Caution. Specific findings reduced this grade. They are listed on the page. 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
mhalder
Source: modelscope · also listed on github_topic
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.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
When Vitest UI server is listening, arbitrary file can be read and executed
Picomatch has a ReDoS vulnerability via extglob quantifiers
Picomatch: Method Injection in POSIX Character Classes causes incorrect Glob Matching
CODE_BATCH_SIZENumber of chunks to embed in one batch 100CODE_CHUNK_OVERLAPOverlap between chunks in characters 300CODE_CHUNK_SIZEMaximum chunk size in characters 2500CODE_ENABLE_ASTEnable AST-aware chunking (tree-sitter) trueCODE_ENABLE_HYBRIDCODE_SEARCH_LIMITCOHERE_API_KEYCohere API key -EMBEDDING_BASE_URLCustom API URL Provider-specificEMBEDDING_DIMENSIONSEMBEDDING_MAX_REQUESTS_PER_MINUTERate limit Provider-specificEMBEDDING_MODELModel name Provider-specificEMBEDDING_PROVIDER"": "openai", // or "cohere", "voyage"EMBEDDING_RETRY_ATTEMPTSRetry count 3EMBEDDING_RETRY_DELAYInitial retry delay (ms) 1000GIT_BATCH_RETRY_ATTEMPTSRetry attempts for failed batches 3GIT_BATCH_SIZENumber of chunks to embed in one batch 100GIT_ENABLE_HYBRIDEnable hybrid search with sparse vectors trueGIT_INCLUDE_DIFFInclude truncated diff in chunks trueGIT_INCLUDE_FILESInclude changed file list in chunks trueGIT_MAX_CHUNK_SIZEMaximum characters per chunk 3000GIT_MAX_COMMITSMaximum commits to index per run 5000GIT_MAX_DIFF_SIZEMaximum diff size in bytes per commit 5000GIT_SEARCH_LIMITDefault search result limit 10GIT_TIMEOUTTimeout for git commands (ms) 300000HTTP_PORTTRANSPORT_MODE=http =3000 node build/index.jsHTTP_REQUEST_TIMEOUT_MSRequest timeout for HTTP transport (ms) 300000LOG_LEVELLogging level (fatal/error/warn/info/debug/trace/silent) infoOPENAI_API_KEY"": "sk-...", // provider-specific API keyPROMPTS_CONFIG_FILENote: By default, the server looks for prompts.json in the project root directory. If the file exists, prompts are automatically loaded. You can specify a custom path using the environment variable.QDRANT_API_KEYFor Qdrant Cloud or secured instances, add --env =your-key or set in env config.QDRANT_URL"": "http://localhost:6333"TRANSPORT_MODEhttp HTTP_PORT=3000 node build/index.jsVOYAGE_API_KEYVoyage AI API key -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
20/20 tools missing one or more hints — index_codebase (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); search_code (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); reindex_changes (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +17 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
11/20 tools referenced in tests (55%)
Write tests that reference each tool by name so every tool has at least one test.
Production dependencies are patched
0 critical, 1 high severity in production deps — picomatch@4.0.3 (high), picomatch@4.0.3 (low)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dev dependencies
1 critical/high in dev-only deps (does not ship to users)
Upgrade dev dependencies when convenient.
Dependency freshness
1/18 production deps stale: bottleneck@2023-02-22 (3.5y)
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/mhalder-qdrant-mcp-server-wg2gzc)?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