Cve SearchSAFE
A Model Context Protocol (MCP) server for querying the CVE-Search API
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://mseep.ai/app/roadwy-cve-search-mcp)
CVE-Search MCP Server
A Model Context Protocol (MCP) server for querying the CVE-Search API. This server provides comprehensive access to CVE-Search, browse vendor and product、get CVE per CVE-ID、get the last updated CVEs.
Requirements
- python 3.10+
- uv
- Cline、Roo Code etc
Tools
- To get a JSON with all the vendors
- To get a JSON with all the products associated to a vendor
- To get a JSON with all the vulnerabilities per vendor and a specific product
- To get a JSON of a specific CVE ID
- To get a JSON of the last 30 CVEs including CAPEC, CWE and CPE expansions
- To get more information about the current databases in use and when it was updated
Quick Start
- Git clone this repository
git clone https://github.com/roadwy/cve-search_mcp.git
- Install the dependencies
cd cve-search_mcp uv sync
3.Add to your mcp client(vscode with cline/roo code) configuration file, modify the "YOU_CVE_SEARCH_MCP_DIR_PATH" as you self dir.
"cve-search_mcp": {
"command": "uv",
"args": [
"--directory",
"YOU_CVE_SEARCH_MCP_DIR_PATH",
"run",
"main.py"
],
"disabled": false,
"autoApprove": []
}Reference
https://github.com/cve-search/cve-search
12294fc84312OBSERVED · 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.
claude mcp add cve-search-mcp -- uvx cve-search-mcp
{
"mcpServers": {
"cve-search-mcp": {
"command": "uvx",
"args": [
"cve-search-mcp"
]
}
}
}Exposed tools (6)
5 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
vul_cve_search | read | |
vul_db_update_status | write | |
vul_last_cves | read | |
vul_vendor_product_cve | read | |
vul_vendor_products | read | |
vul_vendors | read |
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
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
12294fc84312full audit observations/trust-audit/mcp-server/roadwy__cve-search.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 | 12294fc84312 | SAFE | B | 89 | first audit |
Questions
What is the Cve Search MCP server?
A Model Context Protocol (MCP) server for querying the CVE-Search API
What tools does Cve Search expose?
6 in total: 5 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Cve Search 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 Cve Search need?
No credential environment variables were found in its source, so it appears to need none.
How does Cve Search run?
It speaks sse and stdio, so it runs as a local process your client starts. It is published on PyPI as cve-search-mcp.
How current is this page?
The grade is for one exact copy of the source (12294fc84312), read on 2026-10-07. The repository is watched and re-audited when it changes.