harshith-nayaka-l-portfolio.vercel.app WebMCP audit

Name: harshith-nayaka-l-portfolio.vercel.app WebMCP audit
Creator: ora

Rescan

audited Sep 4, 2026in 13s

69/ 100100% of the applicable check weight evaluated

3 tools registered. Strongest in shared experience, weakest in tool selection.

Shared experience100

Tool selection9

Tool quality97

Trust62

https://harshith-nayaka-l-portfolio.vercel.app

Tools

1 read, 1 write, 1 undeclared

Loading map

list_projects

List the engineering projects Harshith Nayaka L has built, with a one-line outcome, the technologies used, and the case-study slug for each. Use this to answer questions about his work or to find the right slug before calling open_case_study.Answers a question. Declared read only.

pagehttps://harshith-nayaka-l-portfolio.vercel.app/

implementation

viaimperative

entry pointdocument

registered after572ms

executepresent

api surfaceTakes no parameters.

annotations

read onlytrue

untrusted contentnot declared

titlenot declared

1 finding

warningInjection surface

weight 3

3 of 3 tools carry instruction-shaped text in their own metadata: list_projects Description instructs agent when to use tool.

list_projects: Description instructs agent when to use tool; open_case_study: Description instructs agent when to use tool; draft_project_enquiry: Description instructs agent on its scope and limitations

fix

{
  name: "list_projects",
  // Metadata DESCRIBES the tool - it never addresses the agent reading it.
  // Rewrite any name, description, title, or schema field description that
  // instructs the agent (which tool to prefer, what to output, rules to
  // ignore) so it states what the tool does and what it returns instead.
  description: "Searches the catalog and returns matching items with prices."
}

tool json

{
  "name": "list_projects",
  "description": "List the engineering projects Harshith Nayaka L has built, with a one-line outcome, the technologies used, and the case-study slug for each. Use this to answer questions about his work or to find the right slug before calling open_case_study.",
  "inputSchema": {
    "type": "object",
    "properties": {}
  },
  "annotations": {
    "readOnlyHint": true
  }
}

Findings

Shared experience

100 / 100 · weight 30

not applicableVisible effect

weight 6

Not invoked on this run: this audit did not call any tool. Scheduled re-audits only read the registry; a live audit from the report page calls the tools that declare readOnlyHint: true.

passPage experience

weight 16

The page a person sees holds up next to the agent surface: a working interface, visible actions, readable content, nothing in the way.

passHuman parity

weight 8

The person co-browsing can see and use this page - the same page the agent's tools act on, and 1 declarative form doubles as visible counterparts.

Tool selection

9 / 100 · weight 25

not applicableInvoke success rate

weight 6

Not invoked on this run: this audit did not call any tool. Scheduled re-audits only read the registry; a live audit from the report page calls the tools that declare readOnlyHint: true.

failTool selection

weight 12

An agent chose an existing tool and built a schema-valid call that held up on 0 of 3 canonical intents; on "Find the record for a company called Northwind." no tool on the page served it. Nothing was executed, so this verifies selection, not outcomes.

failCoverage vs. site type

weight 7

The tool set covers 1 of the 4 things an agent needs on a saas site; it cannot read one item in detail or create a record or start a job or update or move an existing record.

Tool quality

97 / 100 · weight 25

passRegistration timing

weight 1

Every measured tool registered within 575ms of navigation. 1 further tool carried no measurable registration time.

toolopen_case_study

passCanonical entry point

weight 3

All 2 tools register on the canonical document.modelContext entry point.

passSchema validity

weight 4

All 2 declared input schemas are structurally valid object schemas.

passSchema quality

weight 4

All 1 of 3 tool schemas that declare parameters describe them (the other 2 declare no parameters), and every description stays within Chrome's size guidance.

warningNaming quality

weight 2

Tool naming makes selection harder than it needs to be: 2 names do not start with a verb (open_case_study).

toolopen_case_study

fix

{ name: "open_case_study" /* short, unique, verb-based */ }

passStub detection

weight 4

All 2 tools declare an execute handler.

passRegistration errors

weight 2

No tool registration threw during the capture.

passDescription quality

weight 5

All 3 rated tool descriptions say what the tool does, when to use it, and what it returns.

Trust

62 / 100 · weight 20

passAnnotations present

weight 5

All 1 read-shaped tool declares readOnlyHint: true - the one declared claim that lets an agent treat a call as safe to make without asking.

passAnnotation mismatch

weight 5

No tool claims to be read-only while its own name or description says it writes (1 declared hint checked).

warningUntrusted content hint

weight 3

1 of 1 tools look like they return text written by other people but declare no untrustedContentHint, so an agent will treat the response as the site speaking.

tooldraft_project_enquiry

draft_project_enquiry: review, message

fix

{ name: "draft_project_enquiry", annotations: { untrustedContentHint: true } }

not applicableHint vs. observed

weight 4

Not invoked on this run: this audit did not call any tool. Scheduled re-audits only read the registry; a live audit from the report page calls the tools that declare readOnlyHint: true.

warningInjection surface

weight 3

3 of 3 tools carry instruction-shaped text in their own metadata: list_projects Description instructs agent when to use tool.

toollist_projects

list_projects: Description instructs agent when to use tool; open_case_study: Description instructs agent when to use tool; draft_project_enquiry: Description instructs agent on its scope and limitations

fix

{
  name: "list_projects",
  // Metadata DESCRIBES the tool - it never addresses the agent reading it.
  // Rewrite any name, description, title, or schema field description that
  // instructs the agent (which tool to prefer, what to output, rules to
  // ignore) so it states what the tool does and what it returns instead.
  description: "Searches the catalog and returns matching items with prices."
}

Tool selection

0% across 3 intents

Find the record for a company called Northwind.missed

choseno toolexpected record searchkind not applicable

No tool was picked for this intent.

arguments

{}

Show me everything on that record.missed

choseno toolexpected record detailkind not applicable

No tool was picked for this intent.

arguments

{}

Create a new contact called Dana Reeve.missed

choseno toolexpected record createkind not applicable

No tool was picked for this intent.

arguments

{}

model: gemini-2.5-flash

Add the tools this site is missing

Our scanner reads your website and suggests the right WebMCP tools for it.

The open source webmcp plugin teaches your coding agent to audit a site, implement tools on document.modelContext, and verify them in a real browser. npx @ora-ai/webmcp-verify runs the verification on its own. No signup, no hosted service.

how this was captured

observed via: capture shim (Chromium 148.0.7778.96)
chrome: 148.0.7778.96
capture shim: v2
spec snapshot: 2026-08-26
mode: fast
pages: 1 - entry page only
tools: 3
invoked: not invoked; a live audit calls them
run time: 13s
finished: Sep 4, 2026

Checked the way in-browser agents discover tools: the top-level document's modelContext registry, read after the page settles.