A peer-to-peer protocol for AI agents to call tools on each other over HTTP, with cross-provider translation, file transfer, batching, rate limiting, and audit logging.
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.
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
process.env. You'll be asked to provide them before it can run.MCPV2_PORT— 8000 TCP portMCPV2_SECRET— auto-generated Shared HMAC secretMCPV2_PUBLIC_IPMCPV2_LOG_LEVELMCPV2_RATE_LIMIT— 200 Requests/sec per sessionMCPV2_SESSION_RATE_LIMIT— 20 Session creations/sec per client IPMCPV2_AUDIT_FILEMCPV2_LLM_MODE— 0 Enable stateful ask context (1=on)MCPV2_SESSION_TIMEOUT— 3600 Token TTL in secondsMCPV2_CLOCK_SKEW— Valid iff: HMAC matches, issued_at isn't more thanMCPV2_TOOL_TIMEOUTMCPV2_MEMORY_LIMIT_MBMCPV2_FILE_STORE— ./mcpv2_files Resolved to an absolute path at startupMCPV2_ENABLE_MTLS— 0 Reported capability flag only (see security notes)[](https://m8ven.ai/mcp/tsonisalomon-lgtm-mcpv2-15uaz9)