WP HealthKit

@wphealthkit/mcp-server v0.4.0

An MCP (Model Context Protocol) server that gives AI assistants direct access to WP HealthKit's plugin audit API. Once configured, tools like Claude Desktop, Claude Code, and Cursor can trigger security audits, retrieve findings, fetch AI-ready fix prompts, bulk-audit entire plugin directories, and flag false positives — all without leaving the chat interface.

Setup

Required environment variable

WPHK_API_KEY=your_api_key_here

Get your API key from wphealthkit.com/dashboard.

Claude Desktop

Add the following to your claude_desktop_config.json (usually at ~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{  "mcpServers": {    "wphealthkit": {      "command": "npx",      "args": ["-y", "@wphealthkit/mcp-server"],      "env": {        "WPHK_API_KEY": "your_api_key_here"      }    }  }}

Claude Code

Add to your project's .mcp.json:

{  "mcpServers": {    "wphealthkit": {      "command": "npx",      "args": ["-y", "@wphealthkit/mcp-server"],      "env": {        "WPHK_API_KEY": "your_api_key_here"      }    }  }}

Cursor

Open Cursor Settings > MCP > Add Server and use:

{  "wphealthkit": {    "command": "npx",    "args": ["-y", "@wphealthkit/mcp-server"],    "env": {      "WPHK_API_KEY": "your_api_key_here"    }  }}

Available tools

Tool reference

audit_plugin

Triggers a security audit for any plugin hosted on wp.org.

Parameters

Example

audit_plugin({ slug: "contact-form-7" })// Returns: { auditId: "abc-123", status: "queued" }

audit_plugin_zip

Triggers an audit from a local ZIP file. Useful for plugins not on wp.org or pre-release builds.

Parameters

Example

audit_plugin_zip({ path: "/Users/me/plugins/my-plugin.zip" })// Returns: { auditId: "def-456", status: "queued" }

audit_plugins_bulk

Audits all plugin ZIP files in a local directory. Submissions are batched in groups of 10. Results stream as each audit completes, and a final summary table is printed with a risk breakdown and links to top findings.

Parameters

Example

audit_plugins_bulk({ directory: "/Users/me/plugins", engines: [] })

Output

Results stream to the conversation as each plugin completes. Once all audits finish, the tool prints a summary table:

Plugin                  Risk      Findings   Report----------------------  --------  ---------  ----------------------------------------my-plugin.zip           CRITICAL  14         https://wphealthkit.com/report/abc-123another-plugin.zip      LOW       2          https://wphealthkit.com/report/def-456legacy-plugin.zip       HIGH      7          https://wphealthkit.com/report/ghi-789
Summary: 3 plugins audited — 1 CRITICAL, 1 HIGH, 0 MEDIUM, 1 LOW

get_report

Polls the status and full results of an audit. Call this after audit_plugin or audit_plugin_zip to wait for completion and retrieve the report.

Parameters

Example

get_report({ auditId: "abc-123" })// Returns: { status: "completed", grade: "C", riskLevel: "HIGH", findingsCount: 7, reportUrl: "..." }

get_findings

Returns paginated findings for a completed audit. Supports filtering by severity and category.

Parameters

Example

get_findings({ auditId: "abc-123", severity: "CRITICAL" })

get_fix_prompt

Returns AI-ready fix prompts for an audit's findings, grouped and batched by severity. Pass the output directly to a coding assistant to generate patches.

Parameters

Example

get_fix_prompt({ auditId: "abc-123", severity: "HIGH" })

check_plugin

Looks up a plugin's current security grade, risk level, and findings count from the WP HealthKit directory without triggering a new audit.

Parameters

Example

check_plugin({ slug: "woocommerce" })// Returns: { grade: "B", riskLevel: "MEDIUM", findingsCount: 3, lastAudited: "2026-04-20" }

list_usage

Returns your current billing period usage — audits consumed, tier, and remaining quota.

Parameters

None.

Example

list_usage()// Returns: { auditsUsed: 47, auditsLimit: 100, tier: "pro", resetsAt: "2026-05-01" }

flag_finding

Flags a finding as a false positive. The report is reviewed by the WP HealthKit team. If the pattern is confirmed as a false positive, the scanner rule is updated to prevent the same result from appearing in all future audits.

Parameters

Example

flag_finding({  auditId: "abc-123-def-456",  findingId: "finding-5",  findingTitle: "Named arguments used in internal function call",  reason: "These are positional args — the scanner is misidentifying the call signature"})// Returns: { flagged: true, reviewTicket: "FP-2891" }

Usage flows

Audit a single plugin and get fix prompts

audit_plugin({ slug: "my-plugin" })  → get_report({ auditId: "..." })          // poll until status === "completed"  → get_findings({ auditId: "...", severity: "CRITICAL" })  → get_fix_prompt({ auditId: "..." })

Audit all plugins in a local directory

audit_plugins_bulk({ directory: "/Users/me/plugins" })  // streams per-plugin results as they complete  // prints final summary table with risk breakdown

Check a plugin before installing

check_plugin({ slug: "advanced-custom-fields" })  // returns grade, risk level, and findings count without consuming an audit credit

Flag a false positive after reviewing findings

get_findings({ auditId: "...", severity: "HIGH" })  → flag_finding({      auditId: "...",      findingId: "finding-12",      findingTitle: "Unescaped output in template",      reason: "Output is escaped upstream via wp_kses before reaching this call"    })

Environment variables

License

MIT