Web ResearcherSAFE
Give your AI assistant real web search, full-page reading, and multi-source research with citations that are never fabricated.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
web-researcher-mcp
Your AI research assistant that cites real sources and stays honest.
Search the entire web or narrow it down to just the sites you trust; medical journals, court databases, news outlets, academic papers. Analyze the full source, not just snippets. Links that work, citations you can trust, no made up closed garden pre-synthesized results.
⭐ If you're tired of AI making things up, and web-researcher-mcp helps you, give us a star ⭐ — it helps more teams discover the project.
7d1fd8a48f8bOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add web-researcher-mcp:1.49.4 --env GOOGLE_CUSTOM_SEARCH_API_KEY=${GOOGLE_CUSTOM_SEARCH_API_KEY} --env BRAVE_API_KEY=${BRAVE_API_KEY} --env SERPER_API_KEY=${SERPER_API_KEY} --env SEARCHAPI_API_KEY=${SEARCHAPI_API_KEY} -- docker run -i --rm ghcr.io/zoharbabin/web-researcher-mcp:1.49.4:Noneclaude mcp add web-researcher-mcp:1.49.4 --env GOOGLE_CUSTOM_SEARCH_API_KEY=${GOOGLE_CUSTOM_SEARCH_API_KEY} --env BRAVE_API_KEY=${BRAVE_API_KEY} --env SERPER_API_KEY=${SERPER_API_KEY} --env SEARCHAPI_API_KEY=${SEARCHAPI_API_KEY} -- docker run -i --rm docker.io/zoharbabin/web-researcher-mcp:1.49.4:NoneTrust audit
SAFEgrade C · trust 73/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (7 observation(s))
- Network
- declared (6 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (25)
print(token)
.gitguardian.yaml
.golangci.yml
.goreleaser.yml
.SRCINFO
# and the research_panel divergence eval (`TestResearchPanelEvalAccuracy`).
return hashlib.sha1(canonical.encode()).hexdigest()[:12]
mkdir -p ~/.ssh
printf '%s\n' "$AUR_SSH_KEY" > ~/.ssh/aur_key
chmod 600 ~/.ssh/aur_key
ssh-keyscan -t ed25519 aur.archlinux.org >> ~/.ssh/known_hosts 2>/dev/null
rm -f ~/.ssh/aur_key
_, _, _ = p.fetchGitHubRepoStats(context.Background(), "../../etc", "passwd#?")
if err := registry.LoadFromDir("../../lenses"); err != nil {t.Fatalf("LoadFromDir(../../lenses): %v", err)if err := registry.LoadFromDir("../../lenses"); err != nil {t.Fatalf("LoadFromDir(../../lenses): %v", err)- `metadata.google.internal` (GCP IMDS)
- `169.254.169.254` (AWS / Azure / GCP / DigitalOcean / OpenStack link-local)
"169.254.169.254",
ip := net.ParseIP("169.254.169.254")t.Error("isPrivateIP(169.254.169.254) = false, want true (cloud metadata endpoint)")withJinaEndpoint(t, "http://127.0.0.1:1/")
wrapperHTML := iframeShellHTML("Wrapper", "Above-the-fold blurb.", "http://169.254.169.254/latest/meta-data/")innerPort := strings.TrimPrefix(inner.URL, "http://127.0.0.1:")
Gates applied: no_behavioural_pass.
7d1fd8a48f8bfull audit observations/trust-audit/mcp-server/zoharbabin__web-researcher.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 7d1fd8a48f8b | SAFE | C | 73 | first audit |
Questions
What is the Web Researcher MCP server?
Give your AI assistant real web search, full-page reading, and multi-source research with citations that are never fabricated.
Is Web Researcher safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it C (73/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Web Researcher need?
It reads BRAVE_API_KEY, EXA_API_KEY, GOOGLE_CUSTOM_SEARCH_API_KEY, SEARCHAPI_API_KEY, SERPER_API_KEY, TAVILY_API_KEY and XQUIK_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Web Researcher run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as smithery-cli-pin.
How current is this page?
The grade is for one exact copy of the source (7d1fd8a48f8b), read on 2026-10-08. The repository is watched and re-audited when it changes.