Skip to main content
Glama

mcp-wordpress-com__search

Read-only

Finds abilities for creating WordPress.com websites, publishing content, customizing design, and managing sites and accounts. The catalog covers: new sites from a title and optional tagline, and subdomain availability; posts and pages, drafts and publishing, individual block sections, custom post type content, categories and taxonomy terms; media upload, image generation, and media library management; comments and moderation; theme discovery and switching, block and pattern reference, templates, template parts, menus, navigation, and global styles; site settings and visibility, plugins, collaborator invitations, traffic counts, and activity logs; domains, DNS, nameservers, SSL, email-service DNS setup, plans, and checkout links; account profile, notifications, security information, billing and subscriptions; Jetpack backup diagnostics, downtime monitoring, account protection, connection diagnostics, newsletters, and security scans. Availability depends on permissions, enabled settings, site features, and pla… Through Royally: its server marks it read-only, so it runs straight away.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "mcp-wordpress-com__search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum abilities returned for a nonempty query: 1 to 25 when detailed=false (default 10), or 1 to 5 when detailed=true (default 5). Does not limit the empty-query category overview.
queryYesCase-insensitive words matched against ability names, labels, categories, descriptions, and keywords, such as "site create", "pages", "templates", or "DNS". Exact names and labels rank first; partial results identify unmatched terms. An empty string returns all matching names and labels grouped by category, with counts, for the selected site and readonly filter; this overview has no schemas or pagination. Maximum 500 UTF-8 bytes.
offsetNoNumber of matching abilities to skip for a nonempty query, starting at 0. Results include total and has_more for pagination. Does not apply to the empty-query category overview.
site_idNoSite to run this tool on: 1484d0f5-e153-4114-b09b-6d03462b465a (https://public-api.wordpress.com/wpcom/v2/mcp/v1)
detailedNoFor a nonempty query, false returns names, labels, short descriptions, categories, and confirmation requirements. True returns complete descriptions, input schemas, instructions, and annotations, with at most five results. Empty queries always return the category overview.
readonlyNoSelects one approval classification, including for an empty query. True returns abilities explicitly marked read-only, plus read/write abilities whose readonly_actions run without approval. False (the default) returns abilities requiring approval, including mixed read/write abilities and those without a read-only annotation. False does not mean all abilities; there is no unfiltered value. Results include other_readonly_matches when the other value has matches.
wpcom_siteNoExisting target site: a site ID encoded as a string, a domain, or a full site URL. Site IDs and URLs are returned by wpcom/user-sites. Sets the site context for discovery or execution and is required for remote: abilities. Without a site, discovery covers only WordPress.com-defined abilities; account operations and creation of a new website need no existing site. Any site selector also present in the ability input must identify the same site.
include_output_schemaNoAdds each ability's declared output_schema to detailed results, describing its result fields and types. True requires detailed=true. Empty-query overviews contain no schemas.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

B3.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, and the description's trailing line about the server marking it read-only merely restates that. The one genuine addition is that availability depends on permissions, enabled settings, site features, and plans, warning the agent that results are permission-filtered and potentially incomplete; no rate limits, response shape, or ranking caveats are given.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded in sentence one, but the bulk of the text is an enormous, comma-spliced catalog enumeration that duplicates what the search itself would return and is cut off mid-word ("pla…"). A malformed fragment ("Through Royally: its server marks it read-only, so it runs straight away") further damages readability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With eight parameters at full schema coverage, no nested objects, and no output schema, the structured data carries most of the load, and the description is long enough. What is missing is workflow context: how results should be fed into describe/execute, and what the returned ability records contain at the detailed=false versus detailed=true level.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and each of the eight parameters already carries a detailed description covering limits, pagination, the detailed flag, readonly classification, and site targeting. The description adds no parameter-level meaning beyond the schema, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence gives a specific verb+resource ("Finds abilities") scoped to WordPress.com site/content/design/account management, which is clearly distinguishable from a concrete action tool. However, it never names the obvious siblings (mcp-wordpress-com__describe, mcp-wordpress-com__docs) it must be paired with, so the agent must infer the search-then-describe relationship.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: the tool is a catalog search, so an agent can reason that it should be called to locate abilities before invoking them. There is no explicit "call this first, then use describe/execute" guidance, no when-not conditions, and no mention of how it relates to mcp-wordpress-com__describe.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources