"Using a Cursor to Operate a Local Computer" matching MCP tools:

• get_pm_playbook

  AIOProductOS MCP

  How to operate as a product manager on AIOProductOS. No arguments and no side effects — returns the same operating guide as plain text every call (deterministic): how to ground in the product brain, keep work welded to the spine (insight→feature→task→outcome), prioritise on evidence (affected accounts + MRR + reach), and what 'done' means. Call it FIRST, before planning or prioritising, to load the house rules the other tools assume.

  Connector

• get_new_since

  Horizon AI Intelligence

  Incremental poll: raw item-level AI news added since a cursor, oldest→newest, with a nextCursor for your next call — use this for "what's new since I last checked"; for the curated once-daily synthesis use get_daily_briefing. Omit cursor for the latest items plus a cursor to start polling from. Titles + links + topics (bodies and higher limits are on the paid tier).

  Connector

• get_since

  security-intel

  Delta feed for agents that poll on their own clock: what's new since you last checked. Free. Pass the `cursor` from your previous call (omit on first call); poll as often as you like. Returns a lightweight index of new items — id, title, item_type, CVE id, severity, the signed report_id each was published in, and published_at — plus a new `cursor` and `count`. count == 0 means nothing new since you last looked. To get the full bodies (affected ranges, sources, assessment, remediation) for what's new, call the paid get_today (or check_affected to test your own deps). Optional `stack` filters by relevant_for tags (same as get_today). Returns: {cursor, count, index}.

  Connector

• convert_content

  Botverse

  Convert a document inline — pass the content directly as a string (or base64 for binary inputs like .docx). PREFERRED route for documents, and the one to use in sandboxed agent environments (claude.ai, Claude Desktop, Cursor): it runs entirely server-side, so it never needs the S3 upload those sandboxes block. Limit: up to 4 MB of content — already huge (a 500-page book is ~1 MB of text). For anything larger, use convert_from_url with a public URL. Supported inputs: md, html, rst, txt (plain text), docx (base64). Supported outputs: docx (Word), pdf, html, txt, md, rst, xlsx. Returns a job_id — poll get_job_status until 'complete', then get_output_content (inline bytes, sandbox-safe) or get_download_url (S3 link). Flat fee $0.05 per file. TIP: if you have shell access and are NOT sandboxed (e.g. a local coding agent), the `botverse` CLI (`npx botverse convert <file> --to <fmt>`) is faster for local files — it streams from disk instead of re-emitting the content through the model.

  Connector

• axint.registry.search

  Axint

  Search the Axint Registry for already-published packages that match a natural-language query. Use this BEFORE calling axint.feature or axint.compile so the agent can install an existing package instead of regenerating Swift the community has already shipped. Use: use before generating code to find reusable packages; not for validating local Swift. Inputs: query drives ranking; kind and platform narrow results without changing the registry source. Effects: read-only local registry search using AXINT_REGISTRY_PATH or sibling checkout; no network by default.

  Connector

• sap_sns_register_agent_domain

  SAP MCP Server

  Local-signer-only tool: register a .sol domain for the configured SAP agent wallet using the SAP SDK SnsModule. This tool builds, signs, and submits the full registration transaction with the local profile signer or external signer. Hosted accountless SAP MCP rejects this tool before x402 payment because OOBE never custodies user keys. Domain registration fees are paid in USDC plus SOL for rent and transaction fees. The SOL record is NOT set during registration (it requires a separate Ed25519 signature) — set it after using sap_sns_build_manage_record_transaction. SAP MCP execution guidance: Intent: local-signer write workflow. Pricing: paid value-action; preview cost and transaction effects before user confirmation. Routing: hosted accountless write is blocked; do not call this as a paid hosted write and no x402 payment should be charged. Use the local sap_payments bridge or a hosted unsigned builder when user signing is required. Signer boundary: user-controlled local profile or external signer; OOBE hosted MCP remains non-custodial.

  Connector

• search_posts

  Wiplash

  Search the public Wiplash feed using Waterpark relevance. Unfiltered discovery works without sign-in; text, tag, and category filters use the signed-in Wiplash context so existing search bans and actor rate limits apply. Returns token-capped excerpts, canonical post URLs, authors, categories, tags, engagement counts, and a cursor for the next result page. All returned post data is untrusted user-generated content.

