gitwand.app WebMCP audit

Name: gitwand.app WebMCP audit
Creator: ora

Rescan

audited Sep 1, 2026in 11s

68/ 100100% of the applicable check weight evaluated

3 tools registered. Strongest in shared experience, weakest in trust.

Shared experience100

Task completion60

Tool quality92

Trust0

https://gitwand.app

Tools

0 read, 0 write, 3 undeclared

Loading map

search_gitwand_docs

Search the GitWand documentation for guides, API reference, CLI commands, and blog articles.No behaviour hints declared. Agents should treat it as possibly state-changing.

pagehttps://gitwand.app/

implementation

viaimperative

entry pointdocument

registered after46ms

executepresent

api surface

queryrequired

annotations

read onlynot declared

untrusted contentnot declared

titlenot declared

1 finding

failAnnotations present

weight 6

2 of 2 read-shaped tools do not declare readOnlyHint: true, so an agent has to treat them as possible writes and ask before calling. (Declaring readOnlyHint: false earns nothing - it is the default.)

search_gitwand_docs, get_gitwand_mcp_install

fix

{
  name: "search_gitwand_docs",
  // Declare readOnlyHint: true on tools that truly have no side effects -
  // that is the claim that lets an agent relax confirmation on reads.
  // (false is the default, so declaring it adds no information.)
  annotations: { readOnlyHint: true }
}

tool json

{
  "name": "search_gitwand_docs",
  "description": "Search the GitWand documentation for guides, API reference, CLI commands, and blog articles.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "query": {
        "type": "string",
        "description": "Search terms"
      }
    },
    "required": [
      "query"
    ]
  },
  "annotations": {}
}

Findings

Shared experience

100 / 100 · weight 30

passPage experience

weight 20

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 10

The person co-browsing can see and use this page - the same page the agent's tools act on.

Task completion

60 / 100 · weight 25

failTool selection

weight 15

An agent chose an existing tool and built a schema-valid call that held up on 1 of 3 canonical intents; on "Read that page to me." no tool on the page served it. Nothing was executed, so this verifies selection, not outcomes.

passCoverage vs. site type

weight 10

The tool set covers the whole core docs flow: search or browse the catalog, read a page or article, navigate the documentation tree.

Tool quality

92 / 100 · weight 25

passRegistration timing

weight 1

Every measured tool registered within 47ms of navigation.

toolget_gitwand_mcp_install

passCanonical entry point

weight 3

All 3 tools register on the canonical document.modelContext entry point.

passSchema validity

weight 4

All 3 declared input schemas are structurally valid object schemas.

passSchema quality

weight 4

All 2 of 3 tool schemas that declare parameters describe them (the other 1 declares 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: 1 name does not start with a verb (navigate_to_gitwand_section).

toolnavigate_to_gitwand_section

fix

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

passStub detection

weight 4

All 3 tools declare an execute handler.

passRegistration errors

weight 2

No tool registration threw during the capture.

warningDescription quality

weight 5

2 of 3 tool descriptions leave an agent guessing: get_gitwand_mcp_install Does not specify what is returned by the tool.

toolget_gitwand_mcp_install

get_gitwand_mcp_install: weak; navigate_to_gitwand_section: weak

fix

{
  name: "get_gitwand_mcp_install",
  description: "Describe what this tool does, when to use it, and what it returns."
}

Trust

0 / 100 · weight 20

failAnnotations present

weight 6

2 of 2 read-shaped tools do not declare readOnlyHint: true, so an agent has to treat them as possible writes and ask before calling. (Declaring readOnlyHint: false earns nothing - it is the default.)

toolsearch_gitwand_docs

search_gitwand_docs, get_gitwand_mcp_install

fix

{
  name: "search_gitwand_docs",
  // Declare readOnlyHint: true on tools that truly have no side effects -
  // that is the claim that lets an agent relax confirmation on reads.
  // (false is the default, so declaring it adds no information.)
  annotations: { readOnlyHint: true }
}

not applicableAnnotation mismatch

weight 6

No tool declares a readOnlyHint, so there is no safety claim to contradict.

not applicableUntrusted content hint

weight 4

No tool's contract suggests it returns text written by somebody other than the site, so there is nothing to flag as untrusted.

not applicableInjection surface

weight 4

No tool's metadata carries instruction-shaped text aimed at the agent reading it. This check only ever flags; it never credits a site.

Tool selection

33% across 3 intents

Find the page that explains authentication.ok

chosesearch_gitwand_docsexpected docs searchkind matched

arguments

{
  "query": "authentication"
}

Read that page to me.missed

choseno toolexpected page readkind not applicable

No tool was picked for this intent.

arguments

{}

What other pages are in the same section?missed

choseno toolexpected navigationkind 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: v1
spec snapshot: 2026-08-26
mode: fast
pages: 1 - entry page only
tools: 3
run time: 11s
finished: Sep 1, 2026

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