QAmcp

Copied. Paste it into Claude Code, Cursor or Codex:Fetch and follow the instructions at https://qamcp.dev/setup.md to test my MCP server.

Your AI finds your server in your project, tests it with QAmcp, explains what's wrong in plain words, fixes it with your OK, and tests again. Read the instructions

NewYour score can change any day. QAmcp Monitor keeps testing your server and emails you when it breaks. Free for 1 server.See what Monitor does →

Directory / Advocate

Advocate

Q: Is Advocate MCP server safe?

QAmcp's test on 7 Nov 2026: None of the hidden-instruction wordings we know were found in its 19 tool descriptions. Its error messages showed no secrets or internal details. 7 of its 19 tools are labeled read-only; the others may change or send things. Overall it scored 85/100 on 7 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.

by app.advocatemcp.com · https://api.advocatemcp.com/mcp

Find participating local businesses, read published facts, and request a quote, callback or booking.

19 tools✓ no account neededPricing: on their site

See pricing →Visit website

85 /100

PASS · WITH NOTES

13 of 13 checks · 7 Nov 2026

Test it now for current results

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: 19 tools
Its own safety labels: 7 read-only, 7 labeled as deleting or destroying, 5 labeled as changing things
Memory it takes: About 6,700 tokens of your AI's memory, just for its tool descriptions
Largest answer: About 2.6 KB in our test
Speed: Average answer in our test: 269 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, 7 Nov 2026.

Is Advocate MCP server safe?

None of the hidden-instruction wordings we know were found in its 19 tool descriptions.
Its error messages showed no secrets or internal details.
7 of its 19 tools are labeled read-only; the others may change or send things.
Overall it scored 85/100 on 7 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

19 tools, in the server's own words.

search_businessesread-only

Find registered businesses by search term and optional location; returns matches with their slugs.

get_credentialsread-only

Returns the business's self-reported licenses, insurance, bonding, and certifications.

get_cancellation_policyread-only

Returns the business's cancellation policy text.

get_availabilityread-only

Return available windows from the business's active configured calendar, using its selected timezone, duration, operating hours, and current local or connected…

get_booking_destinationread-only

Returns the public booking or inquiry route for a business.

list_servicesread-only

Lists the services a business has configured, with their prices and the exact arguments to quote each one.

get_quote

Return a price quote for a service at a business.

reserve_slot

Reserve a time slot on an active configured calendar.

confirm_booking

Confirm a reservation made with reserve_slot.

initiate_handoff

Begin a handoff from the agent to either a human operator (SMS/email via lead_routing_json) or another agent (signed continuation URL).

request_callback

Submit a callback request on behalf of a user.

subscribe_to_updates

Start a pending email subscription to updates from a business.

query_business_agent

Ask a registered business's AI advocate a question and get a citation-ready answer plus a referral link.

get_payment_handoff_url

Returns a plain-text summary of a priced offer (service, amount, currency, cancellation policy, and how long the price is valid) plus a URL on our domain that …

request_service

Open a quote-request form for a specific business using its public slug or provider_business_id obtained from search or the business feed.

submit_quote_request

After the customer explicitly agrees, save their service requirements and contact details and send a notification to the business's configured email or opted-i…

create_booking_payment_link

For a reservation that reserve_slot returned with payment.required = true: returns the MPP payment link, the amount charged now, and the balance due at the vis…

cancel_booking

Cancels a confirmed booking.

get_request_statusread-only

Reads the business's answer to a request this caller sent with submit_quote_request or request_callback, using the status_token that call returned.

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 (2025-11-25). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
note
!
Every tool is described
1 warning
- !submit_quote_request: Inputs with no description: contact_name, contact_email, contact_phone
note
!
Follows MCP best practices (not scored yet)
1 tip (not scored)
- !The tool list is about 51 KB (roughly 13k tokens). AI apps send it with every message, so it takes that much of the AI's memory before any work starts.
note
!
Resources and prompts work
1 warning (1 resource)
- !1 of 1 resources have no description, so people can't tell what they contain.
- and 2 more
note
✓
ConnectsConnected in 876 ms
pass
✓
Lists its toolsFound 19 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_businesses: Worked (317 ms)
- ✓get_credentials: Answered with an error, probably because of our sample input: {"error":"business_not_found","slug":"test"}
- ✓get_cancellation_policy: Answered with an error, probably because of our sample input: {"error":"business_not_found","slug":"test"}
- ✓get_availability: Answered with an error, probably because of our sample input: {"error":"business_not_found","slug":"test"}
- ✓get_booking_destination: Answered with an error, probably because of our sample input: {"error":"business_not_found","slug":"test"}
- ✓list_services: Answered with an error, probably because of our sample input: {"error":"business_not_found","slug":"test"}
- ✓get_request_status: Answered with an error, probably because of our sample input: {"error":"invalid_arguments","message":"Check the arguments against this tool's input schema."}
- –get_quote: Not run: labeled as changing data
- and 11 more
pass
✓
Bad inputs give a clean error
All good
- ✓search_businesses: Refused missing required input "search" with a clear error
- ✓search_businesses: Refused wrong type for "search" with a clear error
- ✓get_credentials: Refused missing required input "slug" with a clear error
- ✓get_credentials: Refused wrong type for "slug" with a clear error
- ✓get_cancellation_policy: Refused missing required input "slug" with a clear error
- ✓get_cancellation_policy: Refused wrong type for "slug" with a clear error
- ✓get_availability: Refused missing required input "slug" with a clear error
- ✓get_availability: Refused wrong type for "slug" with a clear error
- and 6 more
pass
✓
Tools work together
4 chains working
- ✓search_businesses → get_credentials: get_credentials found what search_businesses returned (slug = "water-wellness-west-valley")
- ✓search_businesses → get_cancellation_policy: get_cancellation_policy found what search_businesses returned (slug = "water-wellness-west-valley")
- ✓search_businesses → get_booking_destination: get_booking_destination found what search_businesses returned (slug = "water-wellness-west-valley")
- ✓search_businesses → list_services: list_services found what search_businesses returned (slug = "water-wellness-west-valley")
pass
✓
Fast enough
All good
- ✓Connecting took 876 ms
- ✓Listing tools took 312 ms
- ✓Average tool answer: 269 ms
- ✓get_booking_destination: Slowest tool: get_booking_destination (515 ms)
pass
✓
No secrets leakedChecked 26 error messages: no secrets or internal details
pass

Test it yourself

Free and open source. Same checks, same score.

npx qamcp-cli https://api.advocatemcp.com/mcp

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.

[![QAmcp score](https://qamcp.dev/s/com-advocatemcp-advocate.svg)](https://qamcp.dev/s/com-advocatemcp-advocate.html)

Score over time

7 Nov 202685

One test so far. New tests will show here.

Reviews

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

Is this your server? Get an alert the moment it breaks.

QAmcp Monitor tests it every hour and emails you when it goes down, the score drops, a tool changes or a secret leaks. Free for 1 server, no card.

Have a concern, or want it removed? Ask us and we'll take it off the list. How the directory works