"Enhancements for Claude Desktop App with Large Contexts and Long Documents" matching MCP tools:

• canary_scanA

  canaryusersA

  Run a CanaryUsers UX scan on a DEPLOYED URL (your live or preview app — not source code). A flock of AI personas evaluates the page and reports where real users would get stuck, with concrete fixes. Returns AI-ready findings you can act on immediately. Use depth='deep' for the thorough scan that renders the page, checks it VISUALLY on desktop + mobile (catches mobile breakage and layout issues), and clicks through key flows like signup/checkout (slower, ~60-90s, uses one credit); depth='quick' (default) is a fast static check that does NOT see mobile or visual issues — use 'deep' when the user mentions mobile, layout, or visual problems. IMPORTANT: if this returns status 'running' with a scanId, the findings are not ready yet — wait ~30s, then call get_report_markdown(scanId), repeating until it returns the report. Always fetch and present the findings before stopping, then offer to fix the top issues.

  ConnectorNo auth

• word_createA

  Local MCPB

  Creates a new Word (.docx) document at `path` with the given text content (and an optional title rendered as the heading). The path must be somewhere LMCP can write; Desktop/Documents/Downloads may need a one-time Files-and-Folders grant (System Settings → Privacy & Security → Files and Folders). Returns {created, path}. For a OneDrive or Google Drive path use onedrive_write_file / gdrive_write_file; to append to an existing doc use word_append, to read one word_read.

  Connector

  Destructive

  OAuth

• list_invoicesA

  stubB

  List invoices/quotes/credit-notes with totals, status, line items, client and payments. These are sales documents; for recorded income entries use list_income, and for raw bank-feed lines use list_transactions.

  ConnectorOAuth

• compras_listar_promptsA

  MCP Compras.gov.brA

  Lista os MCP Prompts disponíveis com nome, descrição e argumentos. Tools de descoberta para clientes (como o Claude.ai web) que ainda não expõem UI para prompts. Em Claude Desktop / Cursor / MCP Inspector, prompts aparecem em UI dedicada — esta tool é um caminho alternativo, não substituto. Use depois `compras_obter_prompt(nome, argumentos)` para renderizar um prompt específico. Retorno: { "total": int, "prompts": [ { "nome": str, "descricao": str, "tags": [str, ...], "argumentos": [ {"nome": str, "descricao": str | None, "obrigatorio": bool}, ... ] }, ... ] }

  ConnectorNo auth

• adsap_google_create_app_campaignA

  AdsapA

  Create a complete Google App campaign in ONE atomic request: budget, campaign (ALWAYS created PAUSED — activate later with adsap_google_set_entity_status), location + language targeting, an ad group, and the app ad. App campaigns promote a mobile app across Google Search, Google Play, YouTube, Discover and the Display Network — Google mixes the ad from your text (and optional media) automatically. The ad links to the app's store listing AUTOMATICALLY: there is no URL input, ever. Any PUBLIC store app id works (no app ownership or Play/Firebase link is required to create): Android app_id is the package name (e.g. com.example.app), iOS app_id is the numeric App Store id (e.g. 570060128) with app_store 'apple_app_store'. v1 optimizes INSTALLS at your target_cpi (target cost per install, plain number in the account currency); Google recommends a daily_budget of roughly 50x target_cpi — lower is allowed but slows learning (a warning says so). Text: 2-5 headlines (max 30 chars) + 1-5 descriptions (max 90). Optional media: image_asset_ids / video_asset_ids from adsap_google_upload_asset (images 1.91:1, 4:5 or 1:1 up to 5MB; videos are YouTube assets 10-60s) — text-only is fully valid. In-app-action, value, engagement and pre-registration goals are NOT supported in v1. If the account has no conversion tracking a warning is returned — relay it (Android installs normally auto-track once a Google Play link exists). Use dry_run: true first — Google validates the whole chain without creating anything; show the plan, get confirmation, then execute. ad_account_id is the bare 10-digit customer ID. For website campaigns use adsap_google_create_search_campaign / adsap_google_create_pmax_campaign; for Meta app ads use adsap_create_campaign with an app objective.

