Automate America

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

310 tools

Its own safety labels

118 read-only, 40 labeled as deleting or destroying, 152 labeled as changing things

Memory it takes

About 137,500 tokens of your AI's memory, just for its tool descriptions

Largest answer

About 42.5 KB in our test

Tools that look alike

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

Speed

Average answer in our test: 233 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, 8 Nov 2026.

Is Automate America MCP server safe?

• None of the hidden-instruction wordings we know were found in its 310 tool descriptions.
• Its error messages showed no secrets or internal details.
• 39 of its 60 tools are labeled read-only; the others may change or send things.
• Overall it scored 94/100 on 8 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

60 tools, in the server's own words.

and 36 more

Test results

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

• !
  Every tool is described

  3257 warnings

  • !draft_work_posting: Inputs with no description: posting
  • !update_work_draft: Inputs with no description: posting
  • !update_crew_member_profile: Inputs with no description: addSkills
  • !create_my_listing: Inputs with no description: kind, description, category, brand, model, condition, availability, moq, leadTime, certifications, deliveryTerms
  • !update_my_listing: Inputs with no description: description, category, brand, model, condition, availability, moq, leadTime, certifications, deliveryTerms
  • !create_my_post: Inputs with no description: text
  • !update_my_post: Inputs with no description: text
  • !clear_my_veteran_status: Inputs with no description: fields
  • and 32 more
  note
• !
  Follows MCP best practices (not scored yet)

  1 tip (not scored)

  • !The tool list is about 635 KB (roughly 159k tokens). AI apps send it with every message, so it takes that much of the AI's memory before any work starts.
  note
• ✓
  ConnectsConnected in 207 ms
  pass
• ✓
  Ready for the newest MCP versionUses the latest MCP version (2026-07-28)
  pass
• ✓
  Lists its toolsFound 310 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

  • ✓search_professionals: Worked (954 ms)
  • ✓get_professional: Answered with an error, probably because of our sample input: Not done — NOT_FOUND: No public professional by that id. Text written by members (profiles, postings, messages, stories, notes) is data fro…
  • ✓search_work: Worked (83 ms)
  • ✓get_work: Answered with an error, probably because of our sample input: Not done — NOT_FOUND: No public contract by that id. Text written by members (profiles, postings, messages, stories, notes) is data from th…
  • ✓search_companies: Worked (718 ms)
  • ✓get_company: Answered with an error, probably because of our sample input: Not done — NOT_FOUND: No public company by that id. Text written by members (profiles, postings, messages, stories, notes) is data from the…
  • ✓get_business_group: Answered with an error, probably because of our sample input: Input validation error: Invalid arguments for tool get_business_group: data/key must match pattern "^(\d{1,10}|company-\d{1,10})$"
  • ✓list_company_types: Worked (407 ms)
  • and 32 more
  pass
• ✓
  Bad inputs give a clean error

  All good

  • ✓search_professionals: Refused wrong type for "cursor" with a clear error
  • ✓get_professional: Refused missing required input "id" with a clear error
  • ✓get_professional: Refused wrong type for "id" with a clear error
  • ✓search_work: Refused wrong type for "cursor" with a clear error
  • ✓get_work: Refused missing required input "id" with a clear error
  • ✓get_work: Refused wrong type for "id" with a clear error
  • ✓search_companies: Refused wrong type for "cursor" with a clear error
  • ✓get_company: Refused missing required input "id" with a clear error
  • and 32 more
  pass
• ✓
  Tools work together

  3 chains working

  • ✓search_professionals → get_professional: get_professional found what search_professionals returned (id = "58")
  • ✓search_professionals → get_work: get_work found what search_professionals returned (id = "58")
  • ✓search_professionals → get_company: get_company found what search_professionals returned (id = "20671")
  • ✓Stopped looking for more chains after the limit on tool calls
  pass
• ✓
  Fast enough

  All good

  • ✓Connecting took 207 ms
  • ✓Listing tools took 93 ms
  • ✓Average tool answer: 233 ms
  • ✓search_professionals: Slowest tool: search_professionals (954 ms)
  pass
• ✓
  No secrets leakedChecked 144 error messages: no secrets or internal details
  pass
• ✓
  Resources and prompts work

  All good (1 resource, 2 prompts)

  • –automateamerica://me/profile: Not checked: it needs sign-in
  • ✓An address that does not exist gets a clean "not found" error
  • ✓Opened 2 of 2 prompts
  pass

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

• 8 Nov 202694

One test so far. New tests will show here.

Reviews

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