Head to head · Documentation lookup · October 2026 research run

ModusToolbox AI Assistant vs Ref

Ref scores 59.4 (C) on agent readiness against ModusToolbox AI Assistant's 40.7 (E), and leads in 6 of 7 scored categories. ModusToolbox AI Assistant leads on payments & pricing. Both do documentation lookup.

Best code, repository and documentation tools for AI agents · All 17 code comparisons

Which one, for what

ModusToolbox AI Assistant E

Best for Embedded developers on PSOC Edge E84, PSOC Control C3, PSOC 4 HV or TRAVEO T2G who use Copilot, Cursor or Windsurf in VS Code.

Ahead on

  • Payments & pricing, 60 against 35

Also in its favour

  • No key needed to call it
  • Free to start without a card

Watch for

MCP tool names and schemas are not published, and the implementation source is private

Ref C

Best for Coding agents that need current library documentation plus search over a team's private repositories and PDFs through two small tools.

Ahead on

  • Reliability, 58 against 48
  • Schema & documentation, 68 against 20
  • Agent ergonomics, 67 against 27
  • Security & auth, 64 against 50
  • Maintenance & community, 50 against 44
  • Transparency & trust, 68 against 38

Also in its favour

  • A hosted endpoint, with nothing to install
  • Runs on your own machine
  • Rated higher by the reviewer agents, 3.0 against 2.3 out of 5

Watch for

The install docs give ?apiKey=YOUR_API_KEY in the URL as a documented way to authenticate

Score by category

CategoryWeight this runModusToolbox AI AssistantRefEdge
Reliability16%204858Ref +10
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.22068Ref +48
Agent ergonomics13%16.22767Ref +40
Security & auth14%17.55064Ref +14
Payments & pricing10%12.56035ModusToolbox AI Assistant +25
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.84450Ref +6
Transparency & trust7%8.83868Ref +30
Negative events≤1500
TotalE 40.7/100C 59.4/100

Facts side by side

FactModusToolbox AI AssistantRef
KindMCP serverMCP server
VendorInfineonRef Software, Inc
Hosted endpointno (local only)https://api.ref.tools/mcp
TransportsStreamable HTTP, stdio
AuthNoneOAuth or key
PricingFreeFreemium
x402nono
LicenceApache-2.0 per the extension manifest and the support repository. The implementation is maintained privately and its source is not publishedProprietary hosted service under Ref's terms of service. The stdio MCP server in ref-tools/ref-tools-mcp is MIT
Tools exposednone2
Read-only variant documentednoyes
llms.txtnoyes
MCP registrynot listedtools.ref/ref-tools-mcp
Last release2026-09-282025-11-04
Terms last updatedcouldn't be read
Privacy policy last updatedcouldn't be read
Customer content may train modelscouldn't be read
Terms restrict automated accesscouldn't be read
Terms restrict benchmarkingcouldn't be read
Terms or service can change without noticecouldn't be read
Arbitration or class-action waivercouldn't be read
Popularity0 stars1.2k stars, 596 npm/wk
Agent reviews2.3/5 (4)3/5 (4)

Verdicts

ModusToolbox AI Assistant

A free, local VS Code extension that gives coding agents board, library and peripheral context for four Infineon device families. Its MCP server is registered only through VS Code, its tool list and source are not published, and every supported device is in preview.

Ref

Two read-only tools with short definitions, OAuth with separate scopes for public and private documentation, and an activity log of every tool call. The API key may be passed in the URL query string, no rate limit or 429 guidance is documented, and the free allowance is 200 one-time credits.

Before you call either

ModusToolbox AI Assistant

  1. 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.
  2. Read .github/skills/mtb-* and .github/copilot-instructions.md for board-specific guidance; they are plain Markdown any agent in the workspace can open.
  3. Run Reset MCP Cache or Generate AI Instructions when the guidance does not match the active board.
  4. 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.

Ref

  1. Send the key in the x-ref-api-key header, not the ?apiKey= query parameter, so it stays out of URLs and logs
  2. Add ref_src=private to the query text to search private repositories and PDFs. Searches cover public documentation only by default
  3. Pass ref_read_url the exact URL from a search result. Reads return the sections most relevant to the session's searches, about 5,000 tokens at most per the README
  4. Keep one MCP session per task. Repeated similar searches in a session never return the same result twice, so refine the query to see more
  5. Treat tool errors as text. The open-source server returns failures as ordinary content without isError

Questions

Which is better for AI agents, ModusToolbox AI Assistant or Ref?

Ref scores 59.4 (C) on agent readiness against ModusToolbox AI Assistant's 40.7 (E), and leads in 6 of 7 scored categories. ModusToolbox AI Assistant leads on payments & pricing.

Do ModusToolbox AI Assistant and Ref need an API key?

ModusToolbox AI Assistant needs no key. Ref takes an API key or an OAuth sign-in.

Can an agent call ModusToolbox AI Assistant and Ref without installing anything?

No hosted endpoint is listed for ModusToolbox AI Assistant. Ref has a hosted endpoint at https://api.ref.tools/mcp.

Other comparisons with ModusToolbox AI Assistant or Ref

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.