Routes coding tasks to local and remote LLMs with intelligent cost-quality optimization, supports benchmarking and code search.
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.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
uuid: Missing buffer bounds check in v3/v5/v6 when buf is provided
process.env. You'll be asked to provide them before it can run.BENCHMARK_DB_PATHBENCHMARK_FRESHNESS_HOURSBENCHMARK_RESULTS_PATH— ./benchmark-resultsBENCHMARK_RUNS_PER_TASKDB_DIRDEFAULT_LOCAL_MODEL— qwen2.5-coder-3b-instructJOB_DB_PATHLM_STUDIO_ENDPOINT— LM Studio API base URLLOCALLAMA_PROFILELOCALLAMA_ROOT_DIR— Copy .env.example to .env and edit with your values. The server resolves .env from its own root directory (or when set), not from the MCP host's CWD.MAX_MODELS_TO_BENCHMARKMIN_VALIDATOR_SCORE— 0.6 Minimum validation score required before a model is eligible for external validationOPENROUTER_FREE_ONLY— false Restrict OpenRouter to free-tier models onlyOTEL_EXPORTER_OTLP_ENDPOINTPROVIDER_MAX_CONCURRENT_LOCAL— 1 Shared local execution slot countPROVIDER_MAX_CONCURRENT_REMOTE— 5 Per-remote-provider slot countPROVIDER_TIMEOUT_MSQUALITY_THRESHOLD— 0.7 Quality score below which paid API is always usedRELIABLE_BENCHMARK_COUNT— 3 Benchmark runs required before empirical scores are treated as fully reliableSTARTUP_BENCHMARK_TARGETSTOKEN_THRESHOLD— 1500 Token count above which local offload is consideredVALIDATION_RETRY_BUDGET— 1 Validation retry attempts allowed after an initial failed validation[](https://m8ven.ai/mcp/heratiki-locallama-mcp-e45ixt)