"How to take notes on my local machine and on Notion" matching MCP tools:

• notion_disconnectA

  Local MCPB

  Turns Notion off in Local MCP: its tools stop reading it until the user turns it back on from LMCP's icon → My apps → open the app's row → the account's Read · Send · Write. Local MCP holds no sign-in for Notion, so nothing is signed out: the Notion app stays signed in on this computer. No tool turns it back on.

  Connector

  Destructive

  OAuth

• set_exercise_noteA

  RepsA

  Use this when the user asks to add, change or clear their own note on an exercise, built-in or custom ("note on my bench: seat 4, pause on the chest"). The note is a short gym-floor cue the Reps app shows on the exercise and during a workout; a custom exercise's step-by-step how-to goes in `notes` on `update_custom_exercise` instead. Get the slug and the current `note` from `get_exercise_library`. `note` replaces the whole note (to add to it, send the old text plus the new); an empty `note` clears it. Applied at once, with no confirmation step, so use it when the user asks for the note or has just agreed to it, and say in one sentence what the note now says.

  Connector

  Destructive

  OAuth

• scalix_computer_set_ssh_keysA

  Scalix CloudA

  Replace the ssh keys authorised for root on a persistent Linux machine. This is how you revoke: send the list without the key you want gone, and on a running machine it stops working immediately. Sending an empty list removes every key. Not a patch — whatever you send becomes the whole list, so read the current keys from scalix_computer_list first if you mean to add one.

  Connector

  Destructive

  No auth

• update_load_test_notesA

  LoadsterA

  Replace the notes on a finished Load Test's Test Report — the only thing on a Load Test this surface edits. Ask the user before writing: notes belong to the user, and advising on a test never requires writing them. The text sent becomes the report's entire notes, so first read the current notes with get_load_test_report and preserve the user's content in what you send.

  Connector

  Destructive

  OAuth

• report_worktreesA

  RetascA

  MACHINE TOOL — your mcp-proxy calls this on its own; an agent never needs to. It reports git worktrees on `rtsc-NN/<slug>` branches that exist on this machine and that no live claim covers, so Retasc can SEE work somebody started without claiming it (RTSC-962). The server never reads git; the local proxy does, and reports. Each reported issue gets a PROVISIONAL HOLD: it becomes visible on `get_issue` / `list_issues` as `hold`, and automatic dispatch (`next_issue` / `next_batch`) withholds it, exactly as it skips another human's lane. A hold is NOT a lease — it has no token, `heartbeat`/`checkpoint`/`done` do not accept it, `check_claim` reports it as not held, and it lapses 60 minutes after the last report. Nothing refuses an explicit `claim_issue`: a named claim from ANY session converts the hold into a real claim, which is how the agent that forgot to claim gets its work back. Ignores anything already claimed, terminal, `work:false`, or outside this key's project.

  ConnectorAPI key

• list_cookidoo_recipesA

  ask.recipesA

  List the recipes the user created on Cookidoo, including ones sent there by send_to_thermomix, for "what is on my Bimby", "my Thermomix recipes", "read recipes from my Cookidoo". This is the Bimby side; list_saved is the ask.recipes side. Returns Cookidoo ids to pass to import_cookidoo_recipe. Names and links only until the user imports one.

  ConnectorOAuth

• packaging_checkA

  SKILL.md Lint by MoltlineA

  Validate a zip layout plan for a skill marketplace before packaging. FREE. Checks SKILL.md placement rules and flags junk files. Typical input {"file_paths": ["my-skill/SKILL.md", "my-skill/examples.md"], "marketplace": "agensi"} returns {"verdict": "pass" | "fail", "issues": ["..."], "skill_files_found": ["my-skill/SKILL.md"]}. Use on a planned file layout, before zipping. Not for the content of a skill file (lint_skill). Errors: on invalid, missing, or malformed input this tool never raises a protocol error; it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "file_paths is empty: list every file that will be inside the zip"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  ConnectorNo auth

• packaging_checkA

  SKILL.md LintA

  Validate a zip layout plan for a skill marketplace before packaging. FREE. Checks SKILL.md placement rules and flags junk files. Typical input {"file_paths": ["my-skill/SKILL.md", "my-skill/examples.md"], "marketplace": "agensi"} returns {"verdict": "pass" | "fail", "issues": ["..."], "skill_files_found": ["my-skill/SKILL.md"]}. Use on a planned file layout, before zipping. Not for the content of a skill file (lint_skill). Errors: on invalid, missing, or malformed input this tool never raises a protocol error; it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "file_paths is empty: list every file that will be inside the zip"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  ConnectorNo auth

• update_pageA

  HovercodeA

  Change an existing landing page without recreating it: edit its blocks, title, description, or colors, and publish/unpublish it. Use for 'fix the typo on my page', 'add a section', or 'take the page down'. If you pass `blocks`, provide the COMPLETE desired list (same {type, content} shape as build_page; include each block's `id` from get_page to keep it, omit to remove) — leaving `blocks` off keeps the existing blocks untouched. If the page is already published, edits are re-published so they go live; pass publish:false to take it offline.

