Baldwin Pergolas

At a glance

Runs where

On their server. What you send to it goes to them.

What you need

Nothing: it answered without a login

Tools

9 tools

Its own safety labels

3 read-only, 6 labeled as changing things

Memory it takes

About 6,600 tokens of your AI's memory, just for its tool descriptions

Largest answer

About 15.9 KB in our test

Tools that look alike

6 pairs of tools with nearly the same description, so the AI may pick the wrong one

Speed

Average answer in our test: 137 ms

Tokens are an estimate: the characters in its tool names, descriptions and inputs, divided by 4. The exact number depends on your AI model. Safety labels are what the server says about itself. From our latest test, 11 Nov 2026.

Is Baldwin Pergolas MCP server safe?

• None of the hidden-instruction wordings we know were found in its 9 tool descriptions.
• 3 of its 9 tools are labeled read-only; the others may change or send things.
• Overall it scored 82/100 on 11 Nov 2026.

A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.

What this test does not check

• Its source code and packages.
• What a tool quietly does behind the scenes, such as writing a file or calling another service.
• Instructions hidden inside live tool answers. We only look for those in tool descriptions.
• Hidden instructions worded in a way our list doesn't know yet.
• Tools that could change something. Those are read, never run.

What QAmcp can and can't see · How to tell if an MCP server is safe · Hidden instructions · Prompt injection

Known security advisories

It lists no public code, so there is nothing to look up in GitHub Security Advisories or OSV.dev. QAmcp tests how a server behaves. It does not scan source code.

What it can do

9 tools, in the server's own words.

Test results

Safe mode: only tools labeled read-only were run. How the test works

• !
  Ready for the newest MCP version

  1 warning

  • !Uses an older MCP version (2025-06-18). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
  note
• !
  Every tool is described

  8 warnings

  • !search_pergola_knowledge: Inputs with no description: query, limit
  • !report_pergola_problem: Inputs with no description: problem_type, topic, description, claim_a, claim_b, source_a, source_b
  • !quote_classic_pergola and quote_curved_pergola have nearly the same description (89% of their words are shared; the only difference: "classic", "freestanding", "attached" vs "curved", "arc", "based"), so an AI may not know which to pick
  • !quote_classic_pergola and quote_modern_classic_pergola have nearly the same description (79% of their words are shared; the only difference: "freestanding", "attached", "colonnade" vs "modern", "four", "column"), so an AI may not know which
  • !quote_modern_classic_pergola and quote_curved_pergola have nearly the same description (79% of their words are shared; the only difference: "modern", "classic", "four" vs "curved", "arc", "based"), so an AI may not know which to pick
  • !quote_curved_pergola and quote_lattice_panel have nearly the same description (70% of their words are shared; the only difference: "curved", "fiberglass", "kit" vs "lattice", "panel", "post"), so an AI may not know which to pick
  • !quote_classic_pergola and quote_lattice_panel have nearly the same description (68% of their words are shared; the only difference: "classic", "fiberglass", "kit" vs "lattice", "panel", "post"), so an AI may not know which to pick
  • !quote_modern_classic_pergola and quote_lattice_panel have nearly the same description (61% of their words are shared; the only difference: "modern", "classic", "fiberglass" vs "lattice", "panel", "post"), so an AI may not know which to pick
  note
• !
  Bad inputs give a clean error

  2 warnings

  • !search_pergola_faq: Accepted wrong type for "query" without complaining
  • !search_pergola_knowledge: Accepted wrong type for "query" without complaining
  note
• !
  Follows MCP best practices (not scored yet)

  1 tip (not scored)

  • !3 tools answer with structured data but don't declare its shape (outputSchema): get_pergola_guidance, search_pergola_faq, search_pergola_knowledge. If those answers change shape, nothing can catch it; with a schema, every answer is checked.
  note
• ✓
  ConnectsConnected in 980 ms
  pass
• ✓
  Lists its toolsFound 9 tools
  pass
• ✓
  Tools are labeled safe or dangerousEvery tool has a safety label
  pass
• ✓
  No known hidden instructionsNone of the hidden-instruction wordings we know were found in tool descriptions. New wordings can get past this check.
  pass
• ✓
  Tools work with good inputs

  All good

  • ✓get_pergola_guidance: Worked (187 ms)
  • ✓search_pergola_faq: Worked (110 ms)
  • ✓search_pergola_knowledge: Worked (115 ms)
  • –quote_classic_pergola: Not run: labeled as changing data
  • –quote_modern_classic_pergola: Not run: labeled as changing data
  • –quote_curved_pergola: Not run: labeled as changing data
  • –quote_lattice_panel: Not run: labeled as changing data
  • –create_contact_link: Not run: labeled as changing data
  • and 1 more
  pass
• ✓
  Fast enough

  All good

  • ✓Connecting took 980 ms
  • ✓Listing tools took 188 ms
  • ✓Average tool answer: 137 ms
  • ✓get_pergola_guidance: Slowest tool: get_pergola_guidance (187 ms)
  pass
• –
  Tools work togetherNo tool's answer could be fed into another tool, so there were no chains to test (not counted either way)
  not tested
• –
  No secrets leakedNo error messages to check
  not tested

Test it yourself

Free and open source. Same checks, same score.

Show this score on GitHub

Free for every server in the directory. Paste this into your README: the badge shows the score from our latest test.

Score over time

• 11 Nov 202682

One test so far. New tests will show here.

Reviews

Coming soon: reviews from people who use Baldwin Pergolas, signed in with GitHub, one per person. Reviews never change the score.