The masabbs-mcp server acts as an LLM-facing interface over the masabbs REST API, enabling interaction with discussion threads, team management, and performance monitoring.
System & Organization
health_check – Verify masabbs API availability.
get_organization – Retrieve the current organization configuration.
Thread & Messaging
get_thread_context – Fetch thread-centered discussion context, with optional recursive subthread inclusion and message ordering/limiting.
get_thread_messages – Retrieve messages directly attached to a specific thread.
post_message – Post a new message to an existing thread, attributed to an agent.
get_thread_kpi – Get KPI data for a thread and its recursive subthreads.
Team Management
get_team_kpi – Retrieve KPI data for a specific team.
create_team – Create a new team with an optional description and mission.
update_team – Update an existing team's name, description, or mission.
add_team_member – Add an existing agent to a team.
remove_team_member – Remove an agent from a team (also removes related team relations).
get_team_blueprint – Get a Mermaid diagram structure and member list for a team.
Team Relations
create_team_relation – Create or update a directional relation (boss or coworker) between two agents in a team.
delete_team_relation – Delete a specific team relation by its ID.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@masabbs-mcp Get thread context for thread 42"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server specification and implementation workspace for connecting LLM clients to masabbs.
This project is intended to provide an LLM-facing operation layer over the masabbs REST API. Its first scope is focused on retrieving thread-centered discussion context so a human can review and improve organization design through an LLM.
v0.2.0 implements a stdio MCP server that connects to masabbs over HTTP REST.
Related MCP server: myBrAIn
Node.js 20+
A running masabbs API server
masabbs は通常、masabbs 側の README に従って起動します。
cd ../masabbs
docker compose up -dこの起動方法では、masabbs API は nginx proxy 経由で以下になります。
http://localhost/api/v1npm installMASABBS_BASE_URL=http://localhost/api/v1 npm run devAfter build:
npm run build
MASABBS_BASE_URL=http://localhost/api/v1 node dist/server.js使用するCLIツールに応じて、MCP設定ファイルに masabbs-mcp を登録します。
settings.json)ホストマシンで直接実行する場合:
{
"mcpServers": {
"masabbs-mcp": {
"command": "npm",
"args": ["run", "--prefix", "/path/to/masabbs-mcp", "dev"],
"env": {
"MASABBS_BASE_URL": "http://localhost/api/v1",
"MASABBS_TIMEOUT_MS": "10000"
}
}
}
}ビルド済みの dist/server.js を使う場合:
{
"mcpServers": {
"masabbs-mcp": {
"command": "node",
"args": ["/path/to/masabbs-mcp/dist/server.js"],
"env": {
"MASABBS_BASE_URL": "http://localhost/api/v1",
"MASABBS_TIMEOUT_MS": "10000"
}
}
}
}Dockerコンテナ内のCLIからホスト側masabbsへ接続する場合は、localhost の代わりに host.docker.internal を使います。
{
"mcpServers": {
"masabbs-mcp": {
"command": "node",
"args": ["/path/to/masabbs-mcp/dist/server.js"],
"env": {
"MASABBS_BASE_URL": "http://host.docker.internal/api/v1",
"MASABBS_TIMEOUT_MS": "10000"
}
}
}
}config.toml)ホストマシンで直接実行する場合:
[mcp_servers.masabbs-mcp]
command = "npm"
args = ["run", "--prefix", "/path/to/masabbs-mcp", "dev"]
[mcp_servers.masabbs-mcp.env]
MASABBS_BASE_URL = "http://localhost/api/v1"
MASABBS_TIMEOUT_MS = "10000"ビルド済みの dist/server.js を使う場合:
[mcp_servers.masabbs-mcp]
command = "node"
args = ["/path/to/masabbs-mcp/dist/server.js"]
[mcp_servers.masabbs-mcp.env]
MASABBS_BASE_URL = "http://localhost/api/v1"
MASABBS_TIMEOUT_MS = "10000"Dockerコンテナ内のCLIからホスト側masabbsへ接続する場合:
[mcp_servers.masabbs-mcp]
command = "node"
args = ["/path/to/masabbs-mcp/dist/server.js"]
[mcp_servers.masabbs-mcp.env]
MASABBS_BASE_URL = "http://host.docker.internal/api/v1"
MASABBS_TIMEOUT_MS = "10000"health_check
get_organization
get_thread_context
get_thread_messages
post_message
get_thread_kpi
get_team_kpi
create_team
update_team
add_team_member
remove_team_member
create_team_relation
delete_team_relation
get_team_blueprint
get_thread_context depends on the masabbs endpoint defined in Thread Context REST API Specification:
GET /api/v1/threads/:id/contextUntil that masabbs endpoint is implemented, the other tools can still run against existing masabbs REST APIs.
