Provides a local, isolated Linux VM sandbox for AI agents using Apple's Virtualization.framework, enabling fast command execution (~60ms) and package management without cloud costs.
Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
bird
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
Tool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
35/35 tools missing one or more hints — exec (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); python (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); write_file (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +32 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Descriptions match behaviour
3 tools describe read intent but their handlers mutate — health (line 3233: disk = await sb.exec(); logs (line 3498: alive_check = await sb.exec(); stats (line 3577: disk_result = await sb.exec()
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
Tool inputs are validated
29/35 tool handlers declare input schemas (83%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
Only 5/35 tool handlers wrap calls in try/catch (14%)
Wrap each tool handler body in try/catch and return a structured error response.
Tests exist
No test files found
Add tests that exercise each declared tool.
Shell command execution
42 child_process calls — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Tool description accuracy
3 tools have description/behavior mismatches: health: description implies read-only but handler writes/deletes/executes; logs: description implies read-only but handler writes/deletes/executes; stats: description implies read-only but handler writes/deletes/executes
Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/bird-sandbox-mcp-90ueep)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check