timetree-worklog-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@timetree-worklog-mcp Log today's work: finished the API migration and reviewed three PRs"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
timetree-worklog-mcp
A local-first MCP server for daily work logs, completed work, progress reports, and optional TimeTree memo publication.
Nine tools. No delete, update, calendar-management, invite, or memo-deletion operations.
Local-first. The canonical record is Markdown on your machine. SQLite only indexes it.
Safe by default. Remote writes are disabled until you explicitly enable them.
Verified writes. Every remote create is read back and hash-checked before success is reported.
The local Markdown archive is the canonical durable record. A transactional SQLite ledger indexes it for retrieval, search, revisions, and sync state. Every work log is saved locally before any remote operation. TimeTree synchronization is optional, disabled by default, and never treated as successful until the created memo has been read back and verified.
Project status: local storage, validation, reports, MCP transport, mock-provider synchronization, reconciliation, and failure recovery are covered by automated tests. Live TimeTree integration — including publication — has been verified end-to-end against an authorized account using the gated write-test in docs/LIVE_TIMETREE_VERIFICATION.md. The community endpoints are unofficial and can change; re-verify after upstream changes.
Table of contents
Related MCP server: worklog-telegram
Important TimeTree notice
TimeTree's official Connect API was discontinued in December 2023. This project does not implement a discontinued API and does not claim official TimeTree support.
The optional community provider uses the same unofficial web endpoints used by the reviewed
ehs208/TimeTree-MCP project at commit
3f77995f4d074364c6ffe14bb95a9d0c43a7c1d8. The adapter here is intentionally narrow: list
calendars, list memos, read one memo, and create one memo. It is not a copy of that project's broad
tool surface, and its installer is not used.
These endpoints are undocumented, may change without notice, and may be subject to TimeTree's terms of service. Use a private calendar you control, keep remote writes disabled until you have reviewed the behavior, and never use the project to bypass authentication, CAPTCHA, access controls, or rate limits.
Google sign-in accounts
This adapter authenticates in one of two ways:
Email/password —
PUT <TIMETREE_BASE_URL>/api/v1/auth/email/signinwithuidandpassword.Session cookie — reuse the
_session_idcookie from a browser session. This is the path for accounts that sign in with Google and have no TimeTree password.
There is no native Google OAuth flow. If your account was created with "Continue with Google" and you have never set a TimeTree password, use session-cookie mode:
Sign in to
timetreeapp.comin your own browser with Google.Open DevTools (
F12orCmd+Option+I) → Application → Cookies →https://timetreeapp.comand copy the Value of the cookie named_session_id. (Or, in the Network tab, open any authenticated request and copy the_session_id=...part of thecookie:request header.)Put that value in
TIMETREE_SESSION_COOKIE. The CSRF token is fetched automatically.
A session cookie is a bearer credential — anyone holding it is signed in as you. It expires, so you will need to copy a fresh one when it stops working. Keep it out of source control and logs, exactly like a password. When both are set, the session cookie takes precedence over email/password.
Alternatively, if TimeTree lets you set a password on a Google-linked account (check Account / Settings), you can use email/password mode instead.
The local-only tools (preview_daily_worklog, save_worklog, get_daily_worklog,
search_worklogs, generate_progress_report, get_sync_status) work with no TimeTree account at
all — only the remote read/write tools need auth.
Always keep TIMETREE_ENABLE_REMOTE_WRITES=false until you have read the
security and privacy section and the
gated live verification procedure.
What this server does
Validates and normalizes a daily work log with strict Zod schemas.
Previews the exact local Markdown and remote memo payload before anything is saved or sent.
Saves a canonical Markdown file and a transactional SQLite revision ledger locally.
Retrieves and searches saved work logs without contacting TimeTree.
Generates an attributed Markdown progress report and writes it to the local reports directory.
Optionally publishes one saved work log as one all-day TimeTree memo in one configured private calendar.
Reconciles before a retry, verifies every remote write by reading it back, and refuses to report remote success when the outcome is uncertain.