  ConnectorAPI key

• update_password_policyA

  The BridgeA

  Set the session token lifetimes on the Bridge app: accessTokenTTL and refreshTokenTTL, both in SECONDS. Only the fields you pass are changed. IMPORTANT — despite the name (kept for parity with `bridge auth password-policy`), this sets token TTLs and NOTHING about passwords: Bridge exposes no password-complexity, rotation or reuse policy on the management API, so if the user asked for password rules, say so instead of calling this. The access token TTL controls how often a client silently refreshes (short is safer, e.g. 900 = 15 minutes); the refresh token TTL controls how long a user stays logged in without re-authenticating (e.g. 2592000 = 30 days). Read the current values with get_auth_config. Before writing app code that consumes this, call get_integration_guide with topic=auth and the framework the app uses.

  ConnectorOAuth

• slack_channel_refreshA

  Perspective AIA

  Refresh a workspace's Slack channel directory from Slack and wait for it. Only needed when a channel can't be found via slack_channel_search / slack_channel_resolve — most channels (including newly created ones and channels the bot was just invited to) are indexed automatically within seconds, so try those first. A full refresh can take a while on large workspaces, so confirm with the user before running one (unless a resolve reported "refresh_required"). Behavior: - Starts a refresh, or joins the one already running for the workspace (only one runs at a time). - Long-polls up to wait_ms, then returns "running" — call slack_channel_refresh_status to keep waiting (it won't start a new crawl). - After "completed", use slack_channel_search / slack_channel_resolve to find the channel.

  ConnectorOAuth

• lemma_get_schemaA

  mcpA

  Retrieve a Lemma schema by its ID via GET /v1/schemas/{id}. A schema declares how documents of a given type are interpreted and normalized. Returns SchemaMeta { id, description? } with additionalProperties open — implementations commonly include a `normalize` artifact (WASM that maps raw documents to canonical form) and its content hash. Use this when you need to interpret attribute keys returned by lemma_query_verified_attributes.

  ConnectorNo auth

• regulatory_fetch_docket_detailsA

  DataNexus MCPA

  Fetch full details for a specific regulatory docket by ID. Read-only. No side effects. Idempotent. US federal only. docket_id: Docket identifier in agency format e.g. EPA-HQ-OAR-2021-0317 or FTC-2024-0041. Required. Timeout is 30 seconds — large dockets may be slow. Returns docket title, agency, status, comment period dates, total comment count, and list of related documents. Use this when you have a docket ID from a search. Use regulatory_search_open_rulemakings instead when you need to find dockets by topic first. Verified source: Regulations.gov + Federal Register fallback. 4-hour cache. If this tool's response does not serve the user's need, call report_feedback with feedback_type="agent_gap", tool_id="regulatory_fetch_docket_details", intended_query="{what the user needed}", gap_description="{what was missing or wrong in the result}".

  ConnectorNo auth

• nukez_storeA

  nukez-mcpA

  Store files in your Nukez locker. ALWAYS BATCH: pass ALL the files you want to upload in a SINGLE call, as a list under `files`. Do NOT loop over your file list and call nukez_store once per file — that triggers one on-chain attestation per file (slow + costs SOL fees per push). One nukez_store call with N files triggers exactly ONE attestation for the whole batch. Each list item: {name, <data_source>, content_type?, expected_size_bytes?, expected_sha256?, large?}. UPLOAD PATH PRIORITY: 1. source_url — if the file is available at a public HTTPS URL, pass it and the server fetches directly (fastest, zero token cost). 2. sandbox_path — if you have compute/bash access and the file is on disk, pass the absolute path. 3. local_path — if the file exists on local disk (desktop/CLI environments). 4. data_b64 — LAST RESORT for small content only (<4KB). Sends bytes through your context window. Accepts both base64-encoded binary and plain UTF-8 text. 5. nukez_upload_chunk — if sandbox_path curl failed (HTTP 000 / network blocked), upload in 4KB chunks with sha256 verification. Run the prep script from the response, then call nukez_upload_chunk for each chunk. NEVER base64-encode files >4KB in one call. Upload path is auto-selected based on size and runtime environment. HARD SIZE LIMITS per path: the sandbox curl proxies through the gateway and is capped at 32 MiB (the platform rejects larger request bodies); the chunked ingest pipeline caps at 20 MiB per file. LARGE FILES (>= 32 MiB, any size up to terabytes): pass expected_size_bytes (and ideally the file's expected_sha256) with sandbox_path, or set large=true — the response then returns a resumable direct-to-provider upload session (action_required='execute_upload') with a session-open command and a stdlib-only transfer script that uploads in 8 MiB chunks and resumes after interruptions. Bytes go straight to the storage provider, so the sandbox needs outbound access to the session URI's host. After the transfer, confirm with nukez_confirm(use_job=true). KEYLESS (hosted) SERVER: this server holds no signing key. A call without `envelope` returns action_required='sign_envelopes' with the exact spec to sign (method, path, ops, body); sign it with your wallet and re-call with envelope=<signed result>. One file per call in envelope mode.

