Enables ordering and managing Forkable corporate lunches from any MCP client, including viewing menus, setting/skipping/confirming meals, and getting personalized recommendations.
Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. 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
colinds
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.
FORKABLE_COOKIE'_easyorder_session=…; other=…' bunx forkable-mcp --authFORKABLE_CSRFPin a CSRF token instead of the auto-fetched one (rarely needed).FORKABLE_EMAILor set / FORKABLE_PASSWORD (+ FORKABLE_MFA), then: bunx forkable-mcp --auth --loginFORKABLE_MAX_TOTALHard spend cap in dollars: a write whose total exceeds it is refused (no confirm-token). Unset = no cap; the preview just notes when a meal is over your company's daily coverage.FORKABLE_MCP_HOME~/.forkable-mcp Directory for the on-disk session (mode 0600).FORKABLE_MFAor set FORKABLE_EMAIL / FORKABLE_PASSWORD (+ ), then: bunx forkable-mcp --auth --loginFORKABLE_PASSWORDor set FORKABLE_EMAIL / (+ FORKABLE_MFA), then: bunx forkable-mcp --auth --loginFORKABLE_WRITE_SECRETper-install HMAC key for write confirm-tokens. Auto-generated and stored in the session file if unset; set it to pin one across machines.All four hints declared on every tool
11/11 tools missing one or more hints — get_profile (missing: destructiveHint, idempotentHint); list_deliveries (missing: destructiveHint, idempotentHint); get_menus (missing: destructiveHint, idempotentHint), +8 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.
Tool inputs are validated
10/11 tool handlers declare input schemas (91%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool test coverage
Only 0/11 tools referenced in tests (0%)
Write tests that reference each tool by name so every tool has at least one test.
Shell command execution
1 child_process/subprocess call in production code — runs shell commands (src/auth/chrome.ts:172)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
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/colinds-forkable-mcp-1fcwif)?variant=verified to the badge 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