Observed Signal · May 7, 2026 · Technical Release · Source: DEV Community · Impact: 4/5 · Sentiment: Positive
Atlassian opens 150B-object Teamwork Graph to MCP agents
Atlassian announced at Team '26 that its Teamwork Graph — a context graph of more than 150 billion objects and relationships across Jira, Confluence, Jira Service Management and connected SaaS tools — is now accessible to any MCP‑compliant agent. The company launched Teamwork Graph MCP servers (open beta), a Teamwork Graph CLI (open beta, free tier), a new Max mode inside Rovo Chat with variable consumption billing, and a public site (teamworkgraph.com) to visualise customer graphs. Third‑party agents such as Claude Code and IDE copilots can query the graph using Atlassian's internal query language, Cipher, enabling multi‑hop relational traversal. Atlassian reported benchmarks showing significant token and accuracy improvements when agents use the graph, and framed the move as a strategic play in the emerging enterprise agent context‑layer alongside Microsoft Graph and Salesforce Data Cloud.
Opening a large, long‑running enterprise context graph to third‑party MCP agents is a strategic platform move that materially affects where agentic enterprise workflows and context fabrics will live — influencing competition among enterprise AI/context providers and agent integrations.
Track Atlassian Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your free Explorer workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- Atlassian announced at Team '26 that the Teamwork Graph (over 150 billion objects and relationships spanning Jira, Confluence, Jira Service Management and connected SaaS tools) is exposed to MCP‑compliant agents.
- Released components (open beta): Teamwork Graph MCP servers and Teamwork Graph CLI (free tier).
- Atlassian introduced 'Max' mode in Rovo Chat (cloud mini-agent) with variable consumption billing and launched teamworkgraph.com for customers to visualise their graphs.
- Third‑party agents (e.g., Claude Code, IDE copilots, Cursor) can query the graph using Atlassian's internal query language 'Cipher' with multi‑hop relationship traversal.
- Atlassian benchmarked Claude Code with graph access and reported 48% fewer tokens used and 44% more accurate results versus without graph access.
Connected Companies & Entities
5 Entities mappedOntology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Atlassian adds visual AI and agents to Confluence
Atlassian announced new AI features for Confluence, including Remix — a visual tool entering open beta that converts Confluence content and data into charts and graphics and recommends optimal visual formats. The company also introduced three third-party agents that run inside Confluence using model context protocols (MCPs), integrating with Lovable (prototype generation), Replit (starter app generation), and Gamma (presentation-building). Atlassian frames these additions as part of a strategy to embed AI agents and tools directly into existing collaboration workflows; the company previously added AI agents to Jira in February. The move aligns with an industry trend toward integrating AI agents into established enterprise apps rather than shipping separate AI platforms.
Atlassian and OpenAI expand partnership to embed frontier AI agents
Atlassian and OpenAI are expanding their strategic partnership to integrate OpenAI frontier models across Atlassian's platform, including Rovo and Jira. The collaboration, which began in 2023, aims to combine OpenAI's models with Atlassian's Teamwork Graph to enable AI agents that help teams plan, build, and deliver work. Atlassian will gain expanded access to OpenAI's latest models, including GPT-6 Astra and the GPT-5.6 series. Over 3,000 Atlassian developers already use Codex, and the companies are exploring deeper Jira integrations to support AI-driven workflows. This is a significant technical and strategic alliance that could influence enterprise AI adoption in workplace tools, relevant to AdTech as AI agents increasingly automate business processes.
Atlassian Unveils Agentic Multiplayer Protocol
Atlassian, the software company behind Jira and Confluence, announced at its Team '26 Europe conference in Amsterdam a new 'Agentic Multiplayer Protocol' aimed at redefining collaboration between humans and AI agents. The announcement was made by CEO Mike Cannon-Brookes. The protocol is designed to enable seamless interaction and coordination among multiple AI agents, potentially transforming enterprise workflows. While specific technical details remain undisclosed due to paywall restrictions, the move underscores Atlassian's commitment to integrating agentic AI into its product suite. The article highlights the growing importance of agentic AI in enterprise software and its potential impact on marketing and advertising workflows.
Track Real-Time Market Signals & Shifts
Set up custom watchlists to receive automated, evidence-grounded executive digests whenever material signals or shifts occur across your tracked landscape.