qsearch
Enables AI agents to perform web searches with full content retrieval and multi-engine provenance, including trust scoring and local corpus persistence, via MCP integration.
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
theYahia
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.
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.
web_searchSearch the web via Brave + SearXNG with multi-engine provenance. Returns results with engines[] field showing which search engines agreed — higher engine_count = higher trust signal.
news_searchSearch recent news with multi-engine attribution. Returns engines[] per result. Defaults to past week.
sweepRun a batch search sweep — accepts label|query lines (same format as brave_sweep.py), fans out queries in parallel, deduplicates results, indexes into corpus, and returns parsed_snippets.md markdown. Free via SearXNG when no Brave key.
index_researchIndex local markdown research files into the qsearch corpus by glob pattern. After indexing, files are searchable via web_search with corpus_first=true. Use to make past research sessions available for cross-project semantic search.
context_searchRetrieve full page content for deep RAG. Returns 2-28 text snippets per source with provenance. Use when depth matters over breadth.
sweep_contextBrave LLM Context endpoint analogue using local Qwen3-600M ($0 cost, GPU only). Fetches HTML, strips boilerplate, extracts facts/numbers/quotes per URL. Use for Phase 4 deep read when Brave Context quota is tight.
academic_searchSearch peer-reviewed papers via arXiv + PubMed + Semantic Scholar in parallel. Free, no auth required. Use for medical research, technical papers, citation chase. Returns deduplicated results across all three sources.
economy_reportMarkdown/JSON report of qsearch costs vs all-Brave baseline. Shows by-backend, by-priority breakdown plus total savings. Filter via from/to ISO dates, sprint_id, topic.
verify_citationCheck whether a cited source actually SUPPORTS a claim — the doesitlie citation-honesty method, live. Fetches the URL (PDF/HTML/headless render, SSRF-guarded), selects the most relevant passages, and an LLM-as-judge at temperature 0 returns a verdict: Supported | Partial | Unsupported (source is sil…
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
PDF.js: Arbitrary JavaScript execution upon opening a malicious PDF
BRAVE_API_KEYBRAVE_BASE_URLCORPUS_FIRSTCRAWL_TIMEOUT_MSDEEPSEEK_API_KEYDOESITLIE_CACHE_DIRDOESITLIE_DEEPSEEK_MODELDOESITLIE_JUDGE_MODELDOESITLIE_JUDGE_NUM_CTXDOESITLIE_JUDGE_PROVIDERDOESITLIE_JUDGE_TIMEOUT_MSLLAMACPP_URLMCP_HOSTMCP_PORTMEILISEARCH_KEYMEILISEARCH_URLMEILI_KEYMEILI_MASTER_KEYMEILI_URLNCBI_API_KEYOBSIDIAN_VAULT_PATHOLLAMA_CLEAN_MODELOllama qwen2.5:7b-instruct (default; configurable via OLLAMA_CLEAN_MODEL)OLLAMA_CLEAN_TIMEOUT_MSOLLAMA_EMBED_DIMOLLAMA_EMBED_MODELOLLAMA_RERANK_TIMEOUT_MSOLLAMA_URLQDRANT_URLQSEARCH_API_KEYQSEARCH_BASELINE_CTX_FRACQSEARCH_BINDQSEARCH_BRAVE_429_RETRIESQSEARCH_BRAVE_RPSQSEARCH_BRAVE_TIMEOUT_MSQSEARCH_CACHE_DBQSEARCH_CORPUS_TIMEOUT_MSQSEARCH_COST_BRAVE_CTXQSEARCH_COST_BRAVE_CTX_CALLQSEARCH_COST_BRAVE_NEWSQSEARCH_COST_BRAVE_WEBQSEARCH_COST_YANDEXQSEARCH_CTX_MAX_SNIPPETSQSEARCH_CTX_MAX_SNIPPETS_PER_URLQSEARCH_CTX_MAX_TOKENSQSEARCH_CTX_MAX_TOKENS_PER_URLQSEARCH_CTX_MAX_URLSQSEARCH_CTX_THRESHOLD_MODEQSEARCH_DATA_ROOTSQSEARCH_HEALTH_REQUIRE_CORPUSQSEARCH_INDEX_CONCURRENCYQSEARCH_IP_ALLOWLISTQSEARCH_LOG_JSONQSEARCH_LOG_LEVELQSEARCH_MAX_BODY_BYTESQSEARCH_MAX_INDEX_FILESQSEARCH_MCP_ALLOWED_ORIGINQSEARCH_MCP_MAX_SESSIONSQSEARCH_QUALITY_AUTHORITYQSEARCH_QUALITY_GATE_ENABLEDQSEARCH_QUALITY_THRESHOLDQSEARCH_QUALITY_TRUST_SATURATIONQSEARCH_QUALITY_WEIGHTSQSEARCH_RATE_LIMITSQSEARCH_RATE_LIMIT_ENABLEDQSEARCH_RATE_WINDOW_MSQSEARCH_RERANK_ENABLEDshippedQSEARCH_RERANK_STAGE2_CONCURRENCYQSEARCH_RERANK_STAGE2_PRIORITIESQSEARCH_RERANK_STAGE2_TOP_INQSEARCH_RERANK_STAGE2_TOP_OUTQSEARCH_RERANK_TOP_N_PER_QUERYQSEARCH_SWEEP_QUERY_TIMEOUT_MSQSEARCH_SWEEP_RETRY_BASE_MSQSEARCH_SWEEP_ZERO_RETRIESQSEARCH_TRUST_DECAY_KQSEARCH_TRUST_FORMULAQSEARCH_TRUST_PROXYQSEARCH_ULTRA_BROAD_MAX_AGE_DAYSQSEARCH_ULTRA_BROAD_MIN_SCOREQSEARCH_ULTRA_BROAD_MIN_TRUSTQSEARCH_URLSEARXNG_URLSEMANTIC_SCHOLAR_API_KEYSWEEP_CONCURRENCYX402_ENABLEDX402_NETWORKX402_PRICE_USDTX402_RECIPIENTYANDEX_BASE_URLYANDEX_FOLDER_IDYANDEX_SEARCH_API_KEYPORTAll four hints declared on every tool
9/9 tools missing one or more hints — web_search (missing: destructiveHint, idempotentHint); news_search (missing: destructiveHint, idempotentHint); sweep (missing: destructiveHint, idempotentHint), +6 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
3/9 tools referenced in tests (33%)
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 — pdfjs-dist@6.0.227 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
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/theyahia/qsearch)?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