What Flows just did
Based on your request to build Threat-Model Your MCP Server, Flows created 4 implementation stages and 12 checks.
You asked for: Produce and act on a threat model for my MCP server: asset inventory, entry-point and trust-boundary analysis, ranked threats, and implemented, tested mitigations.. Flows generated 4 stages because the application requires An asset inventory: what the server can access, expose, or affect; Entry points and trust boundaries mapped (who calls, with what authority, over what transport); Threats enumerated per boundary using a structured method (STRIDE or equivalent). Each stage tells your AI builder what to do, tests whether it actually worked, and gives a repair instruction when it fails. These checks are designed to catch: Shipping an MCP server with no analysis of what it exposes; Trusting the calling agent implicitly despite injection risk upstream; Threats listed but never mitigated or tested.
Example failure
The form reported success, but no database record was created.
What Flows does
Flows detects the failure, generates a repair instruction, reruns the test, and stores the passing evidence.
Stages — Plan → Build → Test → Fix → Prove → Ship
4 stages · 12 checks · progressive disclosure — open a stage for details
Copy to external builder
Copies a prompt for Claude/Cursor/etc. Records prompt_copied only — not execution, commits, or checks.
Execute through Oort
Requires Sign in with Oort + a provider connection (BYOK). Keys stay on Oort. A model name in the dropdown is not the same as a live connection.
Next
Check off: Read/write/host assets enumerated
Add a proof note on each check — a checkbox alone is weak proof.
Probes & advanced tools are under “More verification tools”. Experience level: Settings.
Project (saved with proof)
Project binding: Unbound — complete project binding before trusting this run · missing repositoryUrl, repositoryStartCommit, environment, stack
More verification tools (probes, timeline, adapters)Show
App persistence (create → read → assert token)
Body template: {"probe":"{{token}}","title":"flows-probe-{{token}}"}. Needs CORS-readable public create/list endpoints (or inconclusive). Badge only when create→read→refresh finds the token (detects false success).
Two-account authorization (User B cannot see/change User A)
Authorization evidence source: Cross-account ownership test (trust level 5/6). These are not equivalent. Unauthenticated probe alone is weaker (source: unauthenticated API probe). Tokens stay in this browser session only — not uploaded to Flows servers.
Generated edge-case tests (review / approve)
- api_probe Create then refresh still shows the record
- api_probe Edit then refresh keeps the edit
- api_probe Delete then refresh removes the record
- api_probe Nonexistent record ID fails cleanly
- cross_account_probe Cross-user record identifier is rejected
Generated from this route’s signals — you approve; you do not invent security tests.
Content probe (GET body contains text)
In-product content probe reads response text when CORS allows — not full DOM/click automation. Playwright script is optional and external.
Proof strength
thin · 0/100
Heuristic from notes + probes + gates — not a production certification.
Verification adapters
- ● Deploy URL probe · idle
- ● API path probe · idle
- ● Authz probe (unauth → 401/403) · idle
- ● Browser persistence · idle
- ● App persistence (create→read) · idle
- ● Content / body text probe · idle
- ○ In-product Playwright DOM · not embedded (download external script)
Filled circles = available here. Empty = not shipped. Probes are not a production audit. Adapter docs
Step 1 of 4
Not startedInventory assets and entry points
Threat modeling starts with what is worth protecting and how it is reached.
Flows keeps plan, checks, failures, and next steps connected
Your AI tool writes or changes the code
Repository grounds the plan only after inspect
Checks always carry a validation tier
How this plan was created
Plan from project details
Flows creates steps using the goal, requirements, stack, platform, and details you provide.
- Project description
- Selected template / route
- User-entered stack
- Constraints and notes
- Threat-Model Your MCP Server
No repository inspection implied. Connect and inspect a codebase to ground steps in real files.
Codebase access
Checking GitHub…
Or paste a repository URL manually
Use these instructions in Claude, ChatGPT, Cursor, Emergent, or another builder.
Document the server's assets and entry points. ASSETS: everything the server can read (files, databases, APIs, secrets), write/mutate (filesystem, records, external calls), and the server process/host itself. ENTRY POINTS: each exposed tool (with its capability), the transport (stdio/local vs networked - networked massively expands the surface), the initialization/discovery interface, and any configuration inputs. For each entry point note the authority it wields (what it can touch) and who can reach it. Explicitly record the trust reality: the calling agent may be acting on injected instructions from untrusted content, so the server cannot assume its caller is benign. Deliver the asset+entry-point inventory.
Project context
Copies the project goal, technical details, current step, previous progress, and checks so your AI tool understands what it is working on.
Expected after this step
An inventory of assets and entry points with authority and reach.
Should not happen
- ✕Shipping an MCP server with no analysis of what it exposes
- ✕Trusting the calling agent implicitly despite injection risk upstream
- ✕Threats listed but never mitigated or tested
- ✕No record of accepted residual risk, so gaps are forgotten
Verify gate — prove this step works before continuing
Do not move on until every check is true. Add proof notes — a checked box alone is weak proof. Checks are manual by default; deploy/API probes live under “More verification tools” and do not auto-check boxes.
Do not continue if…
- !Shipping an MCP server with no analysis of what it exposes
- !Trusting the calling agent implicitly despite injection risk upstream
- !Threats listed but never mitigated or tested
- !No record of accepted residual risk, so gaps are forgotten
Repair path — if this step fails
Use the Repair Prompt when a verify gate fails. Loop: Detected → Diagnosed → Repair issued → Changed → Retested → Resolved
Show repair prompt textShow
The inventory assumes only a trusted local agent calls it. Even a local agent can be injection-driven - and if the transport is or could become networked, the surface is far larger; model the realistic worst case, not the demo setup.
Your notes for this step
Definition of Done
Final route-level requirements. Manual checks — separate from per-step verify gates. Completing step gates does not auto-check these. Route completion is not a production-ready claim.