Skip to main content
Glama
mcp-agent-hub

mcp-agent-hub

by LianXia233

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
AGENT_NAMENo默认 Agent 名(也可用 --name)
AGENT_ROLENo职责描述
AGENT_HUB_DBNoSQLite 路径(多客户端务必同一文件)./agent-hub.db
AGENT_ROLE_TYPENomaster 或 subagent(主理人请设为 master)subagent
AGENT_REPORTED_TONo子代理汇报的主理人名字(不填则自动挂靠)
AGENT_CAPABILITIESNo能力标签,逗号分隔

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
whoamiB

查看当前默认身份,以及 Hub 中已注册的主理人/子代理概况。

join_hubB

登记或更新 Agent 身份。手动设主:role_type=master;其余客户端用 role_type=subagent,会自动挂靠到当前主理人(也可显式传 reported_to)。支持任意多个子代理同时在线。

list_agentsB

列出已登记 Agent。可按 role_type(master/subagent)或 status 过滤。

set_statusC

设置自己的在线状态:('online', 'away', 'busy', 'offline')。

set_masterA

手动指定某个 Agent 为唯一主理人。exclusive=true 时把其他 master 降为 subagent,并把子代理的汇报线改到新的主理人。用法:set_master(name='boss')。

broadcastB

向全部 Agent 广播一条消息(一对多通知)。kind 可用 announce/order/report 等。

team_statusA

查看全体 Agent(多个主理人 + 全部子代理/peer)及其当前任务负载,以及 Hub 统计。适合主理人总览,也适合任何 Agent 看队伍在干什么。

send_messageB

发送消息。to 可为 Agent 名/'*'(广播),room 为频道名;kind 可用 ('message', 'order', 'report', 'question', 'answer', 'announce', 'handoff', 'escalation', 'system')(order=派令,report=汇报)。task_id 可关联任务。

read_inboxB

读取收件箱。默认返回发给自己、广播和已加入房间的消息。unread_only=true 只看未读;kinds 可过滤消息类型;task_id 可只看某任务相关。

mark_readB

标记消息已读。不传 message_ids 则标记全部已可见消息。

create_roomC

创建协作房间(频道)并自动加入。

join_roomC

加入协作房间。

list_roomsC

列出房间及成员。

rememberB

写入共享黑板(跨 Agent 记忆)。同一 key 会递增 version 并保留历史。

recallB

读取共享黑板。可按精确 key、key 前缀或 tag 查询。

forgetC

删除共享黑板上的某个 key。

dispatch_taskB

主理人专用:向子代理派发任务(工作单)。会创建任务并自动给子代理发一条 order 消息。可传 parent_id 挂到父任务下形成子任务树。

create_taskB

创建任务(不指定负责人则进入 open 池,供子代理 claim_task 认领)。

list_tasksB

列出任务。可按 status/assignee/tag/parent_id 过滤。status ∈ ('open', 'claimed', 'in_progress', 'blocked', 'done', 'cancelled')。

my_assignmentsB

子代理:查看分配给自己的任务(默认不含已完成)。

claim_taskA

子代理:认领 open/blocked 任务,避免重复劳动。已有负责人则会失败并提示持有者。

report_progressA

子代理:向主理人汇报任务进度(0-100)。会自动给 master 发一条 report 消息。可同时更新 status(如 in_progress/blocked)。

update_taskC

更新任务字段(status/description/result/assignee/priority)。主理人可用来改派。

complete_taskB

完成任务并附交付说明。会自动给主理人发一条 report 消息。

escalateA

子代理专用:遇到阻塞时上报主理人。会把任务标为 blocked(若提供 task_id)并给 master 发一条 escalation 消息。

hub_statsB

Hub 总览:Agent/任务/消息/黑板计数与 DB 路径。

activity_logC

查看最近协作事件流(派单、认领、汇报等)。

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

C2.9/5.0

Scored across 27 tools

Disambiguation3/5

Most tools target distinct resources, but several boundaries overlap: broadcast vs send_message with '*', team_status vs list_agents vs hub_stats, and report_progress vs update_task vs complete_task vs escalate. The descriptions help clarify intended use, but an agent could still misselect among these related coordination tools.

Naming Consistency4/5

Tool names consistently use snake_case and are mostly readable verb_noun patterns such as create_room, dispatch_task, send_message, and complete_task. A few names are noun-only or phrase-like (whoami, team_status, hub_stats, my_assignments), which is a minor deviation rather than a structural inconsistency.

Tool Count2/5

At 27 tools, the surface is heavy for a single MCP server and exceeds the typical 3-15 well-scoped range. Some tools are convenience wrappers or overlapping views that could be consolidated, especially broadcast/send_message and team_status/list_agents/hub_stats.

Completeness4/5

The server covers the core multi-agent lifecycle: rooms, shared memory, agent identity, tasks, messaging, escalation, and stats. Minor gaps remain, such as leaving/deleting rooms, deregistering agents, or fetching a single task by ID, but agents can mostly work around these.