ModusToolbox AI Assistant

# Fix list: ModusToolbox AI Assistant

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/modustoolbox-ai-assistant, the October 2026 research run, assessed 21 October 2026. Grade E, 40.7 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on ModusToolbox AI Assistant: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Schema & documentation, 20 out of 100, up to 13 more on the total

Why it scored 20: The MCP server is registered through VS Code's `mcpServerDefinitionProviders` and its tool names, descriptions and input schemas are not published in the README, the manifest or the support repository. With the source private, none could be read (0 of 25, 0 of 20, 0 of 15). The extension writes Markdown instruction files and device skills into the workspace for the agent to read, which is agent-facing documentation, though not served on the web (6 of 10). The README has two worked setup flows and a troubleshooting section, with no error responses documented (4 of 15). A public changelog with dated 0.x versions (10 of 15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 15, versioning and a public changelog.

Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.

## 2. Agent ergonomics, 27 out of 100, up to 11.9 more on the total

Why it scored 27: The tool count is unknown. The changelog says code-example discovery gained keyword and category filters, category summaries and result limits to cut catalogue data in conversations, and skills are deployed per board, which counts as a partial subset (10 of 25). Those filters and limits are the only output controls documented (8 of 20). 0.6.0 added user-visible error reporting for asset loading, with no agent-facing error format documented (3 of 20). No idempotency or tool annotations could be read (0 of 20). Settings have defaults and the ModusToolbox path is auto-detected. No SDK, which fits an editor extension (6 of 15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.

Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.

## 3. Reliability, 48 out of 100, up to 10.4 more on the total

Why it scored 48: Read with the local-software lines, because the extension and its MCP server run on the developer's machine. Official package on the VS Code Marketplace with VS Code 1.85, ModusToolbox 3.7 and Python 3.9 stated as requirements (20). The implementation is private, so no CI or test suite can be seen (0 of 25). The public tracker has three issues, all opened on 21 October 2026 and each answered the same day by an Infineon contributor. The sample is one day old (20 of 25). Keep a Changelog format with 0.x versions, and the extension id change in 0.1.21 is recorded but not marked as breaking (8 of 15). Version 0.6.0 and declared Preview (0 of 15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 10, the surface agents use is generally available, not beta or preview.

Local packages, SDKs, frameworks and stdio MCP servers.

- 20, installs from an official package with supported runtimes stated.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 15, version 1.0 or later, or declared stable.

Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.

## 4. Security & auth, 50 out of 100, up to 8.8 more on the total

Why it scored 50: No credential at all. The server is local, takes no key and is registered by the editor (20 of 30, as for other keyless local servers whose only boundary is the developer's machine). Project planning confirms the board, template, project name and directory before creating a project. Build commands and tool launching have no documented read-only mode (5 of 20). The server returns local project data and Infineon's catalogue and skill content, mostly vendor-written. No injection guidance (8 of 15). An Output panel with log levels for the extension and the server is the only per-call visibility (5 of 15). Infineon publishes a valid security.txt to PSIRT@infineon.com (expires 11 September 2027), the repository's SECURITY.md points to its vulnerability notification process, and coordinated disclosure is linked. No bug bounty or certification was checked for this product (12 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.
- 0 to 15, audit logs or per-call visibility for the operator.
- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.

Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.

## 5. Transparency & trust, 38 out of 100, up to 5.4 more on the total

Made of editorial 29, provenance 47.

Why it scored 38: The manifest and the support repository state Apache-2.0, but the implementation is maintained privately and the repository cannot build the extension, so which code the licence covers is unclear (12 of 30). The README says the server runs locally and fetches Infineon's super-manifest from GitHub at startup, with other work offline. There is no product data statement, and Infineon's general privacy policy was not readable (8 of 30). The changelog records the extension id change, with no deprecation policy (3 of 20). No telemetry setting in the manifest and no telemetry statement either way. Network use is stated in one sentence (6 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).

The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.

Provenance checks not met in full (half of this category, computed from checked facts):

- Legal entity named: not found (0 of 20)
- Domain age: infineon.com, no registry record we could read (0 of 15)
- Status page: not found (0 of 10)

## 6. Payments & pricing, 60 out of 100, up to 5 more on the total

Why it scored 60: Free software that runs on the developer's machine, so the self-hosted rule applies, 20 + 20 + 20. No payment protocol (0). It needs a local ModusToolbox install. Whether that download needs an Infineon account was not established, and is in the open questions.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).

- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.
- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login.
- 20, a free tier or trial that doesn't need a card.
- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).

Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.

Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.

## 7. Maintenance & community, 44 out of 100, up to 4.9 more on the total

Why it scored 44: 0.6.0 is dated 28 September 2026 in the changelog and its Marketplace package 1 October 2026, within 30 days (30). Two dated releases in the last 90 days, 0.5.0 on 28 August and 0.6.0 (0 of 20). The three issues opened on 21 October 2026 were each answered within about nine hours, and pull requests are not accepted (12 of 25). Not in the official MCP registry under any Infineon name (0 of 15). No dependencies or CI visible for the private implementation (2 of 10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- unchecked: the body of Infineon's technology news item inftn202610-011 (sitemap date 20 October 2026). WebFetch returned only the site navigation, and plain fetches failed on the sandbox's TLS proxy.
- unchecked: the Marketplace version history and release dates, which the page draws by script; /_apis/ is disallowed by robots.txt and was not used. firstReleased is the 0.6.0 changelog date, 28 September 2026, three weeks before the lead's date. Whether 0.5.0 (28 August) or 0.1.21 (21 May) were public was not established.
- unchecked: the MCP server's tool names, input schemas and annotations, and its transport. The README names none and the source is private.
- unchecked: Infineon's imprint and privacy policy bodies, so no legal entity is recorded.
- unchecked: whether downloading ModusToolbox 3.7 needs an Infineon account.
- Whether the Apache-2.0 licence in the manifest covers the privately maintained implementation shipped in the package.
- Not the same job as LocalGhost or letme; graded the normal way.

## Weaknesses

- MCP tool names and schemas are not published, and the implementation source is private
- Preview at 0.6.0, and every supported device family is marked preview
- The MCP server registers through VS Code's API only, with no configuration documented for other clients
- Not on Open VSX and not in the official MCP registry

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Expect this only inside VS Code, with ModusToolbox 3.7 or later, Python 3.9 or later and the ModusToolbox for VS Code extension installed.
- Read `.github/skills/mtb-*` and `.github/copilot-instructions.md` for board-specific guidance; they are plain Markdown any agent in the workspace can open.
- Run Reset MCP Cache or Generate AI Instructions when the guidance does not match the active board.
- Check the board is PSOC Edge E84, PSOC Control C3, PSOC 4 HV or TRAVEO T2G before relying on it; PSOC 6 and PSOC 4 are not supported yet.

## What the review panel asked for

- Publish the MCP tool list
- Document errors the agent sees
- a published MCP tool list with versions
- breaking changes marked in the changelog
- publish the MCP tool list and annotations
- publish the MCP tool list
- document other MCP clients

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.