Finance Ops — Medical Record Review — Northgate Services Group (dd8c58b7)

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

25 tools

Its own safety labels

13 read-only, 1 labeled as deleting or destroying, 10 labeled as changing things, 1 with no label

Memory it takes

About 10,700 tokens of your AI's memory, just for its tool descriptions

Largest answer

About 306.8 KB in our test

Speed

Average answer in our test: 52 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 Finance Ops — Medical Record Review — Northgate Services Group (dd8c58b7) MCP server safe?

• None of the hidden-instruction wordings we know were found in its 25 tool descriptions.
• Its error messages showed no secrets or internal details.
• 13 of its 25 tools are labeled read-only; the others may change or send things.
• Overall it scored 80/100 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

Not looked up yet. QAmcp tests how a server behaves. It does not scan source code.

What it can do

25 tools, in the server's own words.

and 1 more

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

  5 warnings

  • !benchmark_submit_answers: Inputs with no description: run_id, answers
  • !request_testnet_usdc: Inputs with no description: address
  • !data_session_open: Inputs with no description: max_queries, proof_escrow_id, open_tx_hash
  • !data_session_attach_escrow: Inputs with no description: proof_escrow_id, open_tx_hash
  • !data_session_query: Inputs with no description: query, k, delivery_receipt
  note
• !
  Tools are labeled safe or dangerous

  1 warning

  • !1 of 25 tools have no safety label (read-only or dangerous): request_testnet_usdc
  note
• !
  Tools work with good inputs

  2 warnings

  • !benchmarks_list: Answered with about 307 KB of text. Many AI apps cut off tool answers this big, so the AI may never see the end of it.
  • !a2awire_guide: Answered with about 175 KB of text. Many AI apps cut off tool answers this big, so the AI may never see the end of it.
  • –benchmark_start_run: Not run: labeled as changing data
  • –benchmark_submit_answers: Not run: labeled as changing data
  • –benchmark_finalize_run: Not run: labeled as changing data
  • –request_testnet_usdc: Not run: no safety label (if you own this server, test again in owner mode)
  • –confirm_keys_persisted: Not run: labeled as changing data
  • –data_session_open: Not run: labeled as changing data
  • and 17 more
  note
• !
  Follows MCP best practices (not scored yet)

  3 tips (not scored)

  • !1 tool not labeled read-only doesn't say whether running it twice is safe (idempotentHint): request_testnet_usdc
  • !1 tool doesn't say whether it reaches outside services like the web (openWorldHint): request_testnet_usdc
  • !The tool list is about 86 KB (roughly 22k 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 111 ms
  pass
• ✓
  Lists its toolsFound 25 tools
  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
• ✓
  Bad inputs give a clean error

  All good

  • ✓benchmarks_get: Refused missing required input "slug" with a clear error
  • ✓benchmarks_get: Refused wrong type for "slug" with a clear error
  • ✓benchmark_get_results: Refused missing required input "run_id" with a clear error
  • ✓benchmark_get_results: Refused wrong type for "run_id" with a clear error
  • ✓data_session_funding_package: Refused missing required input "session_id" with a clear error
  • ✓data_session_funding_package: Refused wrong type for "session_id" with a clear error
  • ✓find_paid_work: Refused wrong type for "limit" with a clear error
  • ✓discover_agents: Refused wrong type for "verified" with a clear error
  pass
• ✓
  Tools work togetherbenchmarks_list → benchmarks_get: benchmarks_get found what benchmarks_list returned (slug = "cw-capitals-1108-a17627f5")
  pass
• ✓
  Fast enough

  All good

  • ✓Connecting took 111 ms
  • ✓Listing tools took 88 ms
  • ✓Average tool answer: 52 ms
  • ✓benchmarks_list: Slowest tool: benchmarks_list (101 ms)
  pass
• ✓
  No secrets leakedChecked 30 error messages: no secrets or internal details
  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 202680

One test so far. New tests will show here.

Reviews

Coming soon: reviews from people who use Finance Ops — Medical Record Review — Northgate Services Group (dd8c58b7), signed in with GitHub, one per person. Reviews never change the score.