Security Intel MCP server
Commit Oct 24, 2026Enables AI agents to perform CVE lookups, check exploit probabilities via EPSS, and audit dependency manifests using NVD, CISA KEV, and OSV data.
Also known as datakoot/security-intel-mcp, security-intel-mcp
- Stars
- 0
- Tools
- 5
- Downloads, 30 days
- —
- Latest version
- 2.1.0
- Last commit
- Oct 24, 2026
- License
- MIT
What is Security Intel MCP?
Security Intel enables AI agents to perform CVE lookups, check exploit probabilities via EPSS, and audit dependency manifests using NVD, CISA KEV, and OSV data. It exposes 5 tools, such as cve_lookup, known_exploited, epss_score.
Summary generated from the project's README
About Security Intel MCP server
Security Intel MCP provides vulnerability intelligence directly to AI agents through a remote MCP server. Developers can connect their clients to the hosted endpoint at security.datakoot.com without needing to manage API keys or sign up for accounts. This server aggregates data from several major security sources to help agents assess risks during their workflows.
The toolset includes cve_lookup for retrieving NVD summaries, CVSS scores, and CWE details. It integrates CISA KEV data to identify actively exploited vulnerabilities and uses FIRST EPSS to provide exploit probability scores between 0 and 1. For software supply chain security, the package_vulnerabilities and audit_dependencies tools utilize OSV.dev data to check specific versions or entire package.json files for known issues.
What you can do with it
- 1Assess specific CVE risksAsk an agent to determine if a specific CVE identifier represents a significant threat based on severity and exploit probability.
- 2Identify active threatsRequest a list of vulnerabilities that are currently being exploited in the wild by filtering through the CISA KEV catalog.
- 3Perform dependency auditsHave an AI agent scan a project's dependency manifest to find known vulnerabilities before deployment.
- 4Calculate exploit probabilityDetermine the statistical chance that a vulnerability will be exploited within the next thirty days using EPSS scores.
Written from the project's README. Every use case is checked against a quote from it.
How to install Security Intel MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Security Intel MCP in Claude Code
$ claude mcp add --transport http security-intel-mcp https://security.datakoot.com/mcpInstall Security Intel MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"security-intel-mcp": {
"url": "https://security.datakoot.com/mcp"
}
}
}Install Security Intel MCP in VS Code
.vscode/mcp.json
{
"servers": {
"security-intel-mcp": {
"type": "http",
"url": "https://security.datakoot.com/mcp"
}
}
}Install Security Intel MCP in VS Code CLI
$ code --add-mcp '{"name":"security-intel-mcp","type":"http","url":"https://security.datakoot.com/mcp"}'Install Security Intel MCP in Codex
$ codex mcp add security-intel-mcp --url https://security.datakoot.com/mcpInstall Security Intel MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.security-intel-mcp] url = "https://security.datakoot.com/mcp"
Install Security Intel MCP in Gemini CLI
$ gemini mcp add -s user --transport http security-intel-mcp https://security.datakoot.com/mcpInstall Security Intel MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"security-intel-mcp": {
"url": "https://security.datakoot.com/mcp",
"type": "http"
}
}
}Security Intel MCP tools 5
Detected from the READMEcve_lookupknown_exploitedepss_scorepackage_vulnerabilitiesaudit_dependencies
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachabledatakoot/security-intel-mcp is public and reachablegithub.com/datakoot/security-intel-mcp ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-24github.com/datakoot/security-intel-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model5 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-06-18 in 95 msPass
README
View on GitHubSecurity Intel MCP — by Datakoot
Vulnerability intelligence for AI agents — as MCP tools your agent can call mid-task. One keyless call fuses NVD, CISA KEV and FIRST EPSS. No API keys.
Tools
| Tool | What it does | Source |
|---|---|---|
cve_lookup |
CVE summary: description, CVSS score & severity, CWE, references, plus whether it is actively exploited (CISA KEV) and its exploit probability (EPSS) | NVD (NIST), CISA KEV, FIRST EPSS |
known_exploited |
Is a CVE on CISA's Known Exploited Vulnerabilities catalog? Or list the newest exploited CVEs (filter by vendor, product or ransomware use) | CISA KEV |
epss_score |
Exploit probability (0–1) and percentile for one or many CVEs: the chance each is exploited in the next 30 days | FIRST EPSS |
package_vulnerabilities |
Known vulnerabilities for a package/version | OSV.dev |
audit_dependencies |
Audit a whole package.json (or dependency list) in one call | OSV.dev |
No API keys required for any tool.
Quick start
claude mcp add --transport http security-intel https://security.datakoot.com/mcp
Or point any MCP client at https://security.datakoot.com/mcp.
Try it in 10 seconds — no key, no signup
Paste this into a terminal:
curl -s https://security.datakoot.com/mcp \
-H 'content-type: application/json' \
-H 'accept: application/json, text/event-stream' \
-d '{"jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": {"name": "cve_lookup", "arguments": {"cve_id": "CVE-2021-44228"}}}'
You get Log4Shell (CVE-2021-44228) in one answer: the NVD record (severity, CVSS vector, references), its CISA KEV entry (exploited in the wild, used in ransomware) and its EPSS exploit probability. No API key, nothing to sign up for.
Or point any MCP client at the URL and just ask your agent, in plain language:
- "Is CVE-2021-44228 something I need to worry about?"
- "Which of these CVEs is actually being exploited right now?"
- "Audit my package.json for known vulnerabilities before I deploy."
Data & attribution
Vulnerability data comes from the National Vulnerability Database (NIST — US public domain), CISA's Known Exploited Vulnerabilities catalog (US public domain), FIRST EPSS and OSV.dev (CC-BY 4.0), the same open sources used by scanners like Trivy and Grype.
Part of Datakoot — keyless intelligence APIs for AI agents.
Security Intel MCP questions
How do I add Security Intel MCP to Claude Code?
Run claude mcp add --transport http security-intel-mcp https://security.datakoot.com/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Security Intel MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Security Intel MCP provide?
It exposes 5 tools, including cve_lookup, known_exploited, epss_score, package_vulnerabilities, audit_dependencies.
Do I need an API key to use this?
No, no API keys are required for any of the tools provided.
Can I audit an entire dependency list at once?
Yes, you can audit a whole package.json or a dependency list in a single call.
What sources of vulnerability data are used?
The server uses data from the National Vulnerability Database (NVD), CISA's Known Exploited Vulnerabilities catalog, FIRST EPSS, and OSV.dev.