What MCP tools does it provide?
It provides 12 MCP tools: 5 worker tools and 7 manager tools, with dynamic schema that adapts to each agent’s permissions.
@Writbase
Basic information
A control plane for AI agents and human supervisors. Persistent task registry with scoped permissions, inter-agent delegation, and full provenance - all accessible via MCP.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"writbase": {
"type": "http",
"url": "https://<project-ref>.supabase.co/functions/v1/mcp-server/mcp",
"headers": {
"Authorization": "Bearer wb_<key_id>_<secret>"
}
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list directly from this server's endpoint using the button above.
Writbase - MCP Task Management for AI Agent Fleets is a Model Context Protocol (MCP) server that provides task management tools for multi-agent AI systems. It offers 12 MCP tools, fine-grained permissions, project and department scoping, delegation with cycle detection, webhook delivery, and an append-only audit log. It is designed for developers building fleets of AI agents that need structured task coordination.
Deploy the server using the Supabase CLI commands (supabase db push && supabase functions deploy mcp-server --no-verify-jwt). Then create an agent key in the dashboard and connect any MCP client (such as Claude Code, Cursor, or VS Code). No further configuration steps are documented beyond these.
It provides 12 MCP tools: 5 worker tools and 7 manager tools, with dynamic schema that adapts to each agent’s permissions.
There are 6 permission types (can_read, can_create, can_update, can_assign, can_comment, can_archive) applied per (project, department) pair.
Yes, deployment relies on Supabase: you must run `supabase db push` and `supabase functions deploy mcp-server --no-verify-jwt`.
The server uses optimistic concurrency with version‑based conflict detection to handle concurrent modifications.
It is licensed under Apache 2

Agent-first hosting. From Claude, Cursor, or Codex, your agent can create an app, push code, and deploy it to a live HTTPS URL, with managed Postgres, custom domains, environment variables, backups, and rollback.

ATL doesn’t just help agents find tools — it gets the job done. It finds and chooses the right AI provider, tool, or MCP server, executes the task, and switches to a fallback when a provider fails. It can optimize for lo
Open-source Node.js FHIR MCP server with SMART Backend Services, metadata-aware search/CRUD tools, compact responses, FHIRPath filtering, safe pagination, audit events, and terminology lookup.
HeyLead: AI agent for LinkedIn outreach. Finds the right people, writes in your voice, follows up and handles replies, from Claude Code, Cursor, any MCP client or a web dashboard.
GoBuy gives AI agents marketplace-evidence trust scores. One call returns a 0–100 Evidence Score with observed/missing signals, freshness, and product context. Tools: • check_product_trust — inspect one Amazon, Walmart,
Comments