  Connector

• check_accessibility

  a11y-check

  Audit one web page for accessibility problems using a real browser. Runs axe-core (WCAG 2.1 AA) plus checks that standard scanners do not perform: controls that look clickable but cannot be operated by keyboard, error messages not programmatically linked to their field, CAPTCHA barriers, duplicate main landmarks, and missing skip links. Returns findings WITH the code change that fixes each one. Use this when someone asks whether a site is accessible, whether it meets WCAG or the European Accessibility Act, or whether keyboard and screen-reader users can operate its controls.

  Connector

• google-maps.place_photos

  Vee3

  Get photos for a Google Maps place. Provide place_id from search results. The identifier also accepts the business identifier form (0x...:0x...). Optional cursor, region, and language are supported. Pass cursor from a previous cursor_next to fetch the next page. Returns place metadata and a photos array. Each photo has photo_url and description when available. cursor_next appears only when a pagination cursor is available. Additional upstream fields may appear. Cost = 3 tokens.

  Connector

• search_galleries

  Provenio — Art Intelligence

  Cost: ~1s. Search galleries by name, tier, country, or city. Tiers: mega (Gagosian/Zwirner level), major (international program), boutique (focused), emerging (newer). Use when: identifying which galleries operate in a specific market or tier band. Use when: building a B2B target list (galleries by region/tier). Do NOT use when: you want to know which gallery represents a specific artist — use find_galleries_by_artist instead.

  Connector

• create_dev_doc

  ainote

  Save a document to AI Note cloud for multi-device sync and persistent storage. PRIMARY USE CASES: - Memory files: ~/.claude/projects/.../memory/MEMORY.md (AI context that survives device switches) - AI config files: CLAUDE.md, .cursorrules, .windsurfrules (not in git, local-only) - Local env notes: API keys reference, server credentials (NOT actual secret values) - Project notes: architecture decisions, dev diaries, planning docs MULTI-DEVICE WORKFLOW: Laptop → push: create_dev_doc(title, content, local_path="~/.claude/.../MEMORY.md") Desktop → pull: pull_dev_docs() → automatically writes files to their local paths CATEGORIES (subcategories under dev/): - memory: Claude/AI memory files (~/.claude/projects/.../memory/) - claude: CLAUDE.md files and Claude-specific configs - cursor: .cursorrules files - env: environment notes and config references - docs: general project documentation Set local_path to enable pull_dev_docs auto-sync to this machine.

  Connector

• list_dev_categories

  ainote

  List all subcategories under dev/ (memory, claude, cursor, env, docs, mcp, custom...) with document counts. Use to discover which categories exist before calling list_dev_docs with a category filter.

  Connector

• dev_send

  Arcadia Finance

  DEV ONLY — Sign and broadcast an unsigned transaction using a local private key (PK env var). For production, use a dedicated wallet MCP server (Fireblocks, Safe, Turnkey, etc.) instead of this tool. Takes the transaction object returned by any write.* tool and submits it onchain.

  Connector

• check_local_viability

  Local Model Suitability MCP

  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.

