urd
A self hosted library of information. Made for AI-Human collaboration. Fully vibe coded.
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
OleBinders
Source: github_repo_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. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
searchSearch the library. Returns metadata only (title, summary, tags, score) for the top matches — never full entry bodies. Follow up with `read` for any entry you actually need in full.
readRead one entry in full: metadata, citations, and the markdown body. Only call this for entries you've identified via `search` or the map — don't loop this over every id to reconstruct the whole library.
writeCreate or update an entry. Writes the markdown file (the source of truth), commits it to the content repo, and upserts the search index — all in the same call. Every entry should carry at least one citation — this is the library's main defense against confident-sounding drift. A body claim can cite …
auditRun a read-only quality audit of the library: entries not updated in 6+ months, citations whose URL no longer resolves, and pairs of highly similar entries that aren't cross-linked (candidates for a human to check for overlap or contradiction — this only surfaces candidate pairs, it never judges whe…
CONTENT_DIRMCP_AUTH_TOKENit as in .env before bringing the stack up — bothMCP_AUTH_MODEmcp_server requires a bearer token by default (=token, theMCP_BEHIND_TLS_PROXYtrue once TLS is actually in place in front of it toCONTENT_BACKUP_REMOTErestarts, but not against loss of the host itself.EMBEDDING_PROVIDER(docker-compose.yml, default fastembed) picks theOLLAMA_URLOLLAMA_EMBED_MODELVOYAGE_API_KEYVOYAGE_MODELOPENAI_API_KEYOPENAI_EMBED_MODELWEB_SHARING_MODEport 8080 sees the whole library, drafts included.DATABASE_URLTool 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 — search (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); read (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); write (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.
Tests exist
No test files found
Add tests that exercise each declared tool.
No eval / new Function
2 eval() or new Function() calls — dynamic code execution
Replace eval / Function with explicit parsing or safer alternatives.
Readable source code
1 file are minified or bundled, which is usually build output rather than concealment
Ship unminified, readable source.
Secrets stay with their owner
3 secrets sent to a request target we could not resolve (MCP_AUTH_TOKEN → dynamic, MCP_AUTH_TOKEN → dynamic) — often a configured endpoint, not necessarily third-party
Audit where credentials are sent. A NOTION_TOKEN should only reach api.notion.com — never a third-party host.
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/olebinders/urd)?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