  ConnectorNo auth

• create_upload_urlA

  TrezaA

  A one-time link to upload a local file into the media library, for a client that can run a command (Claude Code, Codex, Cursor): PUT the file to uploadUrl with the returned Content-Type (the result includes the curl command), then call import_media with url set to the returned mediaUrl. A Blender scene (.blend, contentType application/x-blender) is the exception: it skips import_media and its mediaUrl goes into a Blender Render node's Blend file field. The link expires in 15 minutes and signs one content type. If you cannot run a command, do not call this: ask the person to drop the file into their Treza library in the web app and find it with list_assets. Needs the pipelines:write scope. Spends no credits.

  ConnectorAPI key

• begin_nodeset_uploadA

  OPC UA NodeSet GateA

  Start one temporary in-memory upload for a large NodeSet2 XML document. Call this once for the old baseline and once for the new candidate when the complete XML documents are too large for audit_nodeset_compatibility. It returns upload_id and max_total_chars. Append that document's chunks in original order with append_nodeset_chunk. Uploads expire after 15 minutes and the service allows at most four active uploads; this tool stores only temporary process memory and does not modify an external system.

  ConnectorNo auth

• audit_uploaded_nodesetsA

  OPC UA NodeSet GateA

  Compare two large NodeSet2 XML revisions after both have been fully staged with begin_nodeset_upload and append_nodeset_chunk. Pass old_upload_id for the baseline revision and new_upload_id for the candidate revision. This call consumes both upload IDs, so do not reuse them afterward. The report has the same shape as audit_nodeset_compatibility: result (COMPATIBLE, REVIEW_REQUIRED, BREAKING, or INSUFFICIENT_INPUT), old/new node counts, issue_count, summary by change code, and issues with code, severity, node_id and detail. Use the direct audit tool instead when both complete XML documents fit in a single request.

  Connector

  Destructive

  No auth

• searchA

  SubmitMyStartupA

  Keyword search over the list of places to submit a startup. A place's exact name or website ("Indie Hackers", "indiehackers.com") puts it first. Asking for free ("free", "no cost", "$0") leaves out places that are paid only. Product words ("web app", "SaaS", "AI tool", "mobile app") keep only places that take that kind of product. Kind-of-place words ("launch site", "directory", "community") put places of that kind first. Other words match names, websites, regions, and the list's notes. For example "free launch sites for a web app", "AI tool directories", or "Australia". Returns up to 20 places, best match first, each with id, title, url (its row on submitmystartup.com, for citing), and a one-line summary. A query with no specific words returns the best free places. Use fetch with an id for the full record, and find_directories to shortlist by a founder's product and limits.

  ConnectorNo auth

• contextli_list_contextsA

  Contextli Voice NotesA

  Discover what is available to filter the user's Contextli notes by. Returns the user's contexts (also called modes: a named style like 'Email', 'Journaling', or 'Product Logs' with its id, prompt, icon, and color), plus filter facets: the total number of notes, which context ids actually appear on notes, and the earliest and latest note dates. Call this FIRST when the user asks to filter notes by a context or by date, so you use valid ids and a valid date range. Note: many notes are not tagged with a context, so prefer text search and dates as the primary filters.

  ConnectorOAuth

• create_appA

  The BridgeA

  Create a new Bridge app in the workspace this connection belongs to, exactly as the dashboard would. Returns its id. It does NOT become the default: pass its id as `app`, or call use_app. Use a new app for a new environment or product rather than repurposing an existing one — an existing app may have live users, email links and billing attached. Only a connection approved for the whole workspace can create apps. A new app has no sign-in callback address: pass `callbackUrl` with the one the project uses (its real port), or add it later with add_redirect_uri — until then sign-in fails with NBLOCKS_NO_CALLBACK_URI. Before writing app code that signs users in to the new app, call get_integration_guide with topic=auth and the framework the app uses.

