WordPress MCP Custom Server
WordPress MCP server with versioned capability-based tools, safe REST write policies, W3C validation, playbooks, SEO checklists, and A/B benchmark reporting for managing WordPress content and sites.
README
WordPress MCP Custom Server
WordPress MCP server with:
- capability-based versioned tools (
*.v1) - backward-compatible aliases (old tool names still work)
- unified error contract
- request-level observability (
requestId, duration, status) - retry/timeout HTTP client for WP + W3C requests
- text playbooks/checklists for repeatable execution
- A/B benchmark report generator (
benchmark-summary.md) - write-safety policy for generic REST writes (allowlist + approval + dry-run)
Installation
cd /Users/yanka/dev/wp-mcp-custom
npm install
Required env
WP_URLWP_USERWP_APP_PASS
Optional:
WP_PROJECT_ROOTfor file toolsPROJECT_PROFILE_PATHfor custom profile location
Project profile
Create project.profile.json in server working directory (or use PROJECT_PROFILE_PATH):
{
"projectType": "wordpress",
"capabilities": ["seo", "content", "site", "validation", "files"],
"limits": {
"listFilesDefault": 200,
"listFilesMax": 2000,
"autofixDefaultMaxFiles": 500,
"autofixMaxFiles": 5000
},
"autofix": {
"defaultPaths": [
"wp-content/themes",
"wp-content/mu-plugins"
]
},
"http": {
"timeoutMs": 15000,
"retries": 2,
"retryDelayMs": 250,
"maxRetryDelayMs": 2000
},
"safety": {
"enabled": true,
"writeMethods": ["POST", "PUT", "DELETE"],
"allowedWritePathPrefixes": [
"/wp/v2/posts",
"/wp/v2/pages",
"/custom/v1/update-option",
"/custom/v1/update-yoast"
],
"requireApprovalPathPrefixes": [
"/wp/v2/settings",
"/wp/v2/users",
"/wp/v2/themes",
"/wp/v2/plugins"
]
}
}
Tool naming
Canonical versioned tools:
content.list.v1content.publish.v1content.update_fields.v1site.request.v1site.update_option.v1seo.set_meta.v1project.files.list.v1project.files.read.v1project.files.write.v1validation.w3c.validate_urls_raw.v1validation.w3c.validate_pages.v1validation.w3c.validate_and_recheck.v1validation.w3c.autofix_safe.v1playbook.list.v1playbook.read.v1checklist.seo_landing_audit.v1checklist.w3c_validate_and_fix_plan.v1checklist.multilang_publish.v1benchmark.compare_ab.v1
Backward-compatible aliases still supported:
list_posts,create_post_multilang,update_acf_fieldswp_request,update_option,update_yoastlist_project_files,read_project_file,write_project_filew3c_validate_live_urls_raw,w3c_validate_pages,w3c_validate_and_recheck,w3c_autofix_safe
Playbooks
Stored in /Users/yanka/dev/wp-mcp-custom/playbooks:
seo-landing-checklist-v1.mdw3c-fix-checklist-v1.mdmultilang-publish-v1.md
Use:
playbook.list.v1playbook.read.v1
Safety behavior for site.request.v1
GETrequests are allowed.- Write methods are checked against
safety.allowedWritePathPrefixes. - Paths in
safety.requireApprovalPathPrefixesrequirerequire_approval=true. dry_run=truereturns preview without sending request.
Benchmark demo report
Use benchmark.compare_ab.v1 with:
runs_prompt_onlyruns_mcp- optional
output_path
Output:
- aggregate metrics
- per-case comparisons
- generated markdown report (
mcp-benchmarks/benchmark-summary.mdby default)
Unified error contract
Every tool error returns:
{
"code": "INVALID_ARGUMENT",
"message": "...",
"details": {},
"retryable": false,
"requestId": "..."
}
Tests
npm test
Notes
- Logs go to stderr as JSON (
tool.start,tool.success,tool.error,server.started). - Tool schemas use stricter JSON Schema (
additionalProperties: false) for stable contracts.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.