A2A Orbit
Server Details
Shared memory for AI agents: prior work, failures, checkpoints, handoffs, and artifacts.
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Uptime
- 0.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 31 tools
Several read tools overlap around Orbit/task state (get_orbit_overview, get_orbit_context, get_task, list_tasks, get_orbit_timeline, get_contribution_changes), and legacy tools duplicate newer contribution/checkpoint/finding/failure flows. Descriptions frequently clarify boundaries and deprecations, but the agent still faces multiple plausible calls for the same intent.
All 31 names are snake_case and follow an action_object pattern (verb_noun), with only minor verb variation across domains. No camelCase or mixed conventions are present.
31 tools is high for the server's apparent scope, and the surface includes multiple legacy compatibility aliases and several overlapping read endpoints. While the domain is broad, consolidation would make the set more navigable.
Core workflows for tasks, leases, checkpoints, handoffs, contributions, revisions, artifacts, and legacy memory are broadly covered. However, topic/member management is notably incomplete: create_topic supports write_policy=members but no tool adds or removes members, and there is no update/delete topic path.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Shared, governed memory for fleets of AI agents: judged contributions, provenance, operator control
Shared memory and teamwork for AI agents: knowledge base, memory, tasks, code maps, encrypted vault.
Shared debugging memory for AI coding agents
Shared project memory for AI coding agents: decisions, lessons, risks and tasks in one graph.
Related MCP Servers
- AlicenseAqualityCmaintenanceShared memory and handoff hub for AI agents, enabling seamless context transfer between sessions with token-budgeted resumes and automatic handoffs.1011 npmMIT
- AlicenseAqualityBmaintenanceGoverned cross-agent memory for coding agents with hybrid retrieval, provenance tracking, and cross-machine sync.918MIT
- AlicenseNot gradedqualityDmaintenanceA shared memory and coordination layer for AI coding agents that provides a tamper-evident timeline, conflict awareness, and attribution for multi-agent coding workflows.55 npm8Apache 2.0
- AlicenseAqualityAmaintenanceFailure Memory provides AI coding agents with a shared local memory of failures, enabling them to record, recall, and learn from mistakes across sessions.2MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.