Understanding MCP

Model Context Protocol, usually shortened to MCP, is an open standard that lets an AI assistant connect to an outside system and use it. SiteTrax.io implements it so that assistants can work with your operational data without anyone exporting it first.

Why it exists

Before MCP, getting an assistant to answer a question about your yard meant copying data into a prompt or building a bespoke integration for each assistant. Both approaches age badly. A copied extract is stale the moment it is pasted, and a bespoke integration has to be rebuilt for the next tool.

MCP replaces that with one connection the assistant understands. SiteTrax.io publishes what it can do once, and any compatible assistant can use it.

What it means in practice

Without MCP With MCP Export a report, paste it into a chat The assistant readscan theretrieve livecurrent recordrecords atwhen theit momentcalls youa askSiteTrax.io tool The extract reflects one moment and one filter EveryA questionnew istool answeredcall against currentretrieves data for its requested scope and time period; a reply without one may use earlier context The assistant cannot check its own answer The assistant can retrieve the supporting record and its image Sharing the extract shares everything in it Access follows the signed-in SiteTrax.io account

How SiteTrax.io implements it

It is a remote server. The endpoint is https://mcp.sitetrax.io/mcp. An assistant that only supports servers running on your own machine cannot reach it. Authorization is OAuth-based. You signapprove inthe toassistant’s access on the SiteTrax.io through its own authorization screen.screen using an active account with verified email. Application login alone does not grant an assistant access, and publishing an Intelligence profile is optional for ordinary MCP queries. No SiteTrax.io password is entered into the assistant. Permissions are scoped. Read access covers operational queries.queries, Notificationselected published profile context, notification lists and digestdelivery actionshistory. needCreating aan separatealert or digest, or cancelling one, needs read access plus an additional write scopescope. thatA isclient approvedmay separately.request it during initial connection or later. Analysis happens on the server. SiteTrax.io calculates supported totals, groupings and durations itself, so the assistant does not pullneed downa rawlarge recordsraw-data todownload dofor arithmetic.those calculations. It can separately retrieve permitted supporting records. SiteTrax.io stays the system of record. The assistant reads; it does not become the source of truth.

What it does not do

It does not widen your SiteTrax.io permissions. A project not shared with you stays out of reach. It does not handrequire youra databulk export or a synchronized index. However, the records, summaries and any permitted evidence returned for a query are sent to the assistant vendorprovider asyou achoose. bulkFollow export.your organization’s policies for using that provider. It does not make an unverified answer verified. Interpretation rules still apply.

See Account Access and OAuth for the account and authorization flow. For the full technical contract, including transport, scopes and response semantics, see the SiteTrax.io MCP Server reference.