Requirements
Node.js 22.12 or newer (Node 24 is also supported).
npm.
Native build tooling for
better-sqlite3if a prebuilt binary is unavailable for your platform.macOS, Linux, or Windows.
The exact dependency versions are locked. package.json also pins install-script approvals for
better-sqlite3, esbuild, and fsevents; review those pins when upgrading dependencies.
The server uses stdio transport only. It does not open an HTTP port.
Installation
git clone https://github.com/gideon211/timetree-worklog-mcp.git
cd timetree-worklog-mcp
npm ci
npm run buildSanity checks:
npm test # 93 tests
npm run verify # typecheck + lint + format + test + build
npm audit # dependency vulnerabilitiesFor development without a build:
npm run dev # tsx src/index.tsThe server speaks MCP over stdin/stdout. Diagnostic logs go to stderr and are redacted.
Quick start with the mock provider
The mock provider is safe for local evaluation and does not contact TimeTree. Start here even if you intend to use TimeTree later.
Open examples/mock-mcp-config.json and replace the placeholder path with the absolute path to
dist/index.json your machine.Paste the
mcpServersblock into your MCP client's configuration (see MCP client configuration).Restart your MCP client. It should now expose 9 tools.
Call
preview_daily_worklog, thensave_worklog, thengenerate_progress_report.
Everything in this flow is local. No credentials are required and nothing is sent anywhere.
Connecting your TimeTree account
Read Google sign-in accounts first. Use
TIMETREE_SESSION_COOKIEfor a Google-only account, or email/password if TimeTree has given your account a password.
Step 1 — Start read-only
In your MCP client config, switch to the community provider. Keep writes disabled. If you signed up
with Google, use TIMETREE_SESSION_COOKIE instead of email/password (see
Google sign-in accounts):
"TIMETREE_PROVIDER": "community",
"TIMETREE_EMAIL": "your-account@example.com",
"TIMETREE_PASSWORD": "<from OS keychain or secret injection, never a committed file>",
"TIMETREE_ENABLE_REMOTE_WRITES": "false"Or, for a Google account:
"TIMETREE_PROVIDER": "community",
"TIMETREE_SESSION_COOKIE": "<_session_id value from your browser>",
"TIMETREE_ENABLE_REMOTE_WRITES": "false"Restart the client and call list_calendars. This is read-only. It returns the calendars
visible to your account.
If sign-in fails with an authentication error, your email/password pair is wrong or the account cannot use email/password sign-in. Do not keep retrying in a loop; the provider backs off and opens a circuit breaker after repeated failures.
Step 2 — Choose a private calendar
From list_calendars, pick a private calendar you control. Do not use a shared, family, team,
or public calendar. Set that single ID in the config:
"TIMETREE_CALENDAR_ID": "<chosen-private-calendar-id>"Restart the client and call get_sync_status. Confirm summary.health.status is ok and the
calendar is configured.
Step 3 — Preview and save locally
Call preview_daily_worklog, inspect the rendered Markdown and the remote note payload, then
call save_worklog. Keep the returned previewHash.
Step 4 — Enable writes and publish
Only now flip the gate:
"TIMETREE_ENABLE_REMOTE_WRITES": "true"Call publish_worklog with the previewHash from the current saved revision and
confirmation: "PUBLISH".
All of these must be true or the call refuses:
Remote writes are enabled.
A single private calendar is configured and exists for this account.
The preview hash matches the current saved revision.
No suspected secret patterns are detected in the content.
The confirmation literal is exactly
PUBLISH.
After creating the memo, the server reads it back, compares the stable work-log ID and the content
hash, and only then reports PUBLISHED. If it cannot verify, it reports UNCERTAIN and never
claims success.
Live verification before trusting it
Because the endpoints are unofficial and unverified in this repo, run the gated procedure in docs/LIVE_TIMETREE_VERIFICATION.md with a dedicated private test calendar and synthetic content before relying on live publication.
