mcp-server@32.0.99
VERIFIED· not startedPublisher claims: "BattleGrid MCP server — play crypto prediction games from AI agents" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
BATTLEGRID_API_KEYBATTLEGRID_API_KEYSConfiguration, not credentials: BATTLEGRID_API_URL- Where it talks to
- battlegrid.trade (its own)
- What the honeypot saw
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard. It asks for BATTLEGRID_API_KEY, BATTLEGRID_API_KEYS and talks to battlegrid.trade. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
What changed since 32.0.97
vet-skills diff mcp-server 32.0.97 32.0.99In the sandbox, this version reached for nothing 32.0.97 did not. Compared from the two recorded runs, not from source.
32.0.97 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-17 and scored it 90/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 27 s · 2 scenarios · 0 deviationsStatic findings
* BATTLEGRID_API_KEYS=bg_live_aaa,bg_live_bbb npx @battlegrid/mcp-serverFix: Pin versions and sources; vendor anything fetched at install time.restated a configured cap of 32 as a looser 64 that never refused anything. `budgets.sections` andFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.input that asks for less adds none. A tool that writes is never refused this way. The code also joins the draftFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- `warnings` — observations that never refuse. `NO_ENTRY_CONDITION` means the strategy declares noFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.// background failure cannot kill a process that has already answered its handshake. The failure isFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.* BATTLEGRID_API_KEYS=bg_live_aaa,bg_live_bbb npx @battlegrid/mcp-serverFix: Pin versions and sources; vendor anything fetched at install time.* BATTLEGRID_API_KEY=bg_live_... npx @battlegrid/mcp-serverFix: Pin versions and sources; vendor anything fetched at install time.outside it, so a create that leaves a dial untouched is never refused for a value the platform seeded.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.… new create draft; the response carries the minted id. A stage that has written never refuses: the composed draft's errors and warnings come back as `diagnostics`. It is re…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.may hold such content — staging never refuses a draft for being invalid — but its commit isFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.always plays. A Radar preview simulates a running platform, so it never reports the kill switch or anFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.* BATTLEGRID_API_KEY=bg_live_... npx @battlegrid/mcp-serverFix: Pin versions and sources; vendor anything fetched at install time.opened after it, and an open position keeps the exit rules it opened with, so an open position neverFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
Not checked against OSV yet; the weekly check has not reached this version.