Everloot: WoW Forever data

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

32 tools

Its own safety labels

32 read-only

Memory it takes

About 10,600 tokens of your AI's memory, just for its tool descriptions

Largest answer

About 345.4 KB in our test

Speed

Average answer in our test: 381 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, 5 Nov 2026.

Is Everloot: WoW Forever data MCP server safe?

• None of the hidden-instruction wordings we know were found in its 32 tool descriptions.
• Its error messages showed no secrets or internal details.
• All 32 of its tools are labeled read-only.
• Overall it scored 85/100 on 5 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

32 tools, in the server's own words.

and 8 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
• !
  Tools work with good inputs

  1 warning

  • !coverage: Answered with about 345 KB of text. Many AI apps cut off tool answers this big, so the AI may never see the end of it.
  • and 31 more
  note
• !
  Fast enough

  1 warning

  • !answer_sources: Slowest tool: answer_sources (2.4 s): users will notice the wait
  • and 3 more
  note
• !
  Follows MCP best practices (not scored yet)

  2 tips (not scored)

  • !Very common tool names: search, fetch. Next to other servers' tools the AI may mix them up; a short prefix helps (like "github_search" instead of "search").
  • !The tool list is about 125 KB (roughly 31k 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

  6 warnings (12 resources, 6 templates, 3 prompts)

  • !everloot://item/{id}: A made-up value (everloot://item/qamcp-test) gets an internal error instead of a clean "not found": everloot://item/qamcp-test: id must be a positive id, not "qamcp-test".
  • !everloot://npc/{id}: A made-up value (everloot://npc/qamcp-test) gets an internal error instead of a clean "not found": everloot://npc/qamcp-test: id must be a positive id, not "qamcp-test".
  • !everloot://quest/{id}: A made-up value (everloot://quest/qamcp-test) gets an internal error instead of a clean "not found": everloot://quest/qamcp-test: id must be a positive id, not "qamcp-test".
  • !everloot://vendor/{id}: A made-up value (everloot://vendor/qamcp-test) gets an internal error instead of a clean "not found": everloot://vendor/qamcp-test: id must be a positive id, not "qamcp-test".
  • !everloot://object/{id}: A made-up value (everloot://object/qamcp-test) gets an internal error instead of a clean "not found": everloot://object/qamcp-test: id must be a positive id, not "qamcp-test".
  • !what_changed: Our sample inputs get an internal error instead of an "invalid input" error: what_changed takes game forever or classic, not "zq7test07e1d": forever or classic. Without it, both.
  • and 3 more
  note
• ✓
  ConnectsConnected in 2.5 s
  pass
• ✓
  Lists its toolsFound 32 tools
  pass
• ✓
  Every tool is describedAll 32 tools and their inputs are described
  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
• ✓
  Bad inputs give a clean error

  All good

  • ✓search_knowledge: Refused missing required input "query" with a clear error
  • ✓search_knowledge: Refused wrong type for "query" with a clear error
  • ✓get_entity: Refused missing required input "id" with a clear error
  • ✓get_entity: Refused wrong type for "id" with a clear error
  • ✓get_by_name: Refused missing required input "name" with a clear error
  • ✓get_by_name: Refused wrong type for "name" with a clear error
  • ✓search: Refused missing required input "query" with a clear error
  • ✓search: Refused wrong type for "query" with a clear error
  • and 32 more
  pass
• ✓
  Tools work together

  5 chains working

  • ✓search_knowledge → fetch: fetch found what search_knowledge returned (id = "11087")
  • ✓search_knowledge → entity_relations: entity_relations found what search_knowledge returned (id = "11087")
  • ✓search → get_entity: get_entity found what search returned (id = "11087")
  • ✓search → fetch: fetch found what search returned (id = "11087")
  • ✓search → entity_relations: entity_relations found what search returned (id = "11087")
  pass
• ✓
  No secrets leakedChecked 60 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

• 5 Nov 202685

One test so far. New tests will show here.

Reviews

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