Three reports from somebody driving the app through the MCP connector,
all the same shape: an argument accepted, an OK returned, and nothing
done.
**project_id on an update never moved the task.** Both the REST handler
and the MCP tool read it, both checked the caller's rights on the
destination — which reads as "understood" — and then neither passed it
on, because store.TaskUpdate has no such field: a project change is a
move, since sort_order is per project. So the task stayed where it was
and the answer said OK. Moving a task between projects was impossible
except by creating it again and closing the old one, which is what the
person ended up doing. Both paths now go through one helper, so they
cannot drift apart again.
**An unknown #project vanished without a word.** The parser reads
"#3Dekoration" correctly; the lookup then fails, the task goes to the
Inbox, and the name is gone from the title with nothing anywhere saying
why. Still not an error — a thought should not be thrown away over a typo
— but quick-add now returns unknown_project, and the MCP tool returns a
note written for a model to relay. The old behaviour was kind in the web
interface, where you see the row appear in the wrong place and fix it. In
a chat nobody sees the row.
**Sub-tasks were unreachable over MCP.** create_task had no parent_id,
though the REST API has had it all along, so importing a parent with
seven children produced eight unrelated tasks with the parent's name
prefixed onto each. A sub-task joins its parent's project — the two
cannot disagree — and a second level is refused rather than silently
flattened.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
verdande could not be added to Claude at all. The documented setup —
POST /api/v1/mcp with an Authorization header — cannot be configured from
Claude's custom-connector dialog, which asks for a name, a URL and OAuth
client credentials and has no field for a bearer token. The instructions
described something the interface does not offer.
Worse, the obvious guess failed silently in the most misleading way
available: /mcp was not a route, so the SPA fallback answered 200 with a
page of HTML. The connector reported a successful connection and then
failed to parse the response, which reads as a broken client rather than
a missing endpoint.
So /mcp exists now and takes its credential in the query string, exactly
as the calendar feed does and for the same reason: a client that cannot
be told to send a header means the address is the credential. The
request logger records paths without their query strings, so the key does
not reach the log.
It is deliberately outside /api/v1 and accepts the key and nothing else.
Reading a session cookie here would make it a state-changing POST outside
the CSRF check — a cross-site request that acts as whoever is signed in —
and there is a test that fails if that ever becomes true.
The API path is unchanged for anything that can send a header. The tokens
page now shows the connector address next to the token it belongs to,
since that is the one moment the token exists.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The MCP server speaks JSON-RPC over Streamable HTTP with the six tools
the brief names, authenticated by a personal API token — so a connector
reaches exactly what its owner reaches and there is no second identity
to reason about. A failed tool call returns a tool error, not a protocol
error: a model can recover from the first and can do nothing with the
second.
CalDAV serves VTODO, two-way, so Apple Reminders and Thunderbird can
read, create and complete tasks. Clients authenticate with Basic using
an API token as the password, never the account password — a client
stores what it is given, and what it is given should not be able to sign
in to the app. Completed tasks stay in the collection: a client that
stops seeing one treats it as deleted and drops its own record of having
done it.
The AI layer is one interface with adapters for Anthropic, OpenAI,
Google and any OpenAI-compatible endpoint. That last one is why the
abstraction exists: an integration that only spoke to a hosted API would
be useless to somebody running their own models. Every feature degrades
to "off" when nothing is configured, and the stored API key is never
returned to the settings page.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>