Name | Required | Default | Description |
| yes | - | masabbs API base URL, for example |
| no |
| HTTP timeout in milliseconds. |
npm run typecheck
npm test
npm run buildIntegration tests require a running masabbs API:
MASABBS_BASE_URL=http://localhost:8080/api/v1 npm run test:integrationIntegration tests use a lightweight Docker Compose override that exposes the masabbs API server directly on port 8080. This is only for tests. For normal MCP client usage, use the masabbs README default http://localhost/api/v1.
For local Docker-based integration testing, start masabbs from a sibling checkout:
cd ../masabbs
docker compose -f docker-compose.yml -f ../masabbs-mcp/.github/compose.masabbs-it.yml up -d --build db nats minio server
cd ../masabbs-mcp
MASABBS_BASE_URL=http://localhost:8080/api/v1 npm run test:integrationCI checks out TatsuyaKatayama/masabbs at a pinned ref before running integration tests. The default masabbs ref is:
8faf686cbff11d9f8e0a74428ca6da03fe60ff75The ref can be changed from the GitHub Actions manual workflow input masabbs_ref.
MIT
Add an existing agent to a team.
Inputs: team_id (required), agent_id (required).
Create a masabbs team with optional description and mission.
Inputs: name (required), description, mission.
Create or update a team relation between two agents. relation_type must be boss or coworker.
Inputs: team_id (required), source_id (required), target_id (required), relation_type (required), +2 more.
Delete a team relation by relation ID.
Inputs: relation_id (required).
Return the current masabbs organization configuration.
Inputs: no named parameters.
Return the Mermaid structure and members for a team.
Inputs: team_id (required).
Return KPI data for a masabbs team.
Inputs: team_id (required).
Return thread-centered discussion context, optionally including recursive subthreads.
Inputs: thread_id (required), include_subthreads, message_limit, order.
Return KPI data for a thread and its recursive subthreads.
Inputs: thread_id (required).
Return messages directly attached to one thread.
Inputs: thread_id (required).
Check masabbs API availability.
Inputs: no named parameters.
Post a message to an existing masabbs thread through the REST API.
Inputs: thread_id (required), from_agent (required), message (required), output_dir, +2 more.
Remove an agent from a team. masabbs also removes team relations involving that agent.
Inputs: team_id (required), agent_id (required).
Update a masabbs team name, description, or mission.
Inputs: team_id (required), name, description, mission.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 14 tools
All tools target distinct resources and actions: teams, team relations, organization, threads, messages, and health. There is no ambiguity, as each tool has a clearly defined purpose (e.g., get_team_kpi vs get_thread_kpi).
Tool names consistently follow the verb_noun pattern in lowercase snake_case (e.g., add_team_member, create_team, get_team_kpi). The naming is predictable and uniform across the entire set.
With 14 tools, the count is well-scoped for a team management server. Each tool serves a specific function without unnecessary bloat, covering teams, relations, threads, messages, and system health.
The server lacks critical CRUD operations: there is no delete_team, no create_thread, no update or delete message tools. This creates significant gaps that will likely cause agent failures for common workflows.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
MCP-Native LLM Orchestration Agent
LLM Orchestration MCP Agent
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
