MCP.so
登录
W

Writbase - MCP Task Management for AI Agent Fleets

@Writbase

代码仓库

关于 Writbase - MCP Task Management for AI Agent Fleets

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.

#mcp#ai-agents#task-management#supabase#multi-agent#agent-framework

基本信息

分类

AI 与智能体

传输方式

stdio

发布者

Writbase

提交者

Alex

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "writbase": {
      "type": "http",
      "url": "https://<project-ref>.supabase.co/functions/v1/mcp-server/mcp",
      "headers": {
        "Authorization": "Bearer wb_<key_id>_<secret>"
      }
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Writbase - MCP Task Management for AI Agent Fleets?

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.

How to use Writbase - MCP Task Management for AI Agent Fleets?

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.

Key features of Writbase - MCP Task Management for AI Agent Fleets

  • 12 MCP tools: 5 worker + 7 manager tools
  • 6 permission types: can_read, can_create, can_update, can_assign, can_comment, can_archive
  • Project + department scoping for permissions
  • Optimistic concurrency with version-based conflict detection
  • Inter-agent delegation with depth limits and cycle detection
  • HMAC‑signed Standard Webhooks on task events
  • Append-only audit log for full provenance
  • Dynamic MCP schema adapting tool visibility per agent’s permissions

Use cases of Writbase - MCP Task Management for AI Agent Fleets

  • Coordinate work among multiple AI agents with role-based access control
  • Enforce fine-grained permissions for task operations within projects and departments
  • Track full provenance of task changes through an immutable audit log
  • Enable real‑time notifications via HMAC‑signed webhooks on task events
  • Support concurrent edits safely with optimistic concurrency and conflict detection

FAQ from Writbase - MCP Task Management for AI Agent Fleets

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.

How are permissions structured?

There are 6 permission types (can_read, can_create, can_update, can_assign, can_comment, can_archive) applied per (project, department) pair.

Does it require Supabase?

Yes, deployment relies on Supabase: you must run supabase db push and supabase functions deploy mcp-server --no-verify-jwt.

How is concurrency handled?

The server uses optimistic concurrency with version‑based conflict detection to handle concurrent modifications.

What is the license of Writbase - MCP Task Management for AI Agent Fleets?

It is licensed under Apache 2

评论

AI 与智能体 分类下的更多 MCP 服务器

MCP Server - Remote MacOs Use

baryhuang

The only general AI agent that does NOT requires extra API key, giving you full control on your local and remote MacOs from Claude Desktop App

487

Shell and Coding agent for Claude and other mcp clients

rusiaaman

Shell and coding agent on mcp clients

666

Intervals.icu MCP Server

mvilanova

Model Context Protocol (MCP) server for connecting Claude and ChatGPT with the Intervals.icu API.

311

MCP Client for Ollama (ollmcp)

jonigl

Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre

768

Perplexity MCP Server

DaInfernalCoder

A Model Context Protocol (MCP) server for research and documentation assistance using Perplexity AI. Won 1st @ Cline Hackathon

295