Warning. Serious findings were identified. Review the full report before connecting. 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
yuk1no4090
Source: github_code
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.
AGENT_GRAPH_MODEsupervisor Graph routing mode: supervisor for dynamic multi-agent routing or linear for the original 9-node pipeline.AGENT_HITL_ENABLEDImpact -->"high risk + " HITL{{"human_review<br/>(paused — resume via POST /api/langgraph-resume)"}}AI_PM_API_TOKENunset Optional token sent as Authorization: Bearer <token>; only needed when the main server runs with AI_PM_AUTH_REQUIRED=true.AI_PM_AUTH_REQUIREDAI_PM_API_TOKEN unset Optional token sent as Authorization: Bearer <token>; only needed when the main server runs with =true.AI_PM_BASE_URL"": "http://127.0.0.1:3000",AI_PM_PROJECT_IDunset Optional default projectId so tool calls can omit it once a repository has been imported.AI_PM_USER_TOKENSunset Token-to-user mapping, either JSON such as {"token-a":"user-a"} / {"token-a":{"userId":"user-a","role":"viewer","scopes":["project:read"]}} or comma-separated token:userId pairs.COMMIT_SHACORS_ORIGINCORS allow-origin header value. Set to a specific origin (e.g. https://yourapp.com) in production.DATA_DIRdata Directory for runtime JSON storage.GITHUB_SHAHOST127.0.0.1 HTTP server host.LOG_LEVELinfo Structured log level: debug, info, warn, or error.MEMORY_DB_PATHDATA_DIR/memory.sqlite SQLite database path for confirmed long-term memory items.MEMORY_EMBEDDING_PROVIDERunset Set to openai to use an OpenAI-compatible embeddings endpoint for long-term memory vectors.MEMORY_VECTOR_INDEX_API_KEYunset Optional bearer token for generic HTTP indexes, Qdrant api-key, or Pinecone Api-Key header value.MEMORY_VECTOR_INDEX_NAMESPACEai-pm-memory / ai_pm_memory Namespace, Qdrant collection name, or Pinecone namespace passed to the external vector index.MEMORY_VECTOR_INDEX_PROVIDERunset Set to http for a generic HTTP vector index, qdrant, or pinecone.MEMORY_VECTOR_INDEX_URLunset Base URL for the external vector index. Generic HTTP calls /upsert and /query; Qdrant calls /collections/{collection}/points; Pinecone calls /vectors/upsert and /query on the index host.OPENAI_API_KEYexport =sk-...OPENAI_BASE_URLexport =https://api.openai.com # or any OpenAI-compatible providerOPENAI_EMBEDDING_API_KEYOPENAI_API_KEY API key for the embeddings endpoint when external memory embeddings are enabled.OPENAI_EMBEDDING_BASE_URLOPENAI_BASE_URL or https://api.openai.com Base URL for the embeddings endpoint; the app calls /v1/embeddings.OPENAI_EMBEDDING_MODELtext-embedding-3-small Embedding model name used when external memory embeddings are enabled.OPENAI_MODELexport =gpt-4o-miniRATE_LIMIT_MAX120 Maximum API requests per window per IP. Set to 0 to disable rate limiting.RATE_LIMIT_WINDOW_MS60000 Rate limit window duration in milliseconds.STORE_PATHDATA_DIR/store.json Exact runtime store file path.PORTTool 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
4/4 tools missing one or more hints — list_projects (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); ask_codebase (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); analyze_impact (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +1 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.
License file
No license file
Add a LICENSE file (MIT, Apache-2.0, etc.).
Tool test coverage
Only 0/4 tools referenced in tests (0%)
Write tests that reference each tool by name so every tool has at least one test.
Secrets stay with their owner
3 secret/sensitive values flow into network calls (OPENAI_API_KEY → dynamic, MEMORY_VECTOR_INDEX_API_KEY → dynamic)
Audit where credentials are sent. A NOTION_TOKEN should only reach api.notion.com — never a third-party host.
Secrets not logged
2 secret values sent to console.log
Redact or omit secret values from log output.
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/yuk1no4090-repomentor-1e1x87)?variant=verified from the 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