CustomCAUTION
MCP server for scraping LinkedIn, Facebook, Instagram profiles and Google search.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Social Media Scraper - Custom MCP Server
A comprehensive Model Context Protocol (MCP) server that provides social media scraping capabilities for LinkedIn, Facebook, Instagram, and Google search functionality.
What is MCP?
[Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction) is an open standard that enables AI assistants to securely connect with external data sources and tools. MCP servers act as bridges between AI models and various services, allowing for enhanced capabilities like real-time data access, API integrations, and custom tool execution.
Features
This server exposes the following tools for an AI assistant to use:
- LinkedIn Profile Scraping: Extract personal and company profile data
- Facebook Profile Scraping: Fetch public profile information
- Instagram Profile Scraping: Get profile data and basic information
- Google Search: Perform web searches using Google Serper API
Installation
Step 1: Adding MCP to your Python project
We recommend using [uv](https://docs.ast
437fc0efed07OBSERVED · 2026-10-07Connect
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 custom-mcp-server --env RAPIDAPI_KEY=${RAPIDAPI_KEY} --env SERPER_API_KEY=${SERPER_API_KEY} -- uvx custom-mcp-server{
"mcpServers": {
"custom-mcp-server": {
"command": "uvx",
"args": [
"custom-mcp-server"
],
"env": {
"RAPIDAPI_KEY": "${RAPIDAPI_KEY}",
"SERPER_API_KEY": "${SERPER_API_KEY}"
}
}
}
}Exposed tools (5)
5 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_company_profile | read | Fetch full LinkedIn company page data for a given URL. |
get_facebook_profile | read | Fetch Facebook profile data for a given public URL. |
get_instagram_profile | read | Fetch Instagram profile data for a given public username or URL. |
get_personal_profile | read | Fetch full LinkedIn personal profile data for a given URL. |
scrape_website | read | Fetch search results for a given query using Google Serper API. |
Trust audit
CAUTIONgrade B · trust 83/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | FAIL |
| 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 (5 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- found
Findings (3)
.env
.env
Gates applied: no_behavioural_pass, no_license.
437fc0efed07full audit observations/trust-audit/mcp-server/sharan-kumar-r__custom-1.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 |
|---|---|---|---|---|---|
| 2026-10-07 | 437fc0efed07 | CAUTION | B | 83 | first audit |
Questions
What is the Custom MCP server?
MCP server for scraping LinkedIn, Facebook, Instagram profiles and Google search.
What tools does Custom expose?
5 in total: 5 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Custom safe to connect to an agent?
With care. The audit graded it B (83/100) and found 3 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does Custom need?
It reads RAPIDAPI_KEY and 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 Custom run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as custom-mcp-server.
How current is this page?
The grade is for one exact copy of the source (437fc0efed07), read on 2026-10-07. The repository is watched and re-audited when it changes.