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

• word_createA

  local-mcpA

  Creates a new Word (.docx) document at `path` with the given text content (and an optional title rendered as the heading). Requires confirm=true — called without it, returns a preview of what will be written instead of creating the file. The path must be somewhere Local MCP 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.

  ConnectorNo auth

• verify_identityA

  Stipple — Document Verification & ExtractionA

  Run an Australian identity check over a SET of identity documents. A vision model reads each document (which ID it is, which fields it shows — name/photo/address/signature — and its issue date); a deterministic engine then tallies them against a scheme and reports whether identity is established, and exactly what's still missing if not. USE THIS WHEN someone needs to verify a person's identity from their documents — KYC / onboarding / "do these documents satisfy the 100-point check?" Pass ALL the person's documents together (a passport alone is 70 points; the check needs >= 100). `documents` is a list, each item ONE of: {"url": "https://..."} (public link, fetched server-side) or {"bytes_b64": "...", "filename": "passport.pdf"} (inline). Up to 10. `scheme`: "afp_100_point" (points, default) or "austrac_safe_harbour" (category combinations). Returns `{established, points/target or satisfied_path, documents[] (per-document: type, fields shown, whether it counted and why-not), reason, accepts, ...}`. This is identity COVERAGE, not a forgery judgment — run verify_document for authenticity. Documents are never stored. Costs 2 credit(s) per call.

  ConnectorNo auth

• analyze_title_documentsA

  Curagent Title RiskA

  Analyzes Florida real estate title documents and returns a structured risk report: a risk score (0-100, higher is safer) and level, findings with verbatim evidence from the documents and guidance on how to cure each one, and the Schedule B-I requirements extracted from any title commitment in the package. Accepts one or more PDF documents as base64 strings (deed, title commitment, mortgage, closing disclosure, survey, payoff letter, HOA estoppel, etc.), including a single PDF containing a whole closing package, which is split into its constituent instruments. Submitting several documents together also enables cross-document checks for contradictions in parcel ID, address, and party names. Uses one of your 3 free analyses (sandbox tier) or 1 credit (paid tiers). Florida properties only — call check_coverage first to confirm scope, and get_credit_balance to confirm available credits.

  ConnectorNo auth

• list_canvasA

  AgentPlaybooksA

  List canvas documents in a workflow run. Canvas documents are collaborative markdown files that multiple agents can edit in parallel. Omit run_id to list documents across all runs. Read-only. Use read_canvas for content and get_canvas_toc for section IDs. There is no get_run; list_runs returns run records. Pass playbook_id as the UUID or GUID of the playbook this call should target.

  ConnectorNo auth

• fetchA

  FirmTape - SPX dealer positioningA

  Retrieve the full text of one FirmTape document by the id `search` returned: `session:YYYY-MM-DD` for a finished trading session, `page:/path` for an explainer or research page. A FirmTape URL or a bare YYYY-MM-DD trading day is accepted too. Use when: you hold an id from `search`, or a client that only speaks search/fetch (ChatGPT). Not for: structured numbers — get_session and get_levels answer the same day with fields instead of prose. Limits: public FirmTape documents only; long pages are truncated with a link to the rest.

  ConnectorNo auth

• 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

• convert_from_urlA

  BotverseA

  Offload a document conversion to Botverse — runs server-side in seconds, returns a download link, and frees you to continue with other tasks while it processes. Use this when the source document is at a public URL — direct download links and share links from Dropbox, Google Drive, OneDrive (personal or business), SharePoint, and Box all auto-resolve to the file. If you already have the content as a string, use convert_content instead — no upload step needed. Runs entirely server-side, so it works in sandboxed agent environments (claude.ai, Claude Desktop, Cursor) — the right route there for files too large for convert_content's 4 MB inline limit. Supported inputs: md, html, rst, txt, docx. Supported outputs: docx (Word), pdf, html, txt, md, rst, xlsx (tables extracted). Returns a job_id immediately. Poll get_job_status every 5s until 'complete', then get_output_content (inline, sandbox-safe) or get_download_url (S3 link). Flat fee $0.05 per file.