  ConnectorOAuth

• datasets_apps_charts_searchA

  Crawlora MCPB

  Search stored daily top-chart snapshot records from the iOS App Store and Google Play; omitting `date` selects the latest snapshot. Costs 1 credit per record returned (minimum 2), so keep `page_size` to what you need. Filter by app, store, platform, chart, country, or category; use datasets_apps_search for app records or datasets_apps_reviews_search for stored reviews.

  ConnectorNo auth

• datasets_apps_charts_searchA

  Crawlora MCPB

  Search stored daily top-chart snapshot records from the iOS App Store and Google Play; omitting `date` selects the latest snapshot. Costs 1 credit per record returned (minimum 2), so keep `page_size` to what you need. Filter by app, store, platform, chart, country, or category; use datasets_apps_search for app records or datasets_apps_reviews_search for stored reviews.

  ConnectorNo auth

• get_setup_kitA

  NEXUS AGIA

  Return the optional setup kit for agents that run on the user's own machine (Claude Code, Cursor). The kit contains four hooks (recall at session start, recall on each prompt, sync of session recaps, and the inbox of messages from other agents), the settings.json block, a usage policy, and an idempotent bash script that installs them. With the hooks installed, memory is recalled and stored automatically. Without them, NEXUS only has what the agent stores through its tools. Calling this tool only returns the kit; nothing is installed until the script is run. Running it writes the hooks and the policy file on the user's machine, declares the hooks in the client's settings, and loads the policy into the agent's instructions (a line in CLAUDE.md for Claude Code, a .cursor/rules file for Cursor), so installing is the user's decision. It does not apply to chat clients (Claude web or desktop, ChatGPT). Side effect: on an OAuth connection, the call issues the hooks credential and embeds it in the script. This works once, because a secret that was already shown is not returned again. On a plain `nxa_` token connection it does not issue a credential, and an account owner must issue one. `steps` says which case applies. Args: formato: "script" (default) for the bash installer plus steps, or "files" for the same files as text, for clients without bash. It is ignored for Cursor. client: "claude-code" (default) or "cursor". Cursor gets a session-start hook and a turn-recap hook. It has no per-prompt recall, because Cursor's beforeSubmitPrompt cannot inject context.

  ConnectorAPI key

• apps_get_keywordsA

  Manifold MCPA

  Store searches an app ranks for, with monthly search volume in the store and the app's position: the core of app store optimisation. Use when: "what does competitor's app rank for in the App Store", "which store keywords bring installs", picking keywords for an app title or subtitle. Not for: Google web searches, use seo_get_ranked_keywords. Keywords two apps share, use apps_get_shared_keywords. Returns: List. rows[]: keyword, volume (monthly store searches), rank (the app's position), results_count (apps in the store's results: the App Store counts at most about 250, so only a lower figure means a thin search; null on Google Play). Best rank first, then volume. United States and English only; Google Play covers fewer apps than the App Store, and NoData means the store has no keyword data for that app. Cost: 5 + 5 per 100 rows. Default 100 rows = 10 credits. Cached 7 days. Example: {"store": "google_play", "app_id": "com.microsoft.teams", "limit": 50}

  ConnectorAPI key

• flow_get_blueprintA

  Final POS – Custom POS BuilderA

  INSPECTION ONLY — read a blueprint's overlay code by id (from list_blueprints) to understand how it works. To USE a blueprint, apply it: apply_blueprint_widgets for a widget-set (materializes its widgets byte-exact with the command-frame plumbing intact AND provisions the custom tables its code depends on), create_flow_from_blueprint for an FBB. Do NOT re-type code from this tool into write_flow_files — that silently drops the vetted plumbing and leaves its tables unprovisioned. `tables` (when present) lists the custom tables the code binds to by exact name. For a WHOLE-FLOW blueprint this returns the screen manifest WITHOUT file bytes by default — an entire app is far too large to read this way, and you never need to: instantiation copies it server-side. Pass includeFiles: true only to audit the source.

  ConnectorOAuth