An MCP server that provides coding models with a live code index, inferred code graph, durable memory, and surgical tools to help them leverage their existing reasoning and coding abilities effectively.
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.JAMBAVAN_ALLOW_BASH— 7. bash — run the smallest relevant check. (needs =1)JAMBAVAN_ALLOW_OUTSIDE_ROOT— off 1 lets tools escape the project root (trusted local use only)JAMBAVAN_ALLOW_SECRETS— off 1 lets file tools touch secret-looking filesJAMBAVAN_ALLOW_WRITE— 5. patch_file over write_file — surgical edits, cheaper tokens. (needs =1)JAMBAVAN_BASH_INHERIT_ENV— off 1 passes the full host env to bash (default: minimal env)JAMBAVAN_DEV_MODE— full Default Vibhishana Niti level (lite / full / ultra)JAMBAVAN_MAX_OUTPUT_CHARS— 100000 Global cap on any tool's returned outputJAMBAVAN_MAX_READ_BYTES— 5242880 Max file size read_file will loadJAMBAVAN_MEMORY_HOME— indexDir>/memory Where OKF memory docs live; point at a shared palace to reuse memory across projectsJAMBAVAN_ROOT— Set =/path/to/project when launching from outside the target repo.JAMBAVAN_TOKEN_BUDGET— 8000 Max tokens in jambavan_context output[](https://m8ven.ai/mcp/beingmartinbmc-jambavan-ghnbgb)