MCP client configuration
The server does not auto-load .env files. Configuration comes only from the environment block
in the client config, or from exported shell variables. Use .env.example as a
variable reference.
Client config locations (create or merge the mcpServers block):
Claude Desktop:
claude_desktop_config.jsonCursor / Windsurf / VS Code-style clients: their
mcp.jsonor equivalentGeneric: any client that launches an MCP server as a child process over stdio
Examples:
examples/mock-mcp-config.json — safe local evaluation.
examples/community-mcp-config.json — community provider with email/password, writes disabled.
examples/community-session-mcp-config.json — community provider using a browser session cookie (Google sign-in), writes disabled.
MCP client configurations commonly store secrets as plaintext. If your client supports environment injection, OS keychain integration, or a secret manager, use that instead of putting a password directly in a checked-in JSON file.
Configuration reference
Variable | Default | Purpose |
|
| Default IANA time zone for dates without an explicit timezone. |
| Platform application-data directory | Base directory for the database, archive, and reports. |
|
| SQLite ledger path. Use |
|
| Canonical Markdown archive. |
|
| Generated progress reports. |
|
|
|
|
|
|
|
| Unofficial TimeTree web base URL. |
| unset | TimeTree account email. Keep out of source control. |
| unset | TimeTree account password. Keep out of source control. |
| unset | Alt. auth: a browser |
| unset | The single private calendar permitted for memos. |
|
| Additional explicit gate for any remote write. |
|
| Maximum TimeTree requests per second. |
|
| Per-request timeout. |
|
| Retries for read-only requests only; writes are never retried blindly. |
|
| Maximum remote note length. The local archive is never truncated. |
|
| Maximum accepted upstream response body. |
Default data directories:
macOS:
~/Library/Application Support/timetree-worklog-mcpLinux:
$XDG_DATA_HOME/timetree-worklog-mcpor~/.local/share/timetree-worklog-mcpWindows:
%APPDATA%\timetree-worklog-mcp
The application creates directories with best-effort 0700 permissions and files with 0600
where the platform supports POSIX permissions.
Tool reference
The MCP surface is deliberately limited to these nine tools.
Tool | Local/remote | Purpose |
| Remote read | List calendars for setup. Requires credentials in community mode; does not require a calendar ID. |
| Local read | Validate and render the Markdown and remote payload without writing. |
| Local write | Save Markdown first, then commit the SQLite ledger transaction. |
| Local read | Retrieve by stable worklog ID or by date plus timezone. |
| Local read | Search text, date range, timezone, and sync state. |
| Local write | Build and write an attributed Markdown progress report. |
| Remote write | Create and verify one memo after all gates pass. |
| Local read | Show counts, per-worklog state, attempts, and provider health. |
| Remote read/write | Reconcile prior attempts; never performs a first publication. |
Every successful tool response uses an { "ok": true, "data": ... } envelope. Failures use
{ "ok": false, "error": { "code", "message", "retryable", "details?" } } and the MCP isError
flag. Unknown arguments are rejected at the schema boundary.
Daily workflows
Record a day's work
preview_daily_worklog— supply the facts the user actually provided. Do not invent dates, deadlines, completed work, decisions, or evidence.Inspect the rendered Markdown, the remote note, and any secret warnings.
save_worklog— writes the local record. Keep thepreviewHashif you may publish later.get_daily_worklog— verify the saved revision when needed.generate_progress_report— build an attributed report over a date range (max 366 days).
Publish to TimeTree
preview_daily_worklog— inspect theremotepayload.save_worklog— ensure the revision matches the preview.publish_worklog— pass the matchingpreviewHashandconfirmation: "PUBLISH".
Check and repair synchronization
get_sync_status— inspect counts, per-log state, attempts, and provider health.retry_pending_sync— defaults to a dry run that only lists what would happen.For a live retry, set
dryRun: falseandconfirmation: "RETRY"(max 10 logs per call).
