AI-company MCP server

Multi-agent team operating system for Claude Code. 108 MCP tools, 40+ agent templates, 10 lifecycle hooks, 7 pipeline workflows. Persistent teams, structured meetings, task wall, real-time React dashboard. No LangChain/AutoGen — pure CC native integration.

What AI-company does

Summarised from the project README; check the repository for the latest details.

Features

• Current work and history: fresh `busy` evidence drives the current roster; waiting, closed and stale records remain available as history. Unknown source or model information stays unknown.
• Project and worktree visibility: inspect current tasks, observed context and uncommitted work before handing off or continuing a session.
• Cross-host messages: use `channelsend`, `channelread` and `channelwait` for explicit communication. A pending wait can return new messages; it does not restart an ended Codex turn.
• `AITEAMREADONLY` read-only profile: an orthogonal overlay that strips every write tool by explicit allowlist and keeps only read tools — ideal for audit / observer sessions.
• Auto-tracking: a hook turns each Workflow run into an OS "team" (`workflow-`) the moment it starts
• Dashboard `/workflows`: a live feed of run cards, a phase swimlane timeline, and per-agent telemetry — tokens / duration / status / tool-call counts, advancing live via incremental journal tailing while a run executes

Tools exposed (20+)

• team_status – Get team details and member status
• team_list – List all teams
• agent_update_status – Update recorded Agent status
• agent_list – List team members
• agent_template_list – Get available Agent template list
• agent_template_recommend – Recommend the best Agent template based on task description
• task_run – Create a team task with parent/dependency links and waiting state; does not launch execution
• task_status – Query task execution status
• task_create – Create a project task with parent/dependency links; `autostart` changes status only, and the retired `tasktype` remains a no-op
• task_create_batch – Atomically create 1-100 tasks with local `@key` references and an idempotency key
• task_update – Update or clear fields, reparent tasks, record waiting, and check revisions; completion validates children and unlocks dependencies
• task_memo_add – Add an execution memo to a task
• task_memo_read – Read task history memos
• task_list_project – List all tasks under a project
• usage_reconciliation – Compare saved journal, agent registration and external execution evidence; report scope, gaps and truncation without running a model
• meeting_create – Create a structured meeting (8 templates, keyword auto-select)
• meeting_send_message – Send a meeting message
• meeting_read_messages – Read meeting records
• meeting_conclude – Summarize meeting conclusions
• meeting_template_list – Get available meeting template list

Requirements

• Python >= 3.11; Python 3.12 is recommended for development and validation
• uv (`pip install uv`)
• Claude Code or Codex with MCP support; hook setup is host-specific
• Node.js >= 20 (Dashboard frontend, optional)

How to install AI-company

Listed on Socketlist – add this badge to your README:

Badge markdown[](https://socketlist.pages.dev/s/cronusl-1141-ai-company/)

Maintain this project? Get it featured for free during launch →

Compare with codebase-memory-mcp →

Related Databases MCP servers