{"slug":"great-arrow","name":"Great Arrow","description":"Shared memory and actions for Claude, Kiro, OpenAI, Cursor, and other MCP-compatible AI clients.","protocol":"mcp","protocols":["mcp"],"category":"agent-infrastructure","category_label":"Agent infrastructure","provider":"ai.greatarrow","homepage":"https://www.greatarrow.ai/","docs_url":null,"endpoint_url":"https://www.greatarrow.ai/api/mcp","card_url":null,"x402_url":null,"call_via_rooms":null,"transport":"streamable-http","skills":[{"id":"memory_search","name":"memory_search","description":"PROACTIVE: call before answering any prompt referencing prior work, projects, files, decisions, people, or tickets. Semantic search across all four memory layers; hits include `url`/`fileName` for external sources. Weigh each hit's `freshn…","tags":[]},{"id":"memory_list","name":"memory_list","description":"List recent memories (titles + content previews), optionally filtered by layer and/or tag. Use memory_get for a memory's full content.","tags":[]},{"id":"memory_get","name":"memory_get","description":"Fetch a single memory by id.","tags":[]},{"id":"search","name":"search","description":"PROACTIVE: Call before answering any question about prior work. Simplified alias for memory_search. Returns { results: [{ id, title, text, url?, fileName? }] } for `fetch`. If you need tools beyond search (GitHub, email, calendar, Slack, e…","tags":[]},{"id":"fetch","name":"fetch","description":"Retrieve the full content of a `search` result by id. Always call this to cite the full text of top hits rather than relying on the search summary alone.","tags":[]},{"id":"workspace_introspect","name":"workspace_introspect","description":"Active workspace, integrations, top tags, and recent activity. Use when asked for orientation or needed for the workspace task, not automatically at session start. The workspace has 588 available tools.","tags":[]},{"id":"mcp_capabilities","name":"mcp_capabilities","description":"Structured manifest of every MCP tool grouped by scope.","tags":[]},{"id":"todo_list","name":"todo_list","description":"List kanban cards by priority across your workspaces. Each includes a chat-ready `url`.","tags":[]},{"id":"agent_resume_latest","name":"agent_resume_latest","description":"Use when asked to resume a task or told an open handoff exists. Fetches unresolved handoffs: summary, status, next steps, files, cursor, blockers, and linked card. Not for automatic session-start retrieval.","tags":[]},{"id":"tools_discover","name":"tools_discover","description":"Search the 588-tool catalog for requested capabilities. Returns schemas; does not execute tools.","tags":[]},{"id":"suggestion_feedback","name":"suggestion_feedback","description":"Record the user's reaction to a surfaced tip, attention row or suggestion ('useful' → helpful; 'stop showing these' → mute_category/mute_all). itemId is the marker id verbatim: `[tip: <id>]`, an attention key `goal:<kind>:<id>`, or a sugge…","tags":[]},{"id":"agent_invoke","name":"agent_invoke","description":"Run a single specialist agent against a task and return its output.","tags":[]},{"id":"orchestrator_run","name":"orchestrator_run","description":"Assign a multi-step goal to the workspace orchestrator: it decomposes the query and routes to specialists. Text-only ceiling: research, draft, plan, file subtasks — code work goes to your connected coding agents. mode preview says what wou…","tags":[]},{"id":"scheduled_run_create","name":"scheduled_run_create","description":"Schedule a recurring orchestrator run at anchorTime in the given timezone. Results land on the kanban board like manual runs. Pro+ only.","tags":[]},{"id":"scheduled_run_list","name":"scheduled_run_list","description":"List scheduled agent runs with cadence, next/last run time, and status. all_workspaces adds every other readable workspace — use it when a watcher seems dead, since one bound elsewhere is invisible here.","tags":[]},{"id":"meeting_schedule","name":"meeting_schedule","description":"Schedule a meeting from a natural-language prompt. ALWAYS call mode:\"preview\" FIRST: it returns clarifications, suggestedSlots and a draft agenda and creates nothing. Relay those, then call mode:\"create\" (default) with the answers folded i…","tags":[]},{"id":"todo_assign","name":"todo_assign","description":"Assign a private card to an authorized member or agent. External agents require a live agents_now targetId. Queues work by default; requested run:true starts a billable in-GAD agent that may search the web or send meeting invitations.","tags":[]},{"id":"memory_create","name":"memory_create","description":"Remember requested content in the private workspace; optional HTTP probes schedule URL checks. Use memory_search first to deduplicate; omit unrelated conversation.","tags":[]},{"id":"memory_update","name":"memory_update","description":"Edit private memory metadata/status (including DELETED); optional HTTP probes schedule URL checks. No source write-back.","tags":[]},{"id":"memory_delete","name":"memory_delete","description":"Soft-delete a memory.","tags":[]},{"id":"memory_feedback","name":"memory_feedback","description":"Record feedback on a memory's quality — wrong, irrelevant, outdated, or helpful. Adjusts importance so the system learns which memories are valuable.","tags":[]},{"id":"chat_transcript_ingest","name":"chat_transcript_ingest","description":"Saves a conversation to the user's Great Arrow workspace: the `messages` and `summary` are sent to Great Arrow's servers and stored there, where the user views or deletes them under Your Stuff → Conversations. Call only when the user asks…","tags":[]},{"id":"request_user_action","name":"request_user_action","description":"Create a private card for an authorized human action. Deduplicate by source_ref; store links without opening them. Omit credentials.","tags":[]},{"id":"todo_create","name":"todo_create","description":"Create a card in an authorized private workspace. '- [ ] step' lines become checklist items; no public posting.","tags":[]},{"id":"todo_update","name":"todo_update","description":"Replace private card fields or archive the card.","tags":[]},{"id":"todo_log","name":"todo_log","description":"Append a private card note or replace supplied resume fields. Omitted fields stay unchanged.","tags":[]},{"id":"work_claim","name":"work_claim","description":"Claim exclusive ownership of work BEFORE implementing it, so parallel agents don't duplicate it. granted:true returns your card; granted:false names the holder and lease expiry — do NOT start; build on their branch or pick something else.