After editing a published log
If the work log is edited after publication, the state becomes STALE. Republishing is blocked as a
CONFLICT because this server intentionally has no destructive update operation. Resolve the remote
memo manually if necessary. A publish_worklog call then reconciles without creating a memo and
clears the conflict if the recorded memo is gone. Inspect the calendar and call publish_worklog
again only if a new memo is intended.
Local data model
Stable identifier
A work log has one stable identifier per date and timezone:
wl_<YYYY-MM-DD>_<timezone-slug>Example: wl_2026-10-26_africa-accra.
Revisions increment when content changes. The identifier stays stable, and prior revisions remain in SQLite.
Markdown
The canonical archive is Markdown with YAML front matter:
<WORKLOG_ARCHIVE_DIR>/<YYYY>/<MM>/<YYYY-MM-DD>--<timezone-slug>.mdThe front matter contains the worklog ID, date, timezone, title, revision, content hash, timestamps, and synchronization metadata. The body contains executive summary, completed tasks, work in progress, blockers/risks, decisions, next actions, and evidence/source references.
SQLite
The ledger stores current worklogs, revision snapshots, synchronization state, sync attempts,
idempotency keys, remote memo references, and local events. Writes use WAL mode, foreign keys,
busy_timeout, and synchronous=FULL. The Markdown file is written atomically before the database
transaction commits; a failed transaction restores the previous archive file on a best-effort
basis.
Remote note
A remote memo title includes the stable ID:
Work Log 2026-10-26 [wl_2026-10-26_africa-accra]The note begins with machine-readable metadata:
Worklog-ID: wl_2026-10-26_africa-accra
Worklog-Date: 2026-10-26
Worklog-Timezone: Africa/Accra
Worklog-Revision: 1
Worklog-Hash: <sha256>If the note exceeds TIMETREE_REMOTE_MAX_CHARS, only the body is truncated. The metadata header is
retained so reconciliation can still verify identity and content.
Synchronization states
State | Meaning |
| Saved locally and eligible for publication. |
| A create attempt was durably recorded before the remote call. |
| A memo was read back and its ID and content hash matched. |
| The write failed with a retryable error and a known not-applied outcome. |
| The write failed permanently or the upstream rejected it. |
| The write outcome is unknown. Never assume success or failure. |
| Local content changed after a remote memo was recorded or a publication was attempted. |
| A memo with this worklog ID has different content, duplicates exist, or the expected memo disappeared. |
| Reserved for an operator-blocked condition. |
Uncertain writes
A timeout does not mean the memo was not created.
Do not call
publish_worklogagain.Call
retry_pending_syncwith its default dry-run mode. It lists memos in the configured calendar and compares the stable work-log ID and content hash.If a matching memo exists, the verified result is recorded as
PUBLISHEDand no duplicate is created.If a memo with the same ID but a different hash exists, the verified result is recorded as
CONFLICTand no duplicate is created.If the listing finds no memo, the dry run reports what a live retry would do but does not persist the absence or a disappeared-memo conflict. Only a live retry persists the absence and may create a memo from an uncertain or publishing attempt.
If the listing itself fails, the state remains uncertain and no write is attempted.
A live retry requires
dryRun: false,confirmation: "RETRY", writes enabled, and at most 10 work logs per call.CONFLICT,FAILED_PERMANENT, blocked states, and work logs that have never been published (NOT_PUBLISHED) are never retried byretry_pending_sync; a first publication must go throughpublish_worklogafter preview. After fixing the cause of aFAILED_PERMANENTrecord, an explicitpublish_worklogwith a matching preview may recover it; reconciliation still runs first.
Reconciliation uses the upstream memo listing. If the upstream service is eventually consistent, wait and reconcile again rather than creating a second memo.
Security and privacy
Remote writes are disabled by default; credentials are required only for the optional community provider and are read only from the process environment. No credentials are written to the archive, database, or logs.
Session cookies and CSRF tokens are held in memory for the provider instance only.
Diagnostic logs go to stderr and pass through a redacting logger. Secret-like values and credential fields are redacted.
