# Context

> Context is a freemium MCP server for security. OSINT lookups and scam investigations whose every answer links back to its evidence. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** Web, API
- **Website:** https://everydaysecurity.ai
- **Repository:** https://github.com/everydaysecurity-ai/context-osint-mcp
- **MCP Registry name:** ai.everydaysecurity/context
- **Categories:** security
- **Listing updated:** 2026-11-14

## About

Context keeps facts and conclusions apart. An indicator lookup reports which sources saw it, when it was first and last seen, which investigations it appeared in and how it links to other indicators, marking whether each link comes from a verified record or only from co-appearing in a case.

Investigation verdicts are categories such as scam or inconclusive with a confidence band, and they list the evidence behind them: source class, strength, capture time and a graph node to open. Missing evidence is never reported as safe: the verdict falls back to inconclusive, and a scam check answers caution. Truncated lists and failed lookups say so. For crawled sites you can pull the captured DOM, console log, network log, HAR file and screenshot.

It covers domains, URLs, IPs and ASNs, email addresses, phone numbers, crypto wallets and state business records, and can run autonomous investigations of suspicious sites. The server is hosted; Claude Desktop needs a small local bridge. The README describes a free tier with browser sign-in, plus a licence to accept on the Context site. The setup also mentions a separate scam-check server using an agent key.

## Features

- **Evidence with provenance:** Lookups show sources, first and last seen times and linked investigations.
- **Labelled verdicts:** Conclusions carry a category, confidence band and the evidence they rest on.
- **No false all-clear:** Missing evidence yields inconclusive or caution, never safe.
- **Raw capture access:** Pull the DOM, console log, network log, HAR and screenshot of a crawled site.
- **Broad indicator types:** Covers domains, URLs, IPs, ASNs, emails, phones, crypto wallets and business records.
- **Autonomous site investigations:** Runs investigations of suspicious sites and exposes what they collected.

## Good for

- Pivot from a suspicious domain to related infrastructure
- Check a link or phone number before an agent acts on it
- Research a company in state business registries
- Review the captured evidence behind a scam verdict
- Trace a crypto wallet to related indicators

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http context https://context.everydaysecurity.ai/api/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://context.everydaysecurity.ai/api/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "context": {
      "url": "https://context.everydaysecurity.ai/api/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "context": {
      "type": "http",
      "url": "https://context.everydaysecurity.ai/api/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "context": {
      "serverUrl": "https://context.everydaysecurity.ai/api/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "context": {
      "type": "http",
      "url": "https://context.everydaysecurity.ai/api/mcp"
    }
  }
}
```

## FAQ

### Is there a free tier?

Yes. The README says anyone can sign up, with no request form or waiting list, and must accept a free licence on the Context site.

### Does a clean result mean a site is safe?

No. With no strong evidence the verdict is inconclusive and a scam check answers caution, which is explicitly not safe.

### How do I connect?

In Claude Code, run claude mcp add with the HTTP endpoint and sign in in the browser. Claude Desktop needs a small local bridge.

### Do I need to install anything?

For most clients no; the server is hosted.

### Is Context free?

Context has a free plan, with paid plans for more usage or features.

### How do I add Context to Claude Code?

Run this command in your terminal: claude mcp add --transport http context https://context.everydaysecurity.ai/api/mcp

### What are the best alternatives to Context?

The closest alternatives to Context are REA, Agent Roast, Midplane, Leash and Tinplate Edge AI Safety, Security & EU Compliance.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Agent Roast](https://ai-powered.com/mcp/agent-roast): Agent Roast is an open-source MCP server for developer tools.
- [Midplane](https://ai-powered.com/mcp/midplane): Midplane is an open-source MCP server for databases.
- [Leash](https://ai-powered.com/mcp/leash): Leash is a free MCP server for security.
- [Tinplate Edge AI Safety, Security & EU Compliance](https://ai-powered.com/mcp/tinplate-edge-ai-safety-security-and-eu-compliance): Tinplate Edge AI Safety, Security & EU Compliance is a freemium MCP server for security.
- [SecureCloud](https://ai-powered.com/mcp/securecloud): SecureCloud is a free MCP server for security.
- [Eikino](https://ai-powered.com/mcp/eikino): Eikino is a freemium MCP server for security.
- [SynomosAI Governance MCP](https://ai-powered.com/mcp/synomosai-governance-mcp-2): SynomosAI Governance MCP is an open-source MCP server for security.

---
Source: https://ai-powered.com/mcp/context-2
