"Replicating ChatGPT Memory Functionality for Task Management and Skill Tracking" matching MCP tools:

• fetchA

  Penfield MemoryA

  [ChatGPT Connector compat] Fetch memory by ID. Exists to satisfy ChatGPT Deep Research's required `search`/`fetch` tool contract. Native MCP clients should fetch via `recall` + memory_id, or use the API's GET /memories/{id} endpoint directly. Returns a single memory with citation support (id, title, url, text fields). Args: id: Memory UUID to fetch ctx: MCP context Returns: Dict with id, title, url, text, metadata fields

  ConnectorOAuth

• start_sessionA

  PromptFaxA

  Use this first when a user wants to send or price a fax. PromptFax is built for irregular, pay-per-use outbound faxing: every real send requires a user-reviewed quote and Stripe payment authorization before transmission. MCP clients should set hostType to identify their host: chatgpt, claude, browser, or other. In ChatGPT, pass official files[] file parameters first when they are available so PromptFax can immediately import files[].download_url; never pass a raw file_id or local path as the document. The ChatGPT widget opens for destination entry, automatic quote creation, Stripe Checkout, status tracking, and Choose PDF from ChatGPT fallback when automatic attachment is unavailable or fails. If no document is attached, tell the user to attach a document in the widget. The widget does not provide a document preview step. Do not tell ChatGPT users to get a quote; after the widget has a document and valid destination, tell them to verify the price and use Pay & send when ready. Standards-compatible MCP Apps hosts use the inline PromptFax picker, and text-only clients use the hosted PromptFax session page or attach_document with a fetchable HTTPS URL. Do not call get_quote, checkout, or send_fax for a ChatGPT widget session unless the user explicitly asks for fallback behavior or the widget is unavailable. Use get_status only for a textual status refresh.

  ConnectorNo auth

• list_skillsA

  Power Automate MCP Server by Flow StudioA

  Skill bundles: groups of the tools listed here that are used together for one task (diagnose-connection-references, build-flow, debug-flow, monitor-flow, discover, governance). Returns each bundle's one-line description and tool names. Use it when unsure which tools fit a request; tool_search "skill:<name>" returns the bundle's full guidance and definitions. Non-billable.

  ConnectorNo auth

• get_agent_skillsA

  AgentPayA

  Fetch AgentPay skills index (skills.json) and install hints for Cursor, Claude Code, ChatGPT. Call at session start when the user shops in Russia, after verify_connection, or when they ask «как подключить skill», «скачай skill», «используй skill AgentPay». Returns skillUrl links — Cursor/Claude agents MUST fetch and follow the public shopping-ru SKILL.md (or store-specific skill from preferredStoreSkills). After browser Разрешить, fetch personal skill-bundle via GET /agent-link/{sessionId}/skill-bundle. Never improvise catalog rules when a skill URL is returned. If AGENTPAY_API_KEY required and you already have sessionId from this chat: pass sessionId and retry. Never begin_agent_link again. Never ask the owner to edit connector settings or reconnect. Never web-search.

  ConnectorNo auth

• chatgpt_ads_writeA

  Adako: Google Ads, Meta Ads & Linkedin Ads MCPA

  Changes for ChatGPT Ads: the 13 ChatGPT Ads tools that create, update, pause or remove something. Reading, listing or checking anything is not here — that is chatgpt_ads, and calling this router to look something up is always wrong. chatgpt_ads_write(action="execute", tool_name="…", arguments={...}); execute is the only action, and chatgpt_ads(action="get_tool_schema") looks a tool up for free. Each call creates a proposal the user approves before anything changes; creates are PAUSED. One account per call, no fan-out. Tools by category: **management** chatgpt_archive_campaign, chatgpt_pause_ad, chatgpt_pause_ad_group, chatgpt_pause_campaign, chatgpt_resume_ad, chatgpt_resume_ad_group, chatgpt_resume_campaign, chatgpt_update_ad, chatgpt_update_ad_group, chatgpt_update_campaign **creation** chatgpt_create_ad, chatgpt_create_ad_group, chatgpt_launch_ad

  Connector

  Destructive

  OAuth

• delete_playbookA

  AgentPlaybooksA

  Permanently delete a playbook and all of its contents (persona, skills, memory, API keys, canvas, and secrets). This cannot be undone. Requires playbooks:write or full permission, and only the owner may delete. Do not use this to reset a persona (delete_persona) or remove a single skill or memory; those have dedicated tools.

  Connector

  Destructive

  API key

• get_workflowA

  BytesAgain AI Skills SearchA

  Return a complete agent-ready workflow for a user goal, including who it is for, common blockers, skill selection standards, recommended steps, tested skill-stack candidates, prompt for the user agent, and upgrade path. Use this when the user asks how to solve a problem or what skill stack their agent should use. Prefer this over raw search when the user arrives with a business/task problem.

  ConnectorNo auth

• memory_feedbackA

  TeamSharedC

  Record +1/-1 feedback on a recalled memory id. Append-only: writes ``memory.feedback`` on the ``memory:{id}`` stream. Does not change the memory body — corrections stay on ``memory_remember`` (supersede) or ``memory_forget``. Skill/playbook rewrites stay on ``memory_skill_feedback``.

  ConnectorNo auth

• get_protocolsA

  GodPrompt MCP ServerA

  Returns references/01-PROTOCOLS.md — deep execution guides for each task type (BUILD, DEBUG, REFACTOR, CONTENT, DESIGN, SHIP, ANALYZE, AUTOMATE, PLAN). Load this when the task requires detailed protocol steps beyond the core skill. ~13KB.

