HODDS

Q: Is HODDS MCP server safe?

QAmcp's test on 26 Oct 2026: No hidden instructions were found in its tool descriptions. Its error messages showed no secrets or internal details. 10 of its 19 tools are labeled read-only; the others may change or send things. Overall it scored 93/100 on 26 Oct 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 hodds.ai · https://hodds.ai/mcp

Find software, SaaS and APIs for a need in a sourced catalogue organised by business process.

19 tools✓ no account neededPricing: not listed

Visit website

93 /100

PASS · WITH NOTES

12 of 12 checks · 26 Oct 2026

Is HODDS MCP server safe?

No hidden instructions were found in its tool descriptions.
Its error messages showed no secrets or internal details.
10 of its 19 tools are labeled read-only; the others may change or send things.
Overall it scored 93/100 on 26 Oct 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

19 tools, in the server's own words.

search_solutionsread-only

Searches the HODDS catalogue of software, SaaS, APIs and online services, organised by business process, for records that match a need written in English or Fr…

get_solutionread-only

Returns one HODDS catalogue record by id (an option id returned by search_solutions): name, homepage, summary in English and French, processes (the first is pr…

list_processesread-only

Returns the HODDS process taxonomy: groups (for example "Run the business") and processes (for example "invoice-and-get-paid"), with English and French labels …

send_feedback

Stores a declarative outcome report for an option returned by search_solutions: outcome YES (the option met the need), PARTLY or NO, with the request_id and th…

watch_need

Opens a watch on a need for the organisation of the token: constraints and software by id or name (any process).

get_watchread-only

Returns one watch of the organisation: constraints, solution in place, challenger with its switch brief and HODDS status, challenger_reason when there is none,…

list_watchesread-only

Lists the watches of the organisation with their challenger and number of pending alerts; include_closed adds the watches closed in the last 30 days.

set_current_choice

Sets a solution by id or free name (any process), null clears.

ack_alerts

Acknowledges alerts of one watch (alert_ids, or all: true for every alert of this watch); the only call that empties the pending delivery.

rate_alert

Marks one alert relevant or not_relevant, with an optional note of at most 500 characters.

unwatch_need

Closes a watch; its need, constraints and alerts are erased 30 days after closing.

get_creator_planread-only

Returns the demand data subscription of the organisation of the token: plan NONE or SUBSCRIBED, subscribed processes, pending removals, the coming invoice, pay…

set_creator_processes

Replaces the list of subscribed processes.

list_gapsread-only

Returns, for a subscribed process, the gaps formulated by HODDS and the client aggregates above the anonymity threshold (watched needs, organisations watching,…

cancel_creator_plan

Stops the subscription at the end of the paid period.

get_planread-only

Returns the plan of the organisation of the token: FREE, PAID, PAST_DUE, ENDING or ENDED; watched solutions billed in the current Stripe period, the coming inv…

cancel_plan

Stops the paid plan at the end of the Stripe period.

compare_solutionsread-only

Compare 2–3 catalogue IDs by required capabilities, offer, context and dated sources.

find_comparable_solutionsread-only

Find alternatives by required priority, optionally relative to one solution.

Test results

Safe mode: only tools labeled read-only were run. How the test works

!
Every tool is described
3 warnings
- !set_creator_processes: Inputs with no description: processes
- !compare_solutions: Inputs with no description: solution_ids, priority, priority_required, criteria, requirements, context, cost_scenario, locale, view
- !find_comparable_solutions: Inputs with no description: reference_id, priority, criteria, requirements, context, cost_scenario, locale, limit, view
note
!
Follows MCP best practices (not scored yet)
1 tip (not scored)
- !The tool list is about 129 KB (roughly 32k 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 451 ms
pass
✓
Ready for the newest MCP versionUses the latest MCP version (2026-07-28)
pass
✓
Lists its toolsFound 19 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
- ✓search_solutions: Worked (454 ms)
- ✓get_solution: Answered with an error, probably because of our sample input: No solution with id "test". Catalogue ids are the option ids returned by search_solutions.
- ✓list_processes: Worked (21 ms)
- ✓get_watch: Answered with an error, probably because of our sample input: token_required: A valid HODDS token is required (Authorization: Bearer hodds_…). See https://hodds.ai/connect/.
- ✓list_watches: Answered with an error, probably because of our sample input: token_required: A valid HODDS token is required (Authorization: Bearer hodds_…). See https://hodds.ai/connect/.
- ✓get_creator_plan: Answered with an error, probably because of our sample input: token_required: A valid HODDS token is required (Authorization: Bearer hodds_…). See https://hodds.ai/connect/.
- ✓list_gaps: Answered with an error, probably because of our sample input: token_required: A valid HODDS token is required (Authorization: Bearer hodds_…). See https://hodds.ai/connect/.
- ✓get_plan: Answered with an error, probably because of our sample input: token_required: A valid HODDS token is required (Authorization: Bearer hodds_…). See https://hodds.ai/connect/.
- and 11 more
pass
✓
Bad inputs give a clean error
All good
- ✓search_solutions: Refused missing required input "need" with a clear error
- ✓search_solutions: Refused wrong type for "need" with a clear error
- ✓get_solution: Refused missing required input "id" with a clear error
- ✓get_solution: Refused wrong type for "id" with a clear error
- ✓get_watch: Refused missing required input "watch_id" with a clear error
- ✓get_watch: Refused wrong type for "watch_id" with a clear error
- ✓list_watches: Refused wrong type for "include_closed" with a clear error
- ✓list_gaps: Refused missing required input "process" with a clear error
- and 5 more
pass
✓
Tools work togethersearch_solutions → get_solution: get_solution found what search_solutions returned (id = "circleci")
pass
✓
Fast enough
All good
- ✓Connecting took 451 ms
- ✓Listing tools took 32 ms
- ✓Average tool answer: 253 ms
- ✓get_watch: Slowest tool: get_watch (1.9 s)
pass
✓
No secrets leakedChecked 32 error messages: no secrets or internal details
pass

Test it yourself

Free and open source. Same checks, same score.

npx qamcp-cli https://hodds.ai/mcp

Score over time

26 Oct 202693

One test so far. New tests will show here.

Reviews

Coming soon: reviews from people who use HODDS, 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 show a "Tested by QAmcp" badge. 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