  ConnectorNo auth

• list_documentsA

  Velvoite — EU Financial Regulatory ComplianceA

  Browse regulatory documents with filters and pagination. Returns a paginated list of documents with summaries, tags, doc_purpose (regulation_text, enforcement, reference, irrelevant), and doc_jurisdictions (e.g. ['eu'], ['fi'], ['de']). Use this for filtered browsing (e.g. all DORA documents from the last 30 days). Use search_regulations instead when you have specific keywords to search for. Args: source: Filter by data source code: eur_lex, eba, esma, eiopa, finfsa, bafin. regulation: Filter by regulation family code: dora, mica, aml, mifid2, crd_crr, psd, csrd, sfdr, ai_act, emir, solvency, idd, gdpr. entity_type: Filter by entity type: credit_institution, payment_institution, e_money, investment_firm, fund_manager, aifm, insurance, pension, crypto_service, crowdfunding, credit_servicer. urgency_max: Max urgency level (1=critical, 2=high, 3=medium, 4=low, 5=informational). E.g. 2 returns only critical and high urgency items. days: Only return documents from the last N days (1-365). page: Page number (default 1). per_page: Results per page (default 20, max 100).

  ConnectorNo auth

• echo_facility_searchA

  Epa EchoA

  Search EPA-regulated facilities by name, state, ZIP code, city, or industry code. facility_name uses a case-insensitive starts-with match; prepend % for a contains search (e.g., "%Exxon%" finds any facility with "Exxon" in its name). Combine at least two filters — a bare state is rejected upstream for large states ({state: "TX"} alone matches ~344,000 facilities and errors). Good queries: {facility_name: "%Exxon%", state: "TX"}, {city: "Baytown", state: "TX"}, {zip: "94025"}, {naics: "3251", state: "TX"}. Returns facility IDs, addresses, lat/long, compliance status, inspection/enforcement counts, and total penalties.

  ConnectorNo auth

• word_appendA

  local-mcpA

  Appends text to the end of an existing Word (.docx) document at `path`, preserving the document's existing content and formatting. Requires confirm=true — called without it, returns a preview instead of modifying the file. Same file-access rules as word_create (Desktop/Documents/Downloads may need a Files-and-Folders grant). Returns {appended, chars_appended, path}. To create a new document use word_create; to read one use word_read.

  ConnectorNo auth

• ris_track_changesA

  ris-austria-mcp-serverA

  Track every document added or changed in one RIS application within an exact date window (changed_from/changed_to), optionally including deletions (include_deleted) — the delta-sync and monitoring primitive for mirrors and watchers, and the only surface that reports removals. Unlike the search tools’ coarse, additive-only changed_since intervals, this is exact-dated and deletion-aware. application accepts every RIS application code listed by ris_list_reference topic applications, including BrKons, LrKons, Dsk, and BgblAuth. Each changed document comes back in a compact cross-class record — document_number (for ris_get_document), title, dates, binding_status, and rendition URLs — plus its last-changed date; removed documents come back as deleted records with a deletion timestamp. One application per call; page explicitly for large windows.

  ConnectorNo auth

• select_surfaceA

  mcpA

  For a repo with SEVERAL runnable parts, call this BEFORE plan_deploy. You enumerate the candidate surfaces (find every Dockerfile/Containerfile, OPEN each, classify by its EXPOSE + CMD — never by directory name) and pass them in; redu RANKS them with fixed rules (a standalone browser desktop/noVNC > a self-contained web app > a keys-required playground > an API > a headless worker > docs/examples). GUIDED: returns the ranked list to present to the user, who picks. YOLO: auto-selects the TOP-ranked surface. Then run plan_deploy on the chosen surface's path + http_port. (A single-surface repo doesn't need this.)

  ConnectorNo auth

• dropyour_read_app_filesA

  DropyourA

  Read what a GRADUATED app actually SERVES right now — not the seed captured before it graduated. Without path: the list of files in the served version, with their size, and whether each one is server code. With path: that file's content, INCLUDING server.js — which is deliberately never served to visitors. Use this before dropyour_replace: a graduated app is replaced WHOLE, so you need its current files to avoid overwriting your own work. Large files are truncated (truncated=true, bytes reports the real size); binary files are reported as binary rather than mangled. Tier 4 only — at tiers 1-3 what the drop serves IS what you published, so use dropyour_read_content.

