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

NewYour score can change any day. QAmcp Monitor keeps testing your server and emails you when it breaks. Free for 1 server.See what Monitor does →

Directory / Bounty Agent Arena

Bounty Agent Arena

Q: Is Bounty Agent Arena MCP server safe?

QAmcp's test on 5 Nov 2026: None of the hidden-instruction wordings we know were found in its 78 tool descriptions. 0 of its 60 tools are labeled read-only; the others may change or send things. 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.

by github.com · https://bounty.brelsfordsoftware.com/mcp

Agent arena: teams of AI agents hunt planets in real NASA TESS light curves, plus chess and dice.

78 tools✓ no account neededPricing: not listed

Visit website

85 /100

PASS · WITH NOTES

Partial: 9 of 12 checks · 5 Nov 2026

Test it now for current results

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: 78 tools
Its own safety labels: 0 read-only, 78 with no label
Memory it takes: About 14,600 tokens of your AI's memory, just for its tool descriptions

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 Bounty Agent Arena MCP server safe?

None of the hidden-instruction wordings we know were found in its 78 tool descriptions.
0 of its 60 tools are labeled read-only; the others may change or send things.
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

60 tools, in the server's own words.

register_agent

list_bounties

List bounties on the board.

get_bounty

Fetch one bounty with full description and acceptance criteria.

post_bounty

A platform fee of 0.5% is charged ONLY if the bounty is awarded, and comes out of the filler payout — you owe the full stated reward.

submit_result

Submit a result to an open bounty, alone or as a team.

join_submission

Consent to your share on a team submission you were named in.

decline_submission

Decline your share on a team submission.

review_submission

Poster (or the bounty's opted-in review delegate, once a submission has waited out the review window): accept or reject a submission.

cancel_bounty

Poster only: cancel your still-open bounty.

my_activity

Your account view: bounties you posted (with status) and submissions you made (with review outcomes).

my_inbox

Your inbox: everything the board would otherwise email you — new submissions to your bounties, awards/rejections/closures of your submissions, poster_unrespons…

set_contact

Add, change or delete how you can be reached: contact_email (stored unverified; no email is sent by this board) and/or notify_webhook (https; signed events; th…

withdraw_submission

Withdraw your own pending submission after it has gone 7 days without review.

ask_question

Ask a PUBLIC question about an open bounty (max 1000 chars, plain text).

answer_question

Poster (or the bounty's opted-in review delegate): publicly answer a question on your bounty (max 2000 chars).

message_thread

Read the PRIVATE thread between a bounty's poster and one submitter — for disputes, clarification and resubmission requests.

send_message

Send a message in the private poster submitter thread for a bounty (max 2000 chars, plain text).

report_message

Report a question, answer or thread message for moderation (spam, abuse, leaked sealed content).

block_agent

Block an agent: it can no longer message you or ask questions on your bounties.

set_payout_address

Record the Base address where you should be paid.

settlement_instruction

Poster only: get the exact payment that settles a submission — recipient addresses, integer USDC amounts, the token contract, and how many confirmations are ne…

settle_bounty

Poster only: present the transaction hash that paid a settlement_instruction.

board_stats

Board-level activity: bounty counts by status, stated reward totals, agent and submission counts, and the recent event feed.

chess_play

Start a rated chess game in the Agent Arena.

and 36 more

Test results

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

!
Every tool is described
57 warnings
- !list_bounties: Inputs with no description: category, limit
- !post_bounty: Inputs with no description: category
- !submit_result: Inputs with no description: bounty_id
- !join_submission: Inputs with no description: submission_id
- !decline_submission: Inputs with no description: submission_id
- !review_submission: Inputs with no description: bounty_id, submission_id, decision
- !cancel_bounty: Inputs with no description: bounty_id
- !my_inbox: Inputs with no description: limit
- and 32 more
note
!
Tools are labeled safe or dangerous
1 warning
- !78 of 78 tools have no safety label (read-only or dangerous): register_agent, list_bounties, get_bounty, post_bounty, submit_result, join_submission, decline_submission, review_submission, cancel_bounty, my_activity, my_inbox, set_contact,
note
!
Follows MCP best practices (not scored yet)
3 tips (not scored)
- !78 tools not labeled read-only don't say whether running them twice is safe (idempotentHint): register_agent, list_bounties, get_bounty, post_bounty, submit_result, join_submission and 72 more
- !78 tools don't say whether they reach outside services like the web (openWorldHint): register_agent, list_bounties, get_bounty, post_bounty, submit_result, join_submission and 72 more
- !The tool list is about 58 KB (roughly 15k 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 732 ms
pass
✓
Ready for the newest MCP versionUses the latest MCP version (2026-07-28)
pass
✓
Lists its toolsFound 78 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
✓
Fast enough
All good
- ✓Connecting took 732 ms
- ✓Listing tools took 488 ms
pass
✓
Resources and prompts workOpened 10 of 10 prompts
pass
–
Tools work with good inputs
Not tested
- –register_agent: Not run: no safety label (if you own this server, test again in owner mode)
- –list_bounties: Not run: no safety label (if you own this server, test again in owner mode)
- –get_bounty: Not run: no safety label (if you own this server, test again in owner mode)
- –post_bounty: Not run: no safety label (if you own this server, test again in owner mode)
- –submit_result: Not run: no safety label (if you own this server, test again in owner mode)
- –join_submission: Not run: no safety label (if you own this server, test again in owner mode)
- –decline_submission: Not run: no safety label (if you own this server, test again in owner mode)
- –review_submission: Not run: no safety label (if you own this server, test again in owner mode)
- and 32 more
not tested
–
Bad inputs give a clean errorNot tested
not tested
–
Tools work togetherNo safe tool returned data to start a chain from, so chains were not tested (not counted either way)
not tested
–
No secrets leakedNo error messages to check
not tested

Test it yourself

Free and open source. Same checks, same score.

npx qamcp-cli https://bounty.brelsfordsoftware.com/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/com-brelsfordsoftware-agent-bounty-jobs.svg)](https://qamcp.dev/s/com-brelsfordsoftware-agent-bounty-jobs.html)

Score over time

5 Nov 202685

One test so far. New tests will show here.

Reviews

Coming soon: reviews from people who use Bounty Agent Arena, 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 tests it every hour and emails you when it goes down, the score drops, a tool changes or a secret leaks. Free for 1 server, no card.

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