MCP server that gives OpenCode a persistent, graph-based memory with semantic search, iterative retrieval, and session-aware knowledge management. It supports capturing fleeting and permanent notes, distilling insights, tracking mistakes and fixes, and auto-archiving stale memories.
Limited view. Automated analysis covers part of this stack. Findings reflect what we verified. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
Limited view: static analysis for Python is partially covered.
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
Adityaladi
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.
QDRANT_HOSTlocalhost Qdrant server hostQDRANT_PORT6333 Qdrant server portQDRANT_COLLECTIONopencode_brain Collection nameEMBEDDING_MODELsentence-transformers/all-MiniLM-L6-v2 Embedding modelHUGGINGFACE_API_KEY├── .env.example # copy to .env and fill in at minimumHUGGINGFACE_PROVIDERFAST_MODEL_IDQwen/Qwen3-4B-Instruct-2507 Fast default LLM for note construction and extractionFAST_MODEL_PROVIDERfeatherless-ai Inference provider for the fast model (overridden to nscale in .env)FAST_MODEL_MAX_TOKENSHARD_MODEL_IDQwen/Qwen3-30B-A3B-Instruct-2507 Hard fallback model for synthesis and memory evolutionHARD_MODEL_PROVIDERfeatherless-ai Inference provider for the hard modelHARD_MODEL_MAX_TOKENSOLLAMA_HOSTOLLAMA_ENABLEDOLLAMA_FAST_MODELOLLAMA_HARD_MODELOBSIDIAN_HOSTOBSIDIAN_API_KEYyour-key-hereOBSIDIAN_VAULT_SUBFOLDERbrain Subfolder in vault for notesGRAPH_PATH~/.opencode-brain/graph.json Knowledge graph persistence pathSTALE_DAYS_THRESHOLD45 Days before a note is staleSTALE_ACCESS_THRESHOLD2 Min accesses to be immune from archivalTool 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
19/19 tools missing one or more hints — add_memory (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); search_memory (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_related (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +16 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
18/19 tool handlers declare input schemas (95%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
Only 1/19 tool handlers wrap calls in try/catch (5%)
Wrap each tool handler body in try/catch and return a structured error response.
License file
No license file
Add a LICENSE file (MIT, Apache-2.0, etc.).
Tests exist
No test files found
Add tests that exercise each declared tool.
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/adityaladi-ai-bain-197di1)?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