  ConnectorNo auth

• oi.contexts.useA

  OiA

  Use Oi Contexts for a concrete task. This is the primary tool for requests like oi designer review this flow, oi ctx growth-lead inspect pricing, or $Oi context product-manager review this roadmap. Treat oi, and $Oi as equivalent invocation forms. When the user names one or more Contexts, pass the raw selector unchanged as contextId, including + multi-context selectors of up to 3 Contexts and @2 or @v2 version pins, for example head-of-product@3+gtm-strategist+staff-engineer. The selectors ctx, context, and contexts are reserved Context type selectors, not Context ids; strip them and use this Context path. The selectors workflow, workflows, and wf are reserved for Workflows, not Contexts; use the Workflow path instead of longer Context chains. Do not first list contexts or treat a missing list preview item as absent. Without contextId, Oi routes implicitly. Returns an execution-ready prompt with the user request appended under ## User Request. ## Plan and Billing Current organization plan: Business. Current limits: 10,000 seats; 10,000 private Guardrails; 10,000 private Skills; 10,000 private Contexts; 10,000 private Workflows; 10,000 Connections; 10,000 API keys; 1,000,000 Agent messages per day; 1,000,000 Agent messages per month. Billing and upgrades: https://app.oioioi.ai/dashboard/organization/billing. When a user asks for work that exceeds the current plan or an unavailable paid capability, do the portion available on the current plan, clearly say what is blocked by the plan, and include the billing link for upgrading. Do not invent exceptions, temporary limit increases, prices, or hidden capabilities.

  ConnectorOAuth

• convert_contentA

  BotverseA

  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.

  ConnectorNo auth

• prepare_consult_domain_expertA

  TasteA

  Get a humantaste.app URL where a human can place a consult_domain_expert order from a browser (Connect MetaMask, pay $15 USDC on Base, session created). Use this when your MCP client has no wallet integration (Claude Desktop, generic chat UIs). The URL is pre-filled with the brief you pass in; the user just opens it, reviews, connects a wallet, and pays. Returns the payment URL and the price. Free.

  ConnectorNo auth

• get_managed_services_pricing_catalogueA

  Tier1 IT AssessmentA

  Returns the current Tier1 standard managed-service package rates, licensing/add-on catalogue, optional wider-scope items, bundling notes (Microsoft app approvals and Huntress IDTR; ESET desktop with Huntress EDR), monthly-only vendor commitment rules, and pricing version. Also returns indicative low/high NZD price bands for email, managed computers, whole-of-business managed services, managed network, business internet, and migration projects, each with what the low and high ends look like and what is excluded, plus a whyTier1 rationale explaining how Tier1's commercial model differs. Use the bands to answer budget or comparison questions without exact scoping. A band with requiresQuote true (migration) is a rough sizing figure only and must be presented with that caveat, never as a comparable rate. Call this before estimating so product IDs are exact. Read-only; stores nothing; not a formal quote.

  ConnectorNo auth

• get_jobA

  FieldTranscriptA

  Check a transcription job. Returns status (queued / working / done / error) and metadata. Set include_transcript=true only once status is 'done' and you actually need the full text in context - transcripts of long videos are large.

  ConnectorNo auth

• get_download_urlA

  BotverseA

  Get a presigned HTTPS URL to download the completed output file. Call after get_job_status returns 'complete'. URL expires in 24 hours. NOTE: fetching this URL is a direct S3 download, which is BLOCKED in sandboxed agent environments (claude.ai, Claude Desktop, Cursor). If you are in a sandbox, use get_output_content instead to receive the bytes inline over the tool channel.

  ConnectorNo auth

• resize_appA

  DockholdA

  Change how much memory one app gets. Call this when an app is running out of memory (OOM) or the user asks to make an app bigger or smaller. memory_mb must be one of the sizes get_resource_usage reports under compute.steps_mb, and the new size has to fit your available compute pool (call get_resource_usage first). Applied with a zero-downtime rolling update. If this app has storage, it is stopped and started again instead, so it is unreachable for a few seconds.

  ConnectorNo auth