Serper Search and ScrapeSAFE
Serper MCP Server supporting search and webpage scraping
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://smithery.ai/server/@marcopesani/mcp-server-serper)
A TypeScript-based MCP server that provides web search and webpage scraping capabilities using the Serper API. This server integrates with Claude Desktop to enable powerful web search and content extraction features.
Features
Tools
google_search- Perform web searches via Serper API- Rich search results including organic results, knowledge graph, "people also ask", and related searches
- Supports region and language targeting
- Optional parameters for location, pagination, time filters, and autocorrection
- Supports advanced search operators:
site: Limit results to specific domainfiletype: Limit to specific file types (e.g., 'pdf', 'doc')inurl: Search for pages with word in URLintitle: Search for pages with word in titlerelated: Find similar websitescache: View Google's cached version of a specific URLbefore: Date before in YYYY-MM-DD formatafter: Date after in YYYY-MM-DD formatexact: Exact phrase matchexclude: Terms to exclude from search resultsor: Alternative terms (OR operator)
scrape- Extract content from web pages- Get plain text and optional markdown content
- Includes JSON-LD and head metadata
- Preserves document structure
Requirements
- Node.js >= 18
- Serper API key (set as
SERPER_API_KEYenvironment variable)
Development
Install dependencies:
npm install
Build the server:
npm run build
For development with auto-rebuild:
npm run watch
Run tests:
npm test # Run all tests npm run test:wa
008ca8ee64b2OBSERVED · 2026-10-06Connect
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 serper-search-scrape-mcp-server --env SERPER_API_KEY=${SERPER_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"serper-search-scrape-mcp-server": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"SERPER_API_KEY": "${SERPER_API_KEY}"
}
}
}
}Exposed tools (15)
15 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
claim | read | Claim to verify |
compare-sources | read | Compare information from multiple sources on a topic |
content_type | read | Type of content (docs, tutorials, issues) |
depth | read | Research depth (basic or detailed) |
fact-check | read | Verify a claim across multiple authoritative sources |
focus_areas | read | Specific areas to focus research on |
google_search | read | Tool to perform web searches via Serper API and retrieve rich results. It is able to retrieve organic search results, people also ask, related searches, and knowledge graph. |
min_sources | read | Minimum number of sources to compare |
query | read | Technical query to search for |
research-topic | read | Guide comprehensive research on a topic with structured results |
scrape | read | Tool to scrape a webpage and retrieve the text and, optionally, the markdown content. It will retrieve also the JSON-LD metadata and the head metadata. |
tech_stack | read | Relevant technologies to focus on |
technical-search | read | Focused technical and programming search |
thoroughness | read | Verification thoroughness (quick or thorough) |
topic | read | Main topic to research |
Trust audit
SAFEgrade B · trust 89/100 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 | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
dotenv, node-fetch, @types/jest, @types/node, @types/node-fetch, jest, ts-jest, typescript
Gates applied: no_behavioural_pass.
008ca8ee64b2full audit observations/trust-audit/mcp-server/marcopesani__serper-search-and-scrape.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 |
|---|---|---|---|---|---|
| 2026-10-06 | 008ca8ee64b2 | SAFE | B | 89 | first audit |
Questions
What is the Serper Search and Scrape MCP server?
Serper MCP Server supporting search and webpage scraping
What tools does Serper Search and Scrape expose?
15 in total: 15 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Serper Search and Scrape safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). 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 Serper Search and Scrape need?
It reads SERPER_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 Serper Search and Scrape run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as serper-search-scrape-mcp-server at 0.2.0.
How current is this page?
The grade is for one exact copy of the source (008ca8ee64b2), read on 2026-10-06. The repository is watched and re-audited when it changes.