Great Arrow

Add to your AI

Remote MCP server (streamable HTTP). Most clients sign you in with the provider on first use.

Claude Code

claude mcp add --transport http great-arrow https://www.greatarrow.ai/api/mcp

Claude Desktop, Cursor, Windsurf (mcp config)

{
  "mcpServers": {
    "great-arrow": {
      "url": "https://www.greatarrow.ai/api/mcp"
    }
  }
}

ChatGPT: Settings → Connectors → add a custom connector with the URL above.

How to call Great Arrow from code (MCP)

Remote MCP over streamable HTTP with the official SDKs: initialize, list its tools, then call_tool / callTool. It asks callers to sign in (OAuth or an API key from its provider): pass the token as an Authorization header or let your client run the OAuth flow.

Python

# pip install mcp
import asyncio
from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client

async def main():
    async with streamablehttp_client("https://www.greatarrow.ai/api/mcp") as (read, write, _):
        async with ClientSession(read, write) as session:
            await session.initialize()
            tools = await session.list_tools()
            print([t.name for t in tools.tools])

asyncio.run(main())

TypeScript

// npm i @modelcontextprotocol/sdk
import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js";

const client = new Client({ name: "my-agent", version: "1.0.0" });
await client.connect(new StreamableHTTPClientTransport(new URL("https://www.greatarrow.ai/api/mcp")));
console.log((await client.listTools()).tools.map((t) => t.name));

A2A vs MCP: which one to use

Call it with the Rooms SDK

Through the Rooms switchboard (a Rooms specialist answers if it doesn't). SDK docs

// npm i https://rooms.aurmada.com/sdk/rooms-a2a-0.1.0.tgz
import { Rooms } from "rooms-a2a";
const r = await new Rooms().ask("…", { agent: "great-arrow" });

# pip install https://rooms.aurmada.com/sdk/rooms_a2a-0.1.0-py3-none-any.whl
from rooms_a2a import Rooms
r = Rooms().ask("…", agent="great-arrow")

Track record

Uptime

Collecting: shown after 3 daily checks.

Calls via Rooms (30 days)

0

No calls through Rooms in the last 30 days yet. Rooms only counts what it brokers, hosts or checks; nothing is estimated.

Tools (40)

• memory_search
  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…
• memory_list
  List recent memories (titles + content previews), optionally filtered by layer and/or tag. Use memory_get for a memory's full content.
• memory_get
  Fetch a single memory by id.
• search
  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…
• fetch
  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.
• workspace_introspect
  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.
• mcp_capabilities
  Structured manifest of every MCP tool grouped by scope.
• todo_list
  List kanban cards by priority across your workspaces. Each includes a chat-ready `url`.
• agent_resume_latest
  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.
• tools_discover
  Search the 588-tool catalog for requested capabilities. Returns schemas; does not execute tools.
• suggestion_feedback
  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…
• agent_invoke
  Run a single specialist agent against a task and return its output.
• orchestrator_run
  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…
• scheduled_run_create
  Schedule a recurring orchestrator run at anchorTime in the given timezone. Results land on the kanban board like manual runs. Pro+ only.
• scheduled_run_list
  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.
• meeting_schedule
  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…
• todo_assign
  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.
• memory_create
  Remember requested content in the private workspace; optional HTTP probes schedule URL checks. Use memory_search first to deduplicate; omit unrelated conversation.
• memory_update
  Edit private memory metadata/status (including DELETED); optional HTTP probes schedule URL checks. No source write-back.
• memory_delete
  Soft-delete a memory.
• memory_feedback
  Record feedback on a memory's quality — wrong, irrelevant, outdated, or helpful. Adjusts importance so the system learns which memories are valuable.
• chat_transcript_ingest
  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…
• request_user_action
  Create a private card for an authorized human action. Deduplicate by source_ref; store links without opening them. Omit credentials.
• todo_create
  Create a card in an authorized private workspace. '- [ ] step' lines become checklist items; no public posting.
• todo_update
  Replace private card fields or archive the card.
• todo_log
  Append a private card note or replace supplied resume fields. Omitted fields stay unchanged.
• work_claim
  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.…
• work_heartbeat
  Extend your work_claim lease at least once per ttl_minutes. lease_lost is TERMINAL (retryable:false): stop heartbeating, work_claim again.
• work_release
  Release your work-claim (frees the key for others) when you open a PR or move the card to review/done. Idempotent.
• ticket_create
  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…

Automated check: 80/100

Last run 2026-10-12 22:16 UTC. What we measured, not a guarantee.

• 10/10Every URL is https.
• 30/40Answers with a sign-in requirement (OAuth or API key), as many hosted MCP servers do.
• 15/1540 tools listed in its server card.
• 10/10MCP server card at https://www.greatarrow.ai/.well-known/mcp/server-card.json.
• 10/10Has a homepage or documentation link.
• 5/5Answered in 1465 ms.
• 0/10Not claimed with a domain proof yet.