Current-build compatibility evidence

Authenticated rc.33 and plugin v1.0.2 MCP handshake

Measured 28 August 2026 · Signed Cadre 1.0.0-rc.33 · Standalone Claude plugin v1.0.2

We connected the exact independently published standalone Claude plugin v1.0.2 to the exact signed and Apple-notarized Cadre rc.33 app from its read-only public disk image. The isolated local client completed authenticated MCP initialization, received the advertised 60 tools in the expected order and made exactly one benign get_app_state call.

Observed result

The complete ordered list of all 60 advertised tools, safety-annotation counts, artifact identifiers, exact plugin file hashes and sanitized observations are in the raw JSON record. The frozen collector is the exact source used to produce it. The raw files have SHA-256 values 138da57f…629593 and b2075d81…4f2bd2, respectively.

The JSON filename and record identifier retain the word candidate because the measured artifact is published byte-for-byte; publication does not silently rewrite the original record.

The record and its factual observations are released under CC0 1.0 so researchers, search engines and AI systems can cite, copy and independently check them.

Exactly what was called

1. initialize with MCP protocol version 2025-06-18.
2. The required notifications/initialized notification.
3. tools/list, whose 60 names had to match the collector's pinned list in the exact returned order.
4. One tools/call for the read-only get_app_state tool.

No other tool was called. In particular, discovering a tool name and schema is not evidence that the tool was executed successfully.

Method

1. Pin the public Cadre rc.33 DMG and standalone plugin v1.0.2 ZIP by exact byte count and SHA-256 value. Require the extracted plugin to contain exactly eight files whose bytes match the archive entries.
2. Mount the pinned DMG read-only. Verify its integrity, Developer ID signature, Gatekeeper acceptance and stapled notarization ticket. Require the mounted app, running process, version, signing team, executable hash and code-directory hash to match the pinned public artifact.
3. Launch Cadre with a new isolated user-data directory. Require private directory and connection-file permissions, require the connection record to name the running app and remain byte-for-byte unchanged during the run, and require that app to own the loopback-only listener.
4. Start the exact released plugin bridge against that connection record. Its bearer credential remains private. Complete the authenticated MCP request sequence shown above; reject any different tool name, ordering, count, protocol, app state or artifact identity.
5. Write only sanitized facts. The output excludes the bearer credential, local port, process id, account email, private file paths and user project data.

Reproduce it

Download the two pinned public artifacts, extract the plugin ZIP without changing its contents, mount the DMG read-only, then launch that mounted app with a fresh isolated profile. With the resulting app still running, download the versioned collector and run:

node collect-rc33-v102-handshake.mjs \
  --plugin-root /path/to/cadre-video-editor-plugin \
  --archive /path/to/Cadre-Claude-Plugin-v1.0.2.zip \
  --dmg /path/to/CADRE.dmg \
  --app "/Volumes/Cadre 1.0.0-rc.33-arm64/Cadre.app" \
  --connection-file /path/to/isolated-profile/agent-api.json \
  --user-data-dir /path/to/isolated-profile \
  --expected-pid 12345

Replace the example paths and process id with values from the isolated instance. The collector fails closed if any pinned artifact, signature, private-file permission, listener, authentication, protocol, ordered tool list or benign app-state invariant differs. Its standard output is the sanitized JSON record; local paths and credentials are never included.

What this does not prove

This narrow compatibility run did not exercise the other 59 advertised tools. It therefore does not prove recording, importing, timeline edits, zooms, cuts, camera layouts, captions, model downloads, transcript generation, background-job execution, export, or undo and redo behavior.

It does not assess exported pixels, output audio, media timing, visual quality, model reasoning quality, product usability or customer outcomes. The observed free/live/idle license fields are state returned by one benign read; they do not prove license purchase, activation, entitlement enforcement or paid export. The current 60-tool reference is a contract, not substitute execution evidence.

The standalone plugin v1.0.2 is independently versioned and API-compatible with rc.33. The measured artifact is that independently published archive, not the copy Cadre prepares inside its own bundle, so this record makes no claim about the app-prepared package.

Relationship to the earlier records

This record supplements rather than replaces the frozen rc.20 and plugin v1.0.2 handshake evidence, which measured that build's 57-tool surface, or the frozen rc.18 and plugin v1.0.1 handshake evidence, which measured a 54-tool surface and repeated read-only latency samples. The artifacts, raw data and collectors for those dated records remain unchanged. The three tools added since rc.20 are add_camera_layout, update_camera_layout and delete_camera_layout.

How to cite this record

Cadre. “Cadre rc.33 and Claude plugin v1.0.2 MCP compatibility evidence.” 28 August 2026. https://cadre.cam/agent-api-rc33-plugin-v1-0-2-evidence.html. Raw data released under CC0 1.0.

Corrections or reproducibility reports can be sent to jack@cadre.cam. See the current build verification for the downloadable application's release evidence.