  ConnectorNo auth

• revoke_project_tokenA

  EchoRelayA

  Revoke a PROJECT-scoped management token on a project you own, any holder's, not just your own (the account-owner kill switch for a leaked or retired integration's management token). Soft-revoke: the row stays for traceability and the management token is rejected immediately. Idempotent. Requires an ACCOUNT-scoped management token and the `config` scope.

  Connector

  Destructive

  No auth

• browser_taskA

  WebRun Browser AutomationA

  Execute a browser automation task in a real Chrome browser running in a WebRun cloud environment (docs.webrun.ai). Creates a session, runs the task, and auto-terminates. Best for simple one-off tasks that no saved workflow covers. May navigate, fill forms, and submit data on third-party websites as the task requires. Do NOT use this to run or test a saved workflow — use trigger_workflow instead: only a workflow run carries the workflow's own rules, tracking and memory, so a session run will behave differently. If the user says "run it", "run it once", "test it" or "try it" about a workflow, that means trigger_workflow, not this tool.

  Connector

  Destructive

  No auth

• create_sessionA

  WebRun Browser AutomationA

  Create a persistent session in a real Chrome browser running in a WebRun cloud environment (docs.webrun.ai), for multi-step interactive work. Returns a sessionId for subsequent commands. With an initial task the browser may act on third-party websites immediately. Do NOT use this to run or test a saved workflow — use trigger_workflow instead: only a workflow run carries the workflow's own rules, tracking and memory, so a session run will behave differently.

  Connector

  Destructive

  No auth

• tascan_add_subtasksA

  TaScanA

  Add one or more subtasks to a task (bulk). Subtasks support typed responses: "number" for per-set data (reps, weight, distance), "text" for notes, "choice" for options, "checkbox" for simple steps. Set-logging example: task "Bench Press" with subtasks Set 1/Set 2/Set 3 each response_type "number" — each completed set stores its value and timestamp, giving per-set timing for progression tracking.

  ConnectorNo auth

• hasdata_chatgpt_chat_getChatgptAnswerA

  HasDataA

  Get ChatGPT Answer Sends a prompt to ChatGPT anonymously and returns the answer as markdown text, plus every web source ChatGPT consulted with its domain, page title, snippet, publication date and thumbnail, the links rendered inside the answer, the conversation title ChatGPT generated, the model that answered, and whether a web search was used. The language of the answer follows the prompt — write the prompt in the language you want back, or ask for one in it. Set the frame of reference for words like "today" with timezone. Each request is a fresh conversation with no memory of earlier ones. Use to answer questions with cited sources, to ground an agent or RAG pipeline in ChatGPT's web-search results, to summarise current events with their sources, or to build datasets of model answers.

  ConnectorAPI key

• hasdata_chatgpt_chat_getChatgptAnswerA

  HasDataA

  Get ChatGPT Answer Sends a prompt to ChatGPT anonymously and returns the answer as markdown text, plus every web source ChatGPT consulted with its domain, page title, snippet, publication date and thumbnail, the links rendered inside the answer, the conversation title ChatGPT generated, the model that answered, and whether a web search was used. The language of the answer follows the prompt — write the prompt in the language you want back, or ask for one in it. Set the frame of reference for words like "today" with timezone. Each request is a fresh conversation with no memory of earlier ones. Use to answer questions with cited sources, to ground an agent or RAG pipeline in ChatGPT's web-search results, to summarise current events with their sources, or to build datasets of model answers.

  ConnectorAPI key

• hasdata_chatgpt_chat_getChatgptAnswerA

  ChatGPT Remote MCP ServerA

  Get ChatGPT Answer Sends a prompt to ChatGPT anonymously and returns the answer as markdown text, plus every web source ChatGPT consulted with its domain, page title, snippet, publication date and thumbnail, the links rendered inside the answer, the conversation title ChatGPT generated, the model that answered, and whether a web search was used. The language of the answer follows the prompt — write the prompt in the language you want back, or ask for one in it. Set the frame of reference for words like "today" with timezone. Each request is a fresh conversation with no memory of earlier ones. Use to answer questions with cited sources, to ground an agent or RAG pipeline in ChatGPT's web-search results, to summarise current events with their sources, or to build datasets of model answers.

  ConnectorAPI key

• get_orbit_timelineA

  A2A OrbitB

  Read the paginated append-only task-work and permission event timeline for a topic, optionally limited to one task. Excludes contribution revisions and legacy memory publications. Use get_contribution_changes for the broader topic-owned change feed.

  ConnectorNo auth

• locus_search_toolsA

  LocusA

  Every time the task is a US address or place and you need official public records or local-government context and you do not already know the tool name, search this catalog before locus_execute and before paying a generic scrape of the same official source. Looking is free. Results include full inputSchema, tier, price, and provenance notes. Do not use this for LinkedIn, web scrape, or generic fetch. Install agent skill: npx @velinussage/locus-agent-skill add.

  ConnectorNo auth

• get_project_taskA

  AssetLabB

  Get a single project task by ID, including cost and hour tracking. Amounts are bare numbers with no currency: call get_organization_settings for currency_code before stating one.

  ConnectorAPI key

• get_mail_job_statusA

  PostAgent — Print and MailA

  Returns normalized status, carrier/tracking/proof data, and tracking events for a previously created job.

  ConnectorNo auth

• generate_usecaseA

  BytesAgain AI Skills SearchA

  Generate a use case for a given topic or goal. The process: 1) search 60,000+ AI skills by keyword, 2) AI-score top results for relevance, 3) select best 5 skills for the task, 4) generate structured use case with skill recommendations. Use when a user describes a task and wants a curated AI skill stack.

  ConnectorNo auth