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

SoonYour score can change any day. QAmcp Monitor tests your server every hour and emails you when it breaks.See what Monitor does →

Directory / arrowmem-mcp

arrowmem-mcp

Q: Is arrowmem-mcp server safe?

QAmcp's test on 1 Nov 2026: None of the hidden-instruction wordings we know were found in its tool descriptions. Its error messages showed no secrets or internal details. 11 of its 14 tools are labeled read-only; the others may change or send things. Overall it scored 88/100 on 1 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 arrowmem.ca · https://mcp.arrowmem.ca/mcp

Canadian public-sector data and legal information for AI agents, paid per call in USDC over x402

14 tools✓ no account neededPricing: on their site

See pricing →Visit website

88 /100

PASS · WITH NOTES

11 of 11 checks · 1 Nov 2026

Is arrowmem-mcp server safe?

None of the hidden-instruction wordings we know were found in its tool descriptions.
Its error messages showed no secrets or internal details.
11 of its 14 tools are labeled read-only; the others may change or send things.
Overall it scored 88/100 on 1 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 it can do

14 tools, in the server's own words.

check_exposed_servicesread-only

ArrowMem Guard's machine security sweep, given diagnostic output your own machine (or AI tool) already produced locally - this tool never reaches your machine …

check_ollama_hardeningread-only

Checks whether a self-hosted model server install still matches the hardening guide's defaults, given the diagnostic output your own machine (or AI tool) alrea…

check_ollama_loopbackread-only

Checks one thing: whether your self-hosted model server is reachable from outside the machine.

disable_alert_relay

Ends this API key's ArrowMem Guard alert relay enrolment.

enrol_alert_relay

Enrols this API key in the ArrowMem Guard alert relay (the watchdog page and the family 'Is It Really Me' check).

get_arrowbridge_inforead-only

ArrowBridge, the local-first / own-hardware half of ArrowMem's privacy design - what it does today and what is still planned, not live.

get_data_dignity_standardread-only

The Data Dignity Standard (v0.5, draft for public comment): a free, open, testable standard for what happens to a person's data when an AI agent interacts with…

get_hardening_guideread-only

The full, live-tested procedure for hardening a self-hosted model server (mesh-only reachability, loopback-only bind, unique per-install credentials, disk encr…

get_org_inforead-only

ArrowMem Inc.

get_privacy_modelread-only

ArrowMem's privacy and security architecture: zero retention, client-side encryption, processing-location disclosure, and how the business is funded without re…

get_verified_business_factsread-only

Looks up hand-verified facts about a local business by name and city: legal name, locations, published prices (each with its source URL and the date it was ver…

inventory_ai_agentsread-only

Lists every AI tool configuration on this machine and every tool each one exposes at the config level, plus which agent hosts could not be checked and why.

list_packsread-only

The specific government disability-claim packs that run inside ArrowMem, and how the optional cross-device sync tier works.

rotate_alert_relay

Replaces part of this API key's ArrowMem Guard alert relay enrolment.

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
6 warnings
- !check_exposed_services: Inputs with no description: platform, ollama_listen_addresses, postgres_listen_addresses, mongodb_listen_addresses, redis_listen_addresses, elasticsearch_listen_addresses, jupyter_listen_addresses, firewall_status_text, disk_encryption_stat
- !check_ollama_hardening: Inputs with no description: platform, ollama_host_env, ollama_listen_addresses, caddy_listen_addresses, caddyfile_text, disk_encryption_status_text
- !check_ollama_loopback: Inputs with no description: ollama_host_env, ollama_listen_addresses
- !get_verified_business_facts: Inputs with no description: business_name, city
- !inventory_ai_agents: Inputs with no description: claude_desktop_config_text, claude_code_user_config_text, claude_code_project_config_text, cursor_global_config_text, cursor_project_config_text, claude_desktop_tools_text, claude_code_user_tools_text, claude_cod
- !rotate_alert_relay: Inputs with no description: scope
note
✓
ConnectsConnected in 505 ms
pass
✓
Lists its toolsFound 14 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
- –check_exposed_services: Needs you to sign in, so it was not tested (not counted against the server)
- ✓check_ollama_hardening: Worked (60 ms)
- ✓check_ollama_loopback: Worked (58 ms)
- ✓get_arrowbridge_info: Worked (60 ms)
- ✓get_data_dignity_standard: Worked (56 ms)
- ✓get_hardening_guide: Worked (63 ms)
- ✓get_org_info: Worked (55 ms)
- ✓get_privacy_model: Worked (55 ms)
- and 6 more
pass
✓
Bad inputs give a clean error
All good
- –check_exposed_services: Needs you to sign in, so bad inputs were not tested
- ✓check_ollama_hardening: Refused wrong type for "platform" with a clear error
- ✓check_ollama_loopback: Refused wrong type for "ollama_host_env" with a clear error
- ✓get_verified_business_facts: Refused missing required input "business_name" with a clear error
- ✓get_verified_business_facts: Refused wrong type for "business_name" with a clear error
- ✓inventory_ai_agents: Refused wrong type for "claude_desktop_config_text" with a clear error
pass
✓
Fast enough
All good
- ✓Connecting took 505 ms
- ✓Listing tools took 60 ms
- ✓Average tool answer: 59 ms
- ✓get_hardening_guide: Slowest tool: get_hardening_guide (63 ms)
pass
✓
No secrets leakedChecked 7 error messages: no secrets or internal details
pass
✓
Follows MCP best practices (not scored yet)Tool names, safety labels and tool list size follow the MCP guide
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

Test it yourself

Free and open source. Same checks, same score.

npx qamcp-cli https://mcp.arrowmem.ca/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/ca-arrowmem-arrowmem-mcp.svg)](https://qamcp.dev/s/ca-arrowmem-arrowmem-mcp.html)

Score over time

1 Nov 202688

One test so far. New tests will show here.

Reviews

Coming soon: reviews from people who use arrowmem-mcp, 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 (coming soon) tests it every hour and emails you when it goes down, the score drops, a tool changes or a secret leaks. You'll also be able to claim this page and get a verified owner mark. Founding price: $19/month for life for the first 50 teams.

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