Agent Search MCP Server
agent-search-mcp
npm
v3.2.1
Published by lennney — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
Free multi-engine web search across seven engines (DuckDuckGo, Sogou, Bing, Baidu, Brave, Tavily, Exa) with waterfall progressive search, multi-source verification, and content enrichment; no API keys needed.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 7 = 93. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 14
high Shell/command execution in server code (dist/aggregation/semantic.js)MTC-SRC-002
In the server's implementation (`dist/aggregation/semantic.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: import { spawn } from 'child_process'; import { createInterface } from 'readline'; import { resolve } from 'path'; impo
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/aggregation/semantic.js
high Shell/command execution in server code (dist/infrastructure/doctor.js)MTC-SRC-002
In the server's implementation (`dist/infrastructure/doctor.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: spawnSync } from 'node:child_process'; import { engines, freeEngines, optionalEngineCredentialEnvironment, } from '../e
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/infrastructure/doctor.js
medium Untrusted input can drive an external actionMTC-FLOW-005
Untrusted-input tools ([fetch_github_readme, fetch_csdn_article, fetch_juejin_article, free_search]) co-exist with external-action tools ([free_extract]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.
Evidence: untrusted [fetch_github_readme, fetch_csdn_article, fetch_juejin_article, free_search] → sinks [free_extract]
Fix: Require confirmation for state-changing/egress actions triggered after processing untrusted content.
Location: flow fetch_github_readme → free_extract
medium Hardcoded egress to an external endpoint (dist/aggregation/enricher.js)MTC-SRC-003
In the server's implementation (`dist/aggregation/enricher.js:30`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const res = await fetch(`https://r.jina.ai/${result.url}`, { headers: { Accept: "text/markdown" },
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/aggregation/enricher.js
medium Hardcoded egress to an external endpoint (dist/cli.js)MTC-SRC-003
In the server's implementation (`dist/cli.js:152`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const res = await fetch(`https://r.jina.ai/${args.url}`, { headers: { 'Accept': 'text/markdown' },
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/cli.js
medium Hardcoded egress to an external endpoint (dist/engines/exa.js)MTC-SRC-003
In the server's implementation (`dist/engines/exa.js:12`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const response = await fetch('https://api.exa.ai/search', { method: 'POST', headers: {
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/engines/exa.js
medium Hardcoded egress to an external endpoint (dist/engines/startpage.js)MTC-SRC-003
In the server's implementation (`dist/engines/startpage.js:11`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const res = await fetch('https://www.startpage.com/', { signal: withTimeout(options?.signal, 5000),
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/engines/startpage.js
medium Hardcoded egress to an external endpoint (dist/engines/tavily.js)MTC-SRC-003
In the server's implementation (`dist/engines/tavily.js:29`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const res = await fetch('https://api.tavily.com/search', { method: 'POST', headers: { 'Con
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/engines/tavily.js
medium Hardcoded egress to an external endpoint (dist/infrastructure/version-check.js)MTC-SRC-003
In the server's implementation (`dist/infrastructure/version-check.js:16`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const res = await fetch('https://registry.npmjs.org/agent-search-mcp/latest', { signal: controller.sig
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/infrastructure/version-check.js
medium Hardcoded egress to an external endpoint (dist/tools/free-extract.js)MTC-SRC-003
In the server's implementation (`dist/tools/free-extract.js:31`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const res = await fetch(`https://r.jina.ai/${url}`, { headers: { 'Accept': 'text/markdown' },
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/tools/free-extract.js
medium Unconstrained URL/host parameter "url" on "fetch_github_readme"MTC-CAP-007
Tool "fetch_github_readme" takes a URL/host parameter "url" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).
Fix: Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.
Location: tool fetch_github_readme · inputSchema.properties.url
medium Unconstrained URL/host parameter "url" on "fetch_csdn_article"MTC-CAP-007
Tool "fetch_csdn_article" takes a URL/host parameter "url" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).
Fix: Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.
Location: tool fetch_csdn_article · inputSchema.properties.url
medium Unconstrained URL/host parameter "url" on "fetch_juejin_article"MTC-CAP-007
Tool "fetch_juejin_article" takes a URL/host parameter "url" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).
Fix: Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.
Location: tool fetch_juejin_article · inputSchema.properties.url
medium Unconstrained URL/host parameter "url" on "free_extract"MTC-CAP-007
Tool "free_extract" takes a URL/host parameter "url" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).
Fix: Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.
Location: tool free_extract · inputSchema.properties.url
Tools 7
Each tool and what it can reach — statically extracted from the published source.
fetch_csdn_articleingests untrusted inputfetch_github_readmeingests untrusted inputfetch_juejin_articleingests untrusted inputfree_extractnetwork egressfree_searchingests untrusted inputfree_search_advancedno sensitive capabilitysearch_with_synthesisno sensitive capability
Toxic flows 1
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (7 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 6
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v3.2.1 latest |
A 93/100 | 14 | 1.13.0 | 2026-08-25 |
v3.2.0 |
A 93/100 | 14 | 1.12.1 | 2026-07-28 |
v3.1.3 |
A 93/100 | 17 | 1.12.1 | 2026-07-27 |
v3.1.2 |
A 100/100 | 9 | 1.5.0 | 2026-07-22 |
v3.1.0 |
A 100/100 | 9 | 1.4.0 | 2026-07-22 |
Show 1 more version ↓
v3.0.1 |
F 51/100 | 15 | 1.3.1 | 2026-07-21 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan agent-search-mcp --onlineMore in Web, Search & Scraping
Agent IP: MCP server with patents search tools
MCP server for searching the Agent Almanac — the public catalog of 9,000+ Model Context Protocol servers. Find, install, and discover MCP servers from inside Claude Desktop, Cursor, Continue, Zed, or any MCP-aware agent.
Search agents & MCP servers by capability, with daily-observed pricing, liveness and market data.
Verified merchants accepting agentic payments on Lightning/L402/BOLT12/USDT — search, verify, pay.
Airframe MCP Client - Connect agents to Airframe's product intelligence
Amazon product search demand over time, with growth for any keyword. Free key at trendsmcp.ai