Work-log content is scanned for common credential patterns. Publication is blocked if a suspected secret is detected, but this is a safety net, not a guarantee.
Only the configured calendar ID is accepted. A different calendar ID is rejected before a write.
Remote note size and upstream response size are bounded.
Read requests use bounded retries and exponential backoff. Writes are not retried after transport, timeout, server, or schema failures. A write may be replayed once after a 401/403 authentication/session rejection, which is treated as not applied; other retries are explicit and reconciled.
A circuit breaker opens after repeated upstream failures.
The project does not bypass authentication, CAPTCHA, access controls, or rate limits.
No HTTP listener is opened. MCP is stdio only.
Back up the data directory, protect it with OS permissions, and avoid syncing it to an untrusted location.
Operations and deployment
Running as a service
The server is a stdio child process, not a daemon. It runs under whatever MCP client launches it. To run it yourself for debugging:
npm start # node dist/index.jsIt will block on stdin waiting for MCP messages. Logs go to stderr.
Backups
Back up the entire data directory, which contains the Markdown archive, the SQLite database, and generated reports. The Markdown files are the durable record; the database is an index and ledger. There is no automatic reindex from Markdown after database loss, so losing the database without a backup means losing search, revision history, and sync state even though the Markdown files survive.
Upgrades
git pull
npm ci
npm run verify
npm run buildReview the dependency lockfile diff and the allowScripts pins before accepting upgrades.
One process per data directory
Publication and retry calls are serialized within one process. Multiple server processes sharing a database are not coordinated. Run one instance per data directory.
Troubleshooting
Sign-in fails with an authentication error. Your email/password pair is wrong, or the account cannot use email/password sign-in (for example, a Google-only account). See Google sign-in accounts. The adapter backs off and opens a circuit breaker after repeated failures, so do not retry in a loop.
Sign-in fails with a permission or 403 error. TimeTree blocked the sign-in. Do not attempt to bypass it. This project will not circumvent access controls, CAPTCHA, or rate limits.
list_calendars fails but local tools work.
Expected when credentials are missing or wrong. All local tools work with no TimeTree account. Only
the remote read/write tools need credentials.
publish_worklog returns PREVIEW_REQUIRED.
The saved revision changed after you previewed it, or it changed while publication was being
prepared. Run preview_daily_worklog again, review, save, and use the new hash.
A publish returned UNCERTAIN.
Do not publish again. Follow Uncertain writes. The server reconciles before any
retry so it never creates a duplicate.
get_sync_status shows CONFLICT.
A remote memo exists with different content, duplicates exist, or the expected memo disappeared.
Resolve it manually in the calendar, then use an explicit publish_worklog to reconcile and clear.
The remote note is truncated.
Only the body is truncated, and only when it exceeds TIMETREE_REMOTE_MAX_CHARS. The metadata header
is always retained. The local archive is never truncated.
Server does not appear in the MCP client.
Confirm the command is node and args[0] is the absolute path to dist/index.js, then restart
the client. Check that npm run build has been run so dist/index.js exists.
Testing
npm run typecheck
npm run lint
npm run format
npm test
npm run build
npm run test:coverage
npm auditThe automated suite uses the mock provider and temporary directories. It covers:
invalid inputs, dates, timezones, evidence references, and secret detection;
local save, retrieval, search, report generation, revisions, and idempotency;
missing credentials, auth/session behavior, rate limiting, schema changes, and timeouts in the community adapter using a fake
fetch;publish gates, duplicate prevention, uncertain pre-write and post-write timeouts, conflicts, restart recovery, and retry policy;
MCP schema boundaries and a real stdio client/server round trip.
