Latest entryGeorge Jieh
A WebMCP manifest is not a working tool
Separate WebMCP discovery documents from browser tool registration, and use an authorized browser test to check the advertised interaction.
webmcpagent-surfacesaudit-pillar
Blog
MachineRead Blog
Deep dives into AI agent readability, machine-readable signals, and how to make your site discoverable by retrieval-augmented systems.
Archive
Earlier entries
Making an agent skill findable
Clear descriptions and accessible package files help supporting clients find an Agent Skill. Check the instructions and helper code before using them.
agent-skillsagent-surfacesaudit-pillar
What an A2A agent card is for
An A2A Agent Card describes a service's identity, capabilities, and interfaces. Check the advertised service as well as the document.
a2aagent-cardaudit-pillar
Using MachineRead from an MCP client
Connect an MCP client to MachineRead's read-only audit tools, request a website audit, and inspect the results without confusing discovery with tool execution.
mcpagent-readinessaudit-pillar
What an entity lookup can and cannot confirm
Read Wikipedia and Wikidata matches with name collisions, cached results, and limited search coverage in mind. A match still needs inspection.
entity-lookupwikimediaaudit-pillar
The HTML cost of a simple page
A small-looking page can still return slow, heavy HTML. MachineRead checks structural performance clues, while browser measurements answer what visitors experience.
crawl-efficiencyhtml-performancemethodology
When a site uses three names for the same thing
Track down stale names and URLs across page titles, share cards, and JSON-LD without mistaking consistent metadata for verified identity.
social-metadataentity-metadataaudit-pillar
Indexing directives are not visibility outcomes
Find accidental noindex rules and restrictive snippet settings in page HTML and response headers, and distinguish them from deliberate publishing choices.
indexing-directivessnippet-controlsaudit-pillar
The page outline a non-browser client can follow
Inspect the landmarks, links, labels, and form controls a client receives before JavaScript runs, then test the interactions separately.
semantic-htmlagent-navigationaudit-pillar
Signals that help crawlers find updated public content
Search discovery checks public signals related to reachability, initial HTML content, and declared modification dates.
search-discoveryaudit-pillardeep-dive
What a non-browser request can actually read
A plain HTTP fetch can reveal whether public HTML is available before a client executes JavaScript. It cannot predict every crawler's behavior.
bot-accessaudit-pillardeep-dive
A sitemap is a map, not an indexing guarantee
A sitemap publishes URLs and optional modification dates for crawlers. It can support discovery, but it does not guarantee crawling or indexing.
sitemapseodeep-dive
robots.txt is a public crawler policy
robots.txt expresses crawl directives for named user agents. AI-related rules should reflect a deliberate, reviewed policy.
robots-txtseodeep-dive
Publishing page facts with Schema.org JSON-LD
JSON-LD can publish page facts in structured fields. It reduces ambiguity for supporting clients but does not determine how they will use the data.
schema-orgjson-lddeep-dive
Choosing one public URL for a page
A canonical tag expresses a preferred URL for duplicate or closely related pages. It can help search systems consolidate signals but does not dictate their behavior.
canonicalseodeep-dive
How an OpenAPI document makes an API easier to inspect
An OpenAPI document describes an HTTP API in a machine-readable form. It can help a supporting client construct requests, but it does not authorize or validate their use.
openapiagent-surfacesdeep-dive
A standard route to an API's public description
RFC 9727 defines a well-known URI for an API catalog expressed as a linkset. It gives supporting clients a predictable discovery path.
api-catalogagent-surfacesdeep-dive
llms.txt is optional, not a visibility shortcut
llms.txt is a proposed discovery file for language-model tools. A MachineRead result describes the response and basic shape, not client support or use.
llms-txtagent-surfacesdeep-dive
What an AI catalog can tell a supporting client
An AI catalog can state what a service does and where its machine-readable surfaces live. The format is early, so the audit gives it limited weight.
ai-catalogagent-surfacesdeep-dive
Why Agents Need to Read Your Site
Agent retrieval depends on what a client can fetch and parse. A page that renders for people may expose less to a non-browser client.
ai-agentsdiscoveryretrieval
Launching MachineRead
MachineRead audits a public website for observable AI agent and search-readiness signals across 14 check groups and 60 checked points.
launchproductai-readiness