Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. 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
sashabedard
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.
TD_MCP_REQUIRE_PLANtd_create_op hard-fails without a registered td_planANTHROPIC_API_KEYShader ingestion / vision + VJ classification. ANTHROPIC_BASE_URL routes the vision pass through an OpenAI-compatible gateway (OpenRouter etc.) — set TD_MCP_VISION_MODEL to that gateway's model idTD_MCP_COOK_PRESSURE_MSMedian-latency threshold for cook_pressure_warning (default 750)TD_MCP_SHADERTOY_API_KEYShader ingestion / vision + VJ classification. ANTHROPIC_BASE_URL routes the vision pass through an OpenAI-compatible gateway (OpenRouter etc.) — set TD_MCP_VISION_MODEL to that gateway's model idTD_MCP_VISION_MODELVision-pass model (default claude-sonnet-5)TD_MCP_YTDLP_COOKIES_BROWSERBrowser to read YouTube cookies from. Leave unset — tried last, and a rotated cookie jar makes YouTube serve images-onlyTD_MCP_VISION_CONCURRENCYTD_MCP_WIKI_CACHETD_MCP_WHISPER_MODELWhisper model (tiny…large-v3, default base)TD_MCP_YTDLP_FORMAT_SORT-S sort passed to yt-dlp (default none)TD_MCP_RERANK_FETCH_KCandidates pulled before reranking (50) / truncation window (512)TD_MCP_RERANK_MAX_TOKENSCandidates pulled before reranking (50) / truncation window (512)TD_MCP_RERANKEnable reranking globally (default off) / cross-encoder overrideTD_MCP_EMBEDDING_MODELEmbedding model override / LanceDB index locationTool 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
52/52 tools missing one or more hints — td_connect (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); td_disconnect (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); td_status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +49 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 test coverage
35/52 tools referenced in tests (67%)
Write tests that reference each tool by name so every tool has at least one test.
Secrets not written to files
1 secret value written to files
Avoid persisting secrets to disk. Keep them in memory or your secret manager.
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/sashabedard/td-mcp)?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