Bragproof

← Reports

agent-referee-mcp

Starts with no setup0.6.1npm

Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.

Needs to start: nothing
Contacts while installing and starting: nothing

6tools listed
0hosts contacted
0files written
0.0 sto start
1dependencies

What it contacted

Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.

Starting it

npx -y -p agent-referee-mcp@0.6.1 agent-referee-mcp

Installing a package runs its code. Use a sandbox for anything you have not read.

What its tools tell an agent

In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.

Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.

Tools

demo_match tier, seats, weights, title
Free, no wallet: runs a complete Agent Referee tie-break in one call, playing both seats, and returns the winner, the signed receipt and the checks. Use it to see how Agent Referee works or to test the connection. It is not a real decision between two agents (use tiebreak for that). Demo limit: 20 per day per IP address.
tiebreak key, my_seat, seats, tier, weights, title, move, wait_seconds
Settle a deadlock with an agent from a different owner, when neither of you should decide alone (who goes first, which of two equal plans). Both agents call this tool with the same key and settings, each with its own my_seat; Agent Referee combines both agents' secret seeds (commit-reveal), so neither side nor the service can steer the result, and both get the same signed receipt. Blocks until the other agent joins (up to wait_seconds) and the result is in. Currently free demo matches only (receipts marked demo); paid tiers are coming next. If both agents have the same owner, deciding in code is the default; this tool is the option when both agree a fair pick is quicker or fairer, and then record the key, both seats, the receipt id and the result afterwards, wherever the team keeps its decisions.
sealed_review task, output, pieces, tier, title, criteria, panel, wait_seconds, free
FREE OR PAID. Free: each address gets 3 single-reviewer reviews and 1 review-3 a day, inside a daily budget shared by everyone (used whenever no wallet is set up, or with free: true). Paid: $0.05, or $0.20 for review-3, in USDC on Base from the wallet the owner configured; charged only if the review completes, and capped per day by the owner. Multi-part (paid only, $0.60 for review-3x2, $0.70 for review-3x3): send the work as 2 or 3 pieces instead of one output, and three reviewers from three companies each read every piece. Team allowance: when the owner has set one up (AGENT_REFEREE_TEAM_MEMBER), reviews are paid from it instead of the wallet, at the same prices; check what's left with team_allowance. Independent AI reviewers check one agent's output against the task it was given and return a verdict (pass, needs_changes, fail, cannot_assess; review-3 can also be split), the problems found, and a signed receipt the agent can hand to whoever receives the work. Use it when someone else needs to trust the check, not for routine self-checks. The task and output are sent to the AI companies running the reviewers: leave out secrets and personal data. Can take a few minutes: the call waits up to wait_seconds (default 45), then returns status "running" and a job_id while the review carries on; get it with review_result. The receipt is saved to disk automatically either way. Agent Referee is for technical evaluation of AI agents' work; it isn't for deciding legal claims, contractual disputes or anyone's rights; results are advisory.
review_result job_id, wait_seconds
Free and local: returns the result of a sealed_review that was still running when its call returned (status "running" and a job_id). Waits up to wait_seconds (default 45) for it to finish; if it still isn't done, call again. Nothing more is charged.
verify_receipt receipt, task, output, pieces, acks, sha256, repo, sha
Free and offline: checks an Agent Referee receipt (a sealed review or a match) against the service's pinned signing key, recomputes what can be recomputed, and lists any problems. For a sealed review someone handed you, pass the exact task and output you have, so the check confirms the review is about that exact work. Flags demo receipts.
saved_receipts id, limit
Free and local: lists the sealed-review receipts this server saved on this machine (newest first), or returns one in full by its review_id, plus today's paid spend. Use it to find a receipt again, for example after a review call timed out on your side but finished on the service.

Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.

Install facts

LicenseMIT
Needsnode >=18
Sourcegithub.com/ccheez34/agent-referee-mcp
Install scriptsNone declared by it or anything installed with it.
Tarballsha512-Wj73GLwciX8XwDY9xxu7so0gsy9jfwuGeOg9okomnjG4/fEC/TDM6P0/N7sqtOjNxVsPq9yc0ILk185MJMy+Nw==

Check this report yourself

This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.

Show it on your README

Bragproof: Starts with no setup

[![Bragproof](https://bragproof.smaverk.com/badge/agent-referee-mcp.svg)](https://bragproof.smaverk.com/r/agent-referee-mcp)

New version out? Ask for a fresh report.