Gated live smoke test
The live smoke test is read-only, requires explicit opt-in, and is not part of npm test. Use
either email/password or a session cookie (for Google-only accounts):
TIMETREE_LIVE_SMOKE=1 \
TIMETREE_EMAIL="..." \
TIMETREE_PASSWORD="..." \
npm run test:liveTIMETREE_LIVE_SMOKE=1 \
TIMETREE_SESSION_COOKIE="<session-value>" \
npm run test:liveIt authenticates, lists calendars, and prints only a summary. It does not print the password, session
cookie, CSRF token, or note contents. Add -- --include-memos and set
TIMETREE_CALENDAR_ID to also count memos in that one calendar. The full authorization, write-test,
and cleanup procedure is in
docs/LIVE_TIMETREE_VERIFICATION.md.
Gated live write test
Live publication is verified by a separate, explicitly gated script. It creates exactly one
clearly-labeled synthetic memo, verifies it by reading it back, confirms re-publication is
idempotent (no duplicate), and prints only summaries. It is not part of npm test and never runs
without opt-in:
TIMETREE_LIVE_WRITE=1 \
TIMETREE_SESSION_COOKIE="<session-value>" \
npx tsx tests/live/write-test.tsThere is no delete tool, so the single test memo must be removed manually in the TimeTree app afterward. Do not point this at a shared, family, team, or production calendar.
Known limitations
Live TimeTree publication is unverified in this repository.
The TimeTree community endpoints are unofficial and can change or stop working.
No native Google OAuth. Google-only accounts must use session-cookie mode (
TIMETREE_SESSION_COOKIE), which relies on a browser-captured bearer cookie that expires. No multi-account session management.No memo update or delete operation is exposed. Editing a published work log results in
STALEand thenCONFLICTrather than a remote update.One configured calendar per server instance.
No attachments, checklists, attendees, reminders, or recurring memos.
No background scheduler; all actions are MCP calls.
Run one server process per data directory. Publication and retry calls are serialized within a process, but cross-process coordination is outside this project.
Publication re-checks the local content hash after reconciliation and again after read-back. A local save that lands during the remote request leaves the memo representing the previous revision, and the state is marked
STALEimmediately.Progress reports are limited to 366 calendar days per request.
Search uses SQLite FTS5 when available and falls back to
LIKEotherwise.There is no automatic reindex of the SQLite ledger from the Markdown archive after database loss. Back up both, and treat the Markdown files as the durable record.
Documentation
License
MIT. See LICENSE. TimeTree is a trademark of its respective owner. This project is not affiliated with or endorsed by TimeTree.
Available Tools
9 toolsgenerate_progress_reportGenerate a progress reportA
Build a Markdown progress report from saved local work logs for an explicit date range and timezone. The report attributes every item to its worklog ID and date, distinguishes verified evidence from user-reported statements, and writes a local report file. It is limited to 366 calendar days per request and does not invent missing work, decisions, blockers, deadlines or completion.
Inputs: to (required), from (required), timezone. Returns: ok, data, error
get_daily_worklogGet a saved daily work logARead-onlyIdempotent
Read a saved work log from the local Markdown archive and SQLite ledger by worklogId or by date plus timezone. This is a local read and does not contact TimeTree.
Inputs: date, timezone, worklogId, includeMarkdown. Returns: ok, data, error
get_sync_statusGet work-log sync statusARead-onlyIdempotent
Read local synchronization state, counts, attempt history and provider health. Without a worklogId or date it returns an aggregate summary. It never writes and does not call TimeTree.
Inputs: date, timezone, worklogId. Returns: ok, data, error
list_calendarsList TimeTree calendarsARead-onlyIdempotent
Read-only. Lists calendars available to the configured TimeTree account. Requires local credentials but never writes. Use this to find the one private calendar ID to configure; no destructive calendar operation is exposed.
Inputs: no named parameters. Returns: ok, data, error
preview_daily_worklogPreview a daily work logARead-onlyIdempotent
Validate and render a daily work log without saving or contacting TimeTree. Returns the full local Markdown, the exact remote memo title/note that a later publish would send, warnings for suspected secrets, and the previewHash required by publish_worklog. Never invents completion, dates, deadlines, decisions, or evidence.
