Skip to content
MCP server

Midkernel Threat Intel

Free public-source threat intelligence feeds over MCP, plus hosted repo security scans

Install
Pricing
Freemium
Platforms
API
Runs
Remotely
Version
0.5.0
Listing updated
1 day ago

About Midkernel Threat Intel

Midkernel Threat Intel is a freemium MCP server for security. It runs as a hosted remote server, so there is nothing to install locally.

Midkernel offers two things on one platform. The no-login Threat Intel URL exposes six read-only tools over public-source evidence: listing sources and classes, a daily report, latest changes since a timestamp, trend comparisons and a record lookup that joins known-exploited status via CVE identifiers. It never touches your repositories or data.

The daily report picks findings from the previous complete UTC day and attaches citations, date basis and coverage caveats. Midkernel states the ordering reflects attention priority, not severity or exploit probability, and that an empty result does not prove there were no threats. Limits are 30 requests and 6 tool calls per minute per IP.

A second OAuth PKCE connection adds Scan, where an agent links a GitHub repository through a read-only app, starts a hosted review and fetches findings. Runs cost fixed credits (10, 25 or 50 by tier) and start_run debits immediately with no confirmation step.

Install

Run in a terminal

claude mcp add --transport http threat-intel https://www.midkernel.com/security/app/mcp/threat-intel

Add to Settings → Connectors → Add custom connector

https://www.midkernel.com/security/app/mcp/threat-intel
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "threat-intel": {
      "url": "https://www.midkernel.com/security/app/mcp/threat-intel"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "threat-intel": {
      "type": "http",
      "url": "https://www.midkernel.com/security/app/mcp/threat-intel"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "threat-intel": {
      "serverUrl": "https://www.midkernel.com/security/app/mcp/threat-intel"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "threat-intel": {
      "type": "http",
      "url": "https://www.midkernel.com/security/app/mcp/threat-intel"
    }
  }
}

Tools this server provides (10)

Taken from the project documentation; the running server may differ.

ti_sources
List configured public source IDs and metadata.
ti_classes
List supported class IDs and taxonomy version.
ti_daily_report
Prioritized findings for the previous complete UTC day.
ti_latest
New or changed public-source threats since a timestamp.
ti_trends
Compare evidence counts across equal UTC windows.
ti_get
Fetch a threat record with evidence and KEV status.
connect_repo
Confirm the read-only GitHub App on chosen repositories.
list_playbooks
List review workflows you can run.
start_run
Start a hosted Scan and debit credits.
fetch_run
Poll a run and fetch its report and findings.

What it does

Daily threat report
Prioritized findings for the previous UTC day with citations and caveats.
Incremental feed
Reads new or changed threats since a timestamp, with class and source filters.
Trend comparison
Compares evidence counts across equal date windows.
KEV matching
Joins known-exploited status through CVE identifiers.
Hosted Scan
Starts repository reviews and fetches reports through OAuth.
Scoped access
Tools are limited to the scopes you approve.

Good for

  • Get a morning threat briefing in an assistant
  • Poll for new exploited vulnerabilities since yesterday
  • Track which threat classes are rising
  • Run an agent-driven review of a GitHub repository

Pricing

Freemium

Threat Intel free; Scan runs use credits (10, 25 or 50 per run)

Prices change. Check midkernel.com before you buy.

Midkernel Threat Intel FAQ

Do I need an account for Threat Intel?

No. Add the URL with no authentication; no key or credits are needed.

What are the rate limits?

30 requests and 6 tool calls a minute per public IP.

Does Scan cost money?

Runs use credits; start_run debits them at once.

Does Threat Intel read my code?

No, it only reads Midkernel's public-source evidence.

Is Midkernel Threat Intel free?

Midkernel Threat Intel has a free plan, with paid plans for more usage or features.

How do I add Midkernel Threat Intel to Claude Code?

Run this command in your terminal: claude mcp add --transport http threat-intel https://www.midkernel.com/security/app/mcp/threat-intel

What are the best alternatives to Midkernel Threat Intel?

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

Alternatives to Midkernel Threat Intel

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Agent Roast

    MCP server

    Offline review that flags agent changes which weaken tests, assertions or CI

    Runs locally
    • Open source
    • 4 Hacker News points
    • Developer tools
  3. Midplane

    MCP server

    Postgres gateway for AI agents with table grants, column masking and approval for writes

    Runs locally
    • Open source
    • 5 GitHub stars
    • Databases
  4. Leash

    MCP server

    Review what your AI touched, approve risky actions and undo supported changes

    • 1 tool
    • Remote
    • Free
    • 1 GitHub star
    • Security
  5. SecureCloud

    MCP server

    SentinelOne and IT security catalog, prices, quotes and checkout links for Israel

    • 7 tools
    • Remote
    • Free
    • Security