MCP-Sentinel
A safety guard for AI assistants that inspects actions (file reads, queries, etc.) and classifies them as SAFE, SUSPICIOUS, or BLOCK with explanations, using both known-attack patterns and behavior-based zero-day detection.
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
RoshiniMlakshmana
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
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.
BASELINE_PATHNO_COLORMODEL_PROVIDEROPENAI_API_KEYUsing OpenAI: copy .env.example to .env and paste your into it.OLLAMA_URLOLLAMA_CHAT_MODELOPENAI_CHAT_MODELCHROMA_PATHCOLLECTIONQUARANTINE_PATHSTATE_PATHMAX_AGE_DAYSATLAS_URLOPEN_IOC_FEED_META_URLTHREATFOX_API_URLTHREATFOX_API_KEYEMBEDDING_PROVIDERFree, on your own computer: install [Ollama](https://ollama.com), then in a file called .env set =ollama.OLLAMA_EMBEDDING_MODELOPENAI_EMBEDDING_MODELPENDING_REMEDIATIONS_PATHFLOW_IDNOTIFY_ON3. Fully quit and reopen Claude Desktop. Now you can ask Claude to check any action, and you'll get a desktop pop-up if something's dangerous (turn alerts on with =block,suspicious).Tool 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
5/5 tools missing one or more hints — scan_tool_call (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); explain_verdict (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); approve_remediation (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +2 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
4/5 tool handlers declare input schemas (80%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
3/5 tool handlers wrap calls in try/catch (60%)
Wrap each tool handler body in try/catch and return a structured error response.
Tests exist
No test files found
Add tests that exercise each declared tool.
No access to sensitive paths
Reads sensitive paths: ~/.config/Claude/claude_desktop_config.json
Remove reads of sensitive system paths. If you genuinely need them, document why in the README.
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/roshinimlakshmana/mcp-vulnerability-detection)?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