Inputs: date (required), executiveSummary (required), title, blockers, +6 more. Returns: ok, data, error
publish_worklogPublish a work log to TimeTreeA
Explicit remote write. Publishes a saved work log as one all-day TimeTree memo in the single configured private calendar. Requires remote writes enabled, credentials, a previewHash that matches the current saved revision, no suspected secrets, and confirmation PUBLISH. It reconciles first to avoid duplicates, verifies the created memo by reading it back, and returns UNCERTAIN or CONFLICT instead of claiming success. No destructive or update operation is provided.
Inputs: worklogId (required), previewHash (required), confirmation (required), calendarId. Returns: ok, data, error
retry_pending_syncRetry pending work-log synchronizationA
Reconcile pending, failed or uncertain work logs before any retry. Defaults to dryRun: true; a dry run records a verified memo or conflict but does not persist an empty listing as absence. A live retry requires remote writes enabled and confirmation RETRY, is limited to 10 work logs per call, never retries CONFLICT, FAILED_PERMANENT, BLOCKED or NOT_PUBLISHED records, and never performs a first publication. Re-verifies every created memo. Never assume a timeout means no memo.
Inputs: dryRun, worklogId, confirmation. Returns: ok, data, error
save_worklogSave a daily work log locallyAIdempotent
Save the work log to the local Markdown archive and SQLite ledger before any remote operation. This tool never contacts TimeTree. Saves are revisioned by date and timezone; identical content is idempotent. Use the returned previewHash with publish_worklog only after reviewing the preview.
Inputs: date (required), executiveSummary (required), title, blockers, +7 more. Returns: ok, data, error
search_worklogsSearch saved work logsARead-onlyIdempotent
Search the local work-log archive by text, date range, timezone and sync state. Results include matching worklog IDs, dates, sync states and short snippets. This is a local read.
Inputs: to, from, limit, query, +3 more. Returns: ok, data, error
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 9 tools
Each tool maps to a distinct stage of the worklog lifecycle (preview, save, get, search, publish, sync status, retry), and descriptions clarify the read-only vs remote-write boundaries. Minor overlap between preview_daily_worklog and save_worklog, and between get_sync_status and search_worklogs' sync-state filtering, but the descriptions disambiguate well.
All tools use snake_case verb_noun patterns consistently (list_calendars, save_worklog, publish_worklog, retry_pending_sync). Minor deviation: 'daily' appears in preview_daily_worklog and get_daily_worklog but not in save_worklog, slightly breaking the resource-naming symmetry.
Nine tools form a tight, well-scoped set covering the full local-to-remote worklog flow. Every tool has a clear, non-redundant role with no filler.
Covers calendar discovery, local preview/save/read/search, reporting, publishing, sync status and retry — strong lifecycle coverage. Gaps exist (no delete/archive removal for local worklogs, no unpublish or update of published memos), but these appear to be intentional safety omissions rather than dead ends.
Related MCP Connectors
Privacy-first work tracking with summaries, reports, coaching, and AI-ready long-term memory.
A self-hostable feed of reminders, learnings and work that Claude and ChatGPT can read and write
Personal context for every AI: search, read, and write back to your private Markdown library.
ADHD system of record for agents: tasks, goals, loops, calendar, focus stats.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables recording, querying, and summarizing daily work entries with tags using a local SQLite database. Supports work logging, search, timeline queries, tag management, and automated reminders for tracking daily tasks.-
- FlicenseNot gradedqualityCmaintenanceLogs work entries to daily Markdown files and sends summaries to Telegram automatically at 11 PM or on demand.-

workhorse-ai-mcpofficial
AlicenseNot gradedqualityBmaintenanceProvides an append-only SQLite journal for orchestrator/worker AI workflows, enabling delegation, reporting, verification, and tracking of tasks with built-in search and optional cloud sync.106 npmMIT- AlicenseNot gradedqualityCmaintenanceEnables developers to maintain a local engineering journal, log work manually or from git history, and let AI assistants query, summarize, and draft standup updates, changelogs, and retro notes.MIT