Seomi Wp MCP Server
@seomi/wp-mcp
npm
v0.3.1
Published by @seomi — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
Universal installer for SEOMI MCP Abilities — wires WordPress projects to AI agents in one command (mu-plugin, MCP servers, Abilities API, MCP Adapter, ai-factory skill).
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 7 = 93. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 11
high Reads a sensitive credential path or dumps the environment (src/lib/ssh-key-setup.mjs)MTC-SRC-006
In the server's implementation (`src/lib/ssh-key-setup.mjs:137`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: th( homedir(), '.ssh', 'id_ed25519' ); const pubKeyPath = keyPath + '.pub'; const comment = cfg.comment || `ai-agent@$
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/lib/ssh-key-setup.mjs
high Shell/command execution in server code (src/commands/doctor.mjs)MTC-SRC-002
In the server's implementation (`src/commands/doctor.mjs:17`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt { spawn } from 'node:child_process'; import { logger } from '../lib/logger.mjs'; import { readMcpJson } from '../li
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/commands/doctor.mjs
high Shell/command execution in server code (src/commands/init.mjs)MTC-SRC-002
In the server's implementation (`src/commands/init.mjs:22`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt { spawn } from 'node:child_process'; import { logger } from '../lib/logger.mjs'; import { mergeEnv } from '../lib/e
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/commands/init.mjs
high Shell/command execution in server code (src/commands/update.mjs)MTC-SRC-002
In the server's implementation (`src/commands/update.mjs:14`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt { spawn } from 'node:child_process'; import { confirm } from '@inquirer/prompts'; import { logger } from '../lib/lo
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/commands/update.mjs
high Shell/command execution in server code (src/lib/metrika-mcp-installer.mjs)MTC-SRC-002
In the server's implementation (`src/lib/metrika-mcp-installer.mjs:26`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: spawnSync } from 'node:child_process'; import { logger } from './logger.mjs'; import { detectPython } from './python-de
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/lib/metrika-mcp-installer.mjs
high Shell/command execution in server code (src/lib/metrika-setup.mjs)MTC-SRC-002
In the server's implementation (`src/lib/metrika-setup.mjs:19`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt { spawn } from 'node:child_process'; import { confirm, input, password, select } from '@inquirer/prompts'; import {
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/lib/metrika-setup.mjs
high Shell/command execution in server code (src/lib/python-detector.mjs)MTC-SRC-002
In the server's implementation (`src/lib/python-detector.mjs:22`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: spawnSync } from 'node:child_process'; import { logger } from './logger.mjs'; const MIN_MAJOR = 3; const MIN_MINOR = 1
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/lib/python-detector.mjs
high Shell/command execution in server code (src/lib/self-update.mjs)MTC-SRC-002
In the server's implementation (`src/lib/self-update.mjs:16`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt { spawn } from 'node:child_process'; import { readFile } from 'node:fs/promises'; import { join, resolve as resolvePa
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/lib/self-update.mjs
high Shell/command execution in server code (src/lib/ssh-key-setup.mjs)MTC-SRC-002
In the server's implementation (`src/lib/ssh-key-setup.mjs:27`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt { spawn } from 'node:child_process'; import { existsSync } from 'node:fs'; import { readFile, mkdir, access } from 'n
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/lib/ssh-key-setup.mjs
high Shell/command execution in server code (src/lib/ssh-mu-plugin-installer.mjs)MTC-SRC-002
In the server's implementation (`src/lib/ssh-mu-plugin-installer.mjs:27`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt { spawn } from 'node:child_process'; import { logger } from './logger.mjs'; /** * Spawn a child process and resolve
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/lib/ssh-mu-plugin-installer.mjs
high Shell/command execution in server code (src/lib/ssh-wp-cli-installer.mjs)MTC-SRC-002
In the server's implementation (`src/lib/ssh-wp-cli-installer.mjs:33`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt { spawn } from 'node:child_process'; import { logger } from './logger.mjs'; export const WP_CLI_PHAR_URL = 'https:/
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/lib/ssh-wp-cli-installer.mjs
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Versions 2
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.3.1 latest |
A 93/100 | 11 | 1.13.0 | 2026-09-07 |
v0.3.0 |
A 93/100 | 11 | 1.12.1 | 2026-08-23 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan @seomi/wp-mcp --onlineOther implementations of Seomi Wp 6
Independent packages implementing the same tool, scanned with the same engine. Compare all 7 side by side →
The WordPress MCP server enables AI assistants to interact with WordPress sites through a standardized interface. It handles authentication and provides a secure way to discover and interact with WordPress REST API endpoints.
WordPress MCP Server - Connect WordPress to AI agents via Model Context Protocol
Wordpress MCP Server
A Model Context Protocol server for interacting with WordPress.
WordPress Model Context Protocol (MCP) implementation
Security scan results for the Wp (npm) MCP server.
More in Content Management
Apify MCP Server
Model Context Protocol (MCP) Server for the *@inkeep/agents-mcp* API.
Medicare spending, chronic conditions, hospital quality, readmissions, and enrollment
Public read-only MCP for products, frameworks, guides, methodology, and blog metadata.
Community-maintained MCP server for Atlassian Confluence Data Center. Not affiliated with Atlassian.
MCP server for Contentful Content Management API integration