Capxule

by capxule.com · https://capxule.ai/mcp

The context marketplace: expert guided journeys your assistant runs step by step.

12 tools✓ no account neededPricing: on their site

See pricing →Visit website

84 /100

PASS · WITH NOTES

11 of 11 checks · 21 Oct 2026

What it can do

12 tools, in the server's own words.

find_capsuleread-only

Covers: 163 guided journeys across 17 areas: Finance (33, e.g.

list_categoriesread-only

Lists the areas the published guided journeys cover: each category slug, a readable label, how many journeys it holds and a few example titles.

browse_catalogread-only

Pages through the published guided journeys, optionally within one category (a slug from list_categories), featured first.

open_journey

Opens (or resumes) a guided journey and returns the session contract: `session` (keep it), the stop list (titles only), the capabilities, the limits in turns, …

turn

Sends the user's move and returns ONE whole beat: `answer`, `statement`, numbered `options` with opaque ids, `media`, `progress`, `limits` and `narration.text_…

journey_stateread-only

Where the user is in the journey: position (stop, visited of total), `remaining` (stops left, percent done, and each top-level topic's visited of total), mode,…

make_artifact

Composes the user's takeaway (kind "takeaway") from THIS conversation: what they asked, what landed, the stops they visited.

handoff

Mints a resume link and code for this session so the user can continue on the website or in another assistant.

restart_journey

Starts the user's walk through a journey over: back to the first step, visited stops cleared, any drill or mock session closed.

account_statusread-only

Whether this connection is bound to an account, whether that account includes the premium journeys (`premium`, a flag) and unlimited web turns, the assistants …

account_bind

Starts binding an account for the user without a web visit.

account_verify

Completes account_bind: pass the challenge it returned and the code the user read you (digits only; spaces are fine).

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
4 warnings
- !turn: Inputs with no description: action
- !make_artifact: Inputs with no description: kind
- !account_bind: Inputs with no description: method
- !account_verify: Inputs with no description: code_challenge_method
note
!
Resources and prompts work
1 warning (2 resources, 1 prompt)
- !1 of 2 resources have no description, so people can't tell what they contain.
- –start_journey: Not checked: the server limited our requests (HTTP 429)
- and 2 more
note
✓
ConnectsConnected in 496 ms
pass
✓
Lists its toolsFound 12 tools
pass
✓
Tools are labeled safe or dangerousEvery tool has a safety label
pass
✓
No hidden instructionsNo hidden instructions found in tool descriptions
pass
✓
Tools work with good inputs
All good
- ✓find_capsule: Worked (1.8 s)
- ✓list_categories: Worked (21 ms)
- ✓browse_catalog: Worked (81 ms)
- ✓journey_state: Answered with an error, probably because of our sample input: { "error": { "code": "session_required", "for_human": "I need to start a session before I can take you through this.", "for_agent": "Call o…
- ✓account_status: Worked (19 ms)
- –open_journey: Not run: labeled as changing data
- –turn: Not run: labeled as changing data
- –make_artifact: Not run: labeled as changing data
- and 4 more
pass
✓
Bad inputs give a clean error
All good
- ✓find_capsule: Refused missing required input "query" with a clear error
- ✓find_capsule: Refused wrong type for "query" with a clear error
- ✓browse_catalog: Refused wrong type for "category" with a clear error
- ✓journey_state: Refused missing required input "session" with a clear error
- ✓journey_state: Refused wrong type for "session" with a clear error
- ✓account_status: Refused wrong type for "session" with a clear error
pass
✓
Fast enough
All good
- ✓Connecting took 496 ms
- ✓Listing tools took 26 ms
- ✓Average tool answer: 387 ms
- ✓find_capsule: Slowest tool: find_capsule (1.8 s)
pass
✓
No secrets leakedChecked 7 error messages: no secrets or internal details
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://capxule.ai/mcp

Score over time

14 Oct 202684
17 Oct 202684
18 Oct 202684
21 Oct 202684

Reviews

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

Is this your server?

Soon you can claim this page: re-test it from here, reply to results, and show a "Tested by QAmcp" badge.

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