  Connector

  Destructive

  OAuth

• list_required_credentialsA

  opencode-workbenchA

  List the credentials the profile references, which the target already provides, and how to acquire each missing one. Value-blind: it reads only whether each env var is set — no values, no network, no writes — via one read-only probe. Parameter semantics: `target` selects the machine (`local` or SSH) and its `home` sets the returned `template` path and the env file the presence check reads; there are no other parameters. Returns `present`/`missing` var-name arrays plus one guidance record per credential (`var`, `purpose`, `url`, `method`, `command`). Use it after plan_clone to see what would degrade; act on one credential with run_auth_flow.

  ConnectorNo auth

• list_required_credentialsA

  opencode-workbenchA

  List the credentials the profile references, which the target already provides, and how to acquire each missing one. Value-blind: it reads only whether each env var is set — no values, no network, no writes — via one read-only probe. Parameter semantics: `target` selects the machine (`local` or SSH) and its `home` sets the returned `template` path and the env file the presence check reads; there are no other parameters. Returns `present`/`missing` var-name arrays plus one guidance record per credential (`var`, `purpose`, `url`, `method`, `command`). Use it after plan_clone to see what would degrade; act on one credential with run_auth_flow.

  ConnectorNo auth

• well_post_notion_commentA

  WellA

  Posts one reply to a Notion page, as a comment. Pass `discussion_id` to reply inside an existing comment thread (the thread the member's request arrived in); pass only `page_id` to start a fresh top-level comment on a page that carries none yet. Call this only after the person confirmed the exact reply text — it posts at once, with no draft step of its own, and it is visible to everyone who can see the page. With no Notion connector live in this workspace, returns `posted: false` and `error: "not_connected"`, and posts nothing. When Notion refuses the call, returns `posted: false` with `error: "provider_rejected_call"`, and when the call itself fails, `error: "provider_call_failed"`: in both cases nothing was posted, so never report a reply as sent.

  ConnectorNo auth

• upload_media_widgetA

  aicutA

  OPENS A FILE PICKER IN THIS CONVERSATION: the user chooses videos or photos from their computer and they land on their aicut account for every tool. CALL IT IMMEDIATELY, WITHOUT ASKING ANYTHING FIRST, the moment the user refers to a video or image file on their machine ('upscale the clip in my Downloads', 'use the picture on my desktop as the character'): do not ask for a path, size, format or URL, the picker asks for the file. A photo attached in chat does not reach aicut: ask the user to choose it again in the picker. WHEN NOT: the file is already a URL (public https, or from an earlier generation): pass it straight to the tool that needs it. Also not when you can run a shell command on their machine and no card renders (a terminal, a script, CI): use `upload_media`. If the user says they cannot see a picker, fall back to `upload_media` and do not call this again. IN THE SAME REPLY: say the picker is open (several files is fine) and to answer here once uploaded; ask what the task needs (what the clip shows, or what the file is for), and stop: no polling, no `upload_media` or `confirm_upload`. On the answer, take the newest url of that kind from `list_uploads` (none: upload unfinished, say so). TAKES MP4/MOV up to 50 MB and PNG/JPEG/WEBP up to 20 MB. Free (daily media allowance). OUTPUT: for the card: do not paste it.

  ConnectorOAuth

• check_relay_statusA

  SimceptorB

  Check if the user currently has an active Local Webhook Relay session (WebSocket tunnel) running. ALWAYS call this tool before setting webhookUrl on any mock if the user is working locally or might want local delivery. If active is true, you can use the 'simceptor://local/<path>' URL scheme to deliver webhooks directly to their local server. If active is false: NEVER generate or read the required Personal Access Token yourself — it must come from the user, who generates it from their dashboard ('Developer Keys', with the 'Local Webhook Relayer' scope). Once they share that token with you, how you proceed depends on whether you have direct local shell/terminal execution access on the SAME machine the user is developing on (e.g. Claude Code): if you do, you may run `npx @simceptor/cli listen --token <PAT> --to http://localhost:<port>` yourself — but first tell the user this opens a persistent background network tunnel from Simceptor's cloud to their machine, and how to stop it (the process can simply be killed) when they're done. If you do NOT have local shell access (e.g. a hosted/remote connector like the claude.ai web app), you cannot run this on the user's machine at all — instruct them to run the command in their own terminal instead, then call this tool again to confirm the session shows active.