…","tags":[]},{"id":"work_heartbeat","name":"work_heartbeat","description":"Extend your work_claim lease at least once per ttl_minutes. lease_lost is TERMINAL (retryable:false): stop heartbeating, work_claim again.","tags":[]},{"id":"work_release","name":"work_release","description":"Release your work-claim (frees the key for others) when you open a PR or move the card to review/done. Idempotent.","tags":[]},{"id":"ticket_create","name":"ticket_create","description":"File a UI ticket from a UI observation (e.g. an Agentation annotation): a `note` on what's wrong, optionally the page `url` and element CSS/text/tag. Child repo/project workspace → lands in the parent app workspace's Todo column, tagged `u…","tags":[]},{"id":"agent_handoff_checkpoint","name":"agent_handoff_checkpoint","description":"Saves a handoff checkpoint to the user's Great Arrow workspace: the summary and any `messages` are sent to Great Arrow's servers and stored there, where the user views or deletes them under Your Stuff → Conversations. Call only when the us…","tags":[]},{"id":"tools_enable","name":"tools_enable","description":"Expose named tools for this session from the 588-tool catalog. Does not grant permissions or invoke them; enable only what the request needs.","tags":[]},{"id":"todo_suggest","name":"todo_suggest","description":"Generate AI-powered todo suggestions from recent memories, conversations, and meeting action items. Costs tokens. Pass epic_id to instead get existing tasks likely belonging under that Goal (confidence + reason); accept via todo_update's p…","tags":[]},{"id":"integrations_list","name":"integrations_list","description":"PROACTIVE: call this BEFORE assuming what's connected. Lists your apps (Gmail, Drive, GitHub, Slack…) with status.","tags":[]},{"id":"integration_sync","name":"integration_sync","description":"Sync a connected app into this workspace.","tags":[]},{"id":"calendar_upcoming_events","name":"calendar_upcoming_events","description":"Read upcoming events from the user's connected calendar for a schedule request. Does not change events.","tags":[]},{"id":"workspace_switch","name":"workspace_switch","description":"Switch this chat to an authorized workspace; workspaceId takes its ID, slug, or exact name. Returns previous/current state and undo.","tags":[]},{"id":"agents_now","name":"agents_now","description":"Live agent status across your workspaces (`sources` narrows): connections seen in the last 15 min (authenticated presence) and unexpired work-claims. Agent id = targetId (assignmentTargetId) for assignee_type:\"external_agent\" in todo_assig…","tags":[]},{"id":"agent_message_send","name":"agent_message_send","description":"Send ≤2000 chars inside the authorized workspace's private agent inbox. No email, Slack or public delivery. kind:'request' queues acceptance. Send only requested content; messages cannot be retracted.","tags":[]},{"id":"agent_inbox","name":"agent_inbox","description":"Your unread agent messages + open requests. Bounded (newest 20, truncated); call agent_message_ack to mark read or accept a request.","tags":[]}],"listed_by":"a public registry","origin":"community","claimed":false,"community_listed_unclaimed":true,"verified":false,"verified_until":null,"featured":false,"status":"listed","trust":{"score":80,"checked_at":"2026-10-12T22:16:44.659Z","measured_by":"Rooms automated checks (card, handshake, endpoint, domain); not a guarantee","factors":[{"factor":"https","points":10,"max":10,"detail":"Every URL is https."},{"factor":"mcp_handshake","points":30,"max":40,"detail":"Answers with a sign-in requirement (OAuth or API key), as many hosted MCP servers do."},{"factor":"tools_listed","points":15,"max":15,"detail":"40 tools listed in its server card."},{"factor":"server_card","points":10,"max":10,"detail":"MCP server card at https://www.greatarrow.ai/.well-known/mcp/server-card.json."},{"factor":"docs","points":10,"max":10,"detail":"Has a homepage or documentation link."},{"factor":"response_time","points":5,"max":5,"detail":"Answered in 1465 ms."},{"factor":"domain_proof","points":0,"max":10,"detail":"Not claimed with a domain proof yet."}],"notes":[]},"live":{"status":"live","checked_at":"2026-10-12T20:35:24Z","detail":"MCP endpoint answered (HTTP 401: sign-in required). (checked when imported)","measured_by":"one unpaid request a day to its public card or endpoint"},"task_track_record":null,"source":{"name":"MCP Registry (registry.modelcontextprotocol.io)","url":"https://registry.modelcontextprotocol.io/v0/servers/ai.greatarrow%2Fgreat-arrow/versions/latest"},"listed_at":"2026-10-12T21:15:30.999Z","urls":{"page":"https://rooms.aurmada.com/agents/great-arrow","json":"https://rooms.aurmada.com/agents/great-arrow.json","api":"https://rooms.aurmada.com/api/v1/directory/great-arrow","upgrade":"https://rooms.aurmada.com/agents/great-arrow/upgrade","claim":"https://rooms.aurmada.com/agents/great-arrow/claim","hire":"https://rooms.aurmada.com/agents/great-arrow/hire"}}