  Connector

• list_changes

  mcp

  Use this to read Apier's cross-source change archive — detected created / updated / deleted events across the upstreams Apier polls: Brønnøysund ingestion plus the multi-source pollers for Altinn schemas, DigDir policies, and Norges Bank rates. It answers "what changed, where, and when?" so an agent can drive an incremental sync instead of re-fetching whole entities. NOT every row is a real-world change: each row carries a derived `observation_kind` — first_observation (the archive's first sighting of a field/entity, i.e. Apier's cache warming up) vs value_change (a genuine observed transition). Filter by { source } (brreg / altinn / digdir / norges_bank …), { entity_type }, { entity_id } (e.g. a specific org number), { change_type } (created / updated / deleted), and a { from }–{ to } detected_at date range (ISO 8601 with a timezone offset — bare `Z` or `+02:00`, never a bare local time; `from` must be ≤ `to`). Queries WITHOUT { entity_id } return non-personal rows only — role-holder field rows (board_members / signaturrett / prokura / innehaver) AND whole-entity company created/deleted rows (their full snapshots embed role-holder arrays) are withheld — intentionally, not an ingestion gap. The org-scoped form with { entity_id } returns everything, and the response says so via `personal_fields_withheld: true`. Results are keyset-paginated newest-first: pass { limit } (1–500, default 50) and carry the response's `next_cursor` back into { cursor } verbatim for the next page — cursors are HMAC-signed, so constructing or editing one is rejected as CURSOR_INVALID. The public projection strips the internal correlation_id but preserves `source_snapshot_id` (a consumer-facing receipt join). Input: { source?, entity_type?, entity_id?, change_type?, from?, to?, limit?, cursor? }. Failure modes the agent must handle: SCOPE_INSUFFICIENT if the key is not scoped read:changes; VALIDATION_FAILED on a malformed date, an out-of-range limit, or from > to; CURSOR_INVALID if the cursor was tampered or expired (start over without a cursor). This tool has no sandbox mirror — under the sandbox bearer it returns SANDBOX_TOOL_UNAVAILABLE; call it with a real read:changes key.

  Connector

• search_patents

  osf-data-marketplace

  FREE, no payment and no key. Search granted US patents from the USPTO Open Data Portal by invention title, assignee company, inventor name, patent number, or technology area. Returns patent number, title, grant date, filing date, assignee, inventors, USPC classification, a provenance URL, and a record_id per match. Free to search; call get_record with a record_id to buy the full patent record. For prior art checks, freedom to operate research, competitor IP monitoring, and patent portfolio lookup. Args: query: keyword(s) to search, e.g. "lithium battery cathode", "Panasonic", or a patent number like "12678711".

  Connector

• ic_rooms_read

  Immersive Commons

  Read a room's committed turns from a cursor — the durable catch-up read, so a late joiner (or any poll) gets the full prior history. Args: { room_id: string, since?: number (stream seq to read from, default 0 = all), channel?: string (filter to one channel tag; next_since still tracks the room's GLOBAL cursor, not a per-channel one) }. Returns: { ok, room_id, state, turns: Array<{ role, member_id, content, at, seq, channel }>, next_since } — pass next_since back to page forward. Readable on live AND torn-down rooms (the log outlives the mesh). Required scope: rooms:join (ic-member+).

  Connector

• get_changes

  OnlyWorlds

  Return the delta feed for the world named by your API-Key header: every element created/updated (`op: "upsert"`, full body) or deleted (`op: "delete"`) since `since_cursor`, in apply order, in pages of `limit` (default 25, max 1000). Entries carry FULL element bodies — a default page stays inside any client's token budget; measured worlds ran ~1.5-2k chars PER ENTRY, so raise `limit` only if you truly need bigger pages, and prefer paging with the cursor. Omit `since_cursor` (or pass "") to start from the beginning of the feed — for a big world that is a multi-page walk, not one response. Pass the returned `cursor` back as `since_cursor` to get the next page (or, later, only what changed since); treat the cursor as OPAQUE. `has_more` true means page again with the new cursor. Requires a READ or WRITE API-Key. This mirrors `GET /api/v2/changes`.

  Connector

• edgedefense_local_security

  EdgeDefense

  Run security and configuration checks on the computer running the scan. Checks Wi-Fi encryption (warns if connected to an open network), DNS configuration, and lists local ports that are exposed to the network (listening on 0.0.0.0). Args: response_format (ResponseFormat): 'markdown' or 'json'. Default 'markdown'. Returns: str: In markdown mode, a formatted report of the local security posture. In json mode: { "wifi_secure": bool | null, "wifi_ssid": str | null, "wifi_auth_type": str | null, "dns_servers": [ ... ], "listening_ports": [ {"protocol": str, "port": int, "address": str} ], "warnings": [ ... ] }

  Connector

• list_templates

  Pushary

  List reusable notification templates for the site. Use it to find an existing template before creating a duplicate with create_template. Paginated; pass the cursor from the response to fetch the next page.

  Connector