source CuratedMCP auditor once. It reads the MCP configuration of every installed AI client and classifies each server against a risk-classified catalog of reviewed servers.
  • What left the machine: server names and risk flags only. Never commands, arguments, environment variable values, or file paths.
  • Risk levels reflect declared capability, not observed behaviour — a server flagged for filesystem access can read files, which is not the same as proof that it did.
  • Findings are a point-in-time snapshot. A developer can add a new server in seconds, so treat this as a baseline rather than a permanent state.
Prepared by CuratedMCP · curatedmcp.com · The auditor used to produce this report is open source (MIT) and can be reviewed before it is run.

Want this for your own fleet?

One week, $2,500 flat, up to 10 machines. Your engineers run one command; you get the report above with your own findings.