  ConnectorAPI key

• check_local_viabilityA

  Local Model Suitability MCPA

  Checks whether a task can be handled by a local model instead of a cloud API. Call this BEFORE your agent routes any task to a cloud model — at the moment a task is ready to be sent and the model has not yet been selected. Use this when your agent is about to make a cloud inference call and wants to determine whether a local model could handle it at lower cost. Returns LOCAL/CLOUD/EITHER verdict with recommended model. If verdict is LOCAL, skip the cloud call entirely — saves cost on every routable inference call. Pass data_sensitivity=CONFIDENTIAL to force LOCAL verdict for tasks that must not leave the machine. Do not route to cloud without checking local viability first.

  ConnectorNo auth

• scaffold_localA

  mcpB

  OPTIONAL preflight: returns a podman-compose.yml + .env so the user can run the app (and a throwaway local Postgres) on THEIR machine before deploying to redu - to see it run / sanity-check the container. Requires local podman/podman-compose. It's a suggestion, not a gate - skip it and go straight to deploy_app any time. Honest caveat: the local Postgres is NOT the managed Postgres, so a green local run does not prove the prod DB wiring.

  ConnectorNo auth

• explain_when_issuers_reportA

  Credit GPS — Canadian creditA

  Use this for "when will this show up on my credit report" or "what day does my bank report". Returns how the monthly reporting cadence works in Canada, how long a change takes to appear on a file, and why an Equifax file and a TransUnion file for the same person differ. This bundled reference has no verified per-issuer transmission calendar and returns no exact reporting day. Returns bundled reference material, optionally filtered or calculated from inputs; does not fetch live data or change accounts.

  ConnectorNo auth

• scan_websiteA

  Build My Digital website scannerA

  Scan any public website and get Build My Digital's free report: a 0 to 100 score across SEO, AI search (GEO), local signals, trust, conversion and speed, every check with pass or fail, the fixes in priority order, and a separate agent-readiness score (can AI agents find, read and act on the site) that never changes the main score. Use when someone asks how good a business website is, why it is not being found, or what to fix first. UK local businesses are the focus but any public site works. Takes 5 to 40 seconds. Read-only: nothing on the scanned site is changed.

  ConnectorNo auth

• get_planA

  postnextA

  Return the user's plan + billing-date info: tier, renewal date, trial end date, and cancel-at-period-end state. Call when the user asks "when does my plan renew?", "how many days left on my trial?", or "is my subscription cancelling?". For quotas and usage (channels, AI credits, posts), call `get_plan_limits` instead — this tool is purely about plan identity and billing dates.

  ConnectorAPI key

• get_upload_linkA

  ScanSing: sheet music to MusicXMLA

  A one-off URL to upload a local file to and have it recognised, for when the file is on the user's machine and this server is remote. Run the returned `command` in a shell on that machine (with the file's path in place of FILE): it uploads the file, waits for the recognition (seconds to minutes) and prints its summary with `id`. Then use get_musicxml, describe_score etc. with that id. The URL works once, within 15 minutes; for another file ask for another link. Not for a file attached to the chat: pass that to recognize_sheet_music as `attachment`.

  ConnectorAPI key

• save_edit_styleA

  IgnixA

  Save this workspace's edit style; it REPLACES the one saved before. Only when the user asked for their style to be learned (or to change it). How: run `ignix-editor style measure <2-3 of their videos> --speech --stills <folder> -o style.json` on their computer, LOOK at the stills it leaves, and pass `version`, `videos`, `measured` and `summary` exactly as the command printed them (never `perVideo`: it holds local file paths). In `look` describe in a few words what you SAW and the numbers cannot say: typography, captions, animations, transitions, soundEffects, hook, pacing, notes (e.g. animations: "word-by-word captions that pop in, a zoom on every key phrase, emoji stickers"; soundEffects: "a whoosh on each cut, a pop when a text appears"). The measurement cannot hear a sound effect mixed under a continuous voice and music: if it reports none on videos with voice, ASK the user whether they use sound effects and which, and write that in soundEffects instead of "none". Show the user the summary and your look notes before saving. The videos never leave their computer.

  Connector

  Destructive

  OAuth