mcp-searxng@2.11.0
CAUTIONPublisher claims: "MCP server for SearXNG integration" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Server started and answered tools/list.- Tested
- MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
- Not tested
- what the tools do when called with real credentials
Before you give it your token
- It will ask for
AUTH_PASSWORDAUTH_USERNAMEMCP_HTTP_AUTH_MODEMCP_HTTP_AUTH_TOKENMCP_HTTP_OAUTH_SCOPESConfiguration, not credentials: CACHE_MAX_ENTRIES, CACHE_TTL_MS, FETCH_TIMEOUT_MS, MCP_HTTP_ALLOW_PRIVATE_URLS, MCP_HTTP_ALLOWED_HOSTS, MCP_HTTP_ALLOWED_ORIGINS, MCP_HTTP_EXPOSE_FULL_CONFIG, MCP_HTTP_HARDEN, MCP_HTTP_HOST, MCP_HTTP_PORT, MCP_HTTP_SESSION_IDLE_TTL_MS, MCP_HTTP_SESSION_REQUEST_TIMEOUT_MS, MCP_HTTP_STATELESS, MCP_HTTP_TRUST_PROXY, NODE_EXTRA_CA_CERTS, SEARCH_CACHE_MAX_ENTRIES, SEARCH_CACHE_TTL_MS, SEARCH_HTTP_PROXY, SEARCH_HTTPS_PROXY, SEARCH_USER_AGENT, SEARXNG_DEFAULT_LANGUAGE, SEARXNG_DEFAULT_RESPONSE_FORMAT, SEARXNG_DEFAULT_SAFESEARCH, SEARXNG_FANOUT, SEARXNG_HEALTHCHECK_TIMEOUT_MS, SEARXNG_HTML_FALLBACK, SEARXNG_LITE_TOOLS, SEARXNG_MAX_RESPONSE_BYTES, SEARXNG_MAX_RESULT_CHARS, SEARXNG_MAX_RESULTS, SEARXNG_STARTUP_HEALTHCHECK, SEARXNG_TIMEOUT_MS, SEARXNG_URL, URL_READ_MAX_CHARS, URL_READ_MAX_CONTENT_LENGTH_BYTES- Where it talks to
- no vendor host named in the code
- What the honeypot saw
- no credential files read · no network
- What we could not test
- what the tools do when called with real credentials
Connect it with a scoped credential, under the guard. It asks for AUTH_PASSWORD, AUTH_USERNAME, MCP_HTTP_AUTH_MODE, MCP_HTTP_AUTH_TOKEN, MCP_HTTP_OAUTH_SCOPES and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
What changed since 2.10.1
vet-skills diff mcp-searxng 2.10.1 2.11.0In the sandbox, this version reached for nothing 2.10.1 did not. Compared from the two recorded runs, not from source.
Tool descriptor hashes were not recorded for both runs; renamed or added tools are compared, rewritten descriptions are not.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-17 and scored it 74/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: URL with embedded credentials; Privileged sudo command; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 47 s · 2 scenarios · 0 deviationsStatic findings
…g., http://localhost:8080). For Basic Auth, embed credentials in the URL (e.g., https://user:[email protected]); percent-encode special characters in the username or passwo…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.return 'Run: sudo security add-trusted-cert -d -r trustRoot -k /Library/Keychains/System.keychain /path/to/ca.crt';Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.logMessage(mcpServer, "info", `Processed cached URL: ${url} (${result.length} chars in ${duration}ms)`);Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them."test:e2e": "node --env-file-if-exists=.env.e2e --import tsx __tests__/e2e/run-e2e.ts",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.return 'Run: sudo cp /path/to/ca.crt /usr/local/share/ca-certificates/ && sudo update-ca-certificates';Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."Please provide a valid URL (e.g., http://proxy:8080 or http://user:pass@proxy:8080)");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.<summary>Capability comparison recorded on 2026-07-29</summary> As of 2026-07-29, the capability comparison below reflects the official [Brave MCP](https://githFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
Not checked against OSV yet; the weekly check has not reached this version.
What would make this Verified
6 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim ihor-sokoliuk: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- URL with embedded credentials≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.