How do I connect AI Company MCP Server to Claude?

The listing records `pip install uv` as its setup step. Run it, then follow the repository's instructions for the client configuration; the listing names Claude Code, Cursor as compatible clients.

Is AI Company MCP Server free?

The listed licence is MIT. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.

What can AI Company MCP Server do?

AI Company MCP Server documents 40 tools to the agent, including agent_list, agent_template_list, agent_template_recommend. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.

AI Company

Unclaimed

by CronusL-1141

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.

Install

$pip install uv

Set up this server

Compare servers My Stack

This server needs project-specific setup. Follow the project instructions; no reusable public launch command is available yet.

Project instructions

agent-frameworkagent-orchestrationai-agentsautonomous-agentsclaudeclaude-codeclaude-code-plugindashboardfastapimcpmcp-servermeeting-systemmulti-agent-systempipeline-workflowpythonreactsqlitetask-managementteam-collaborationtypescript

Is this your MCP server?

This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.

Claim this server

Security profile

Claimed and verified servers get a weekly static scan that shows what the code can reach: external services, environment variables, shell commands, agent configuration folders, plus any dependencies with known advisories. Claim this listing to get one. How the security profile works

40 of 40 tools

Documented tools (40)

From project documentation. A server handshake does not verify each tool’s description or behavior.

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

agent_update_status

Update Agent status (idle/busy/error)

channel_mentions

Get unread @mentions for an agent

channel_read

Read messages from a channel

channel_send

Send a message to a channel (team:/project:/global) with @mention support

context_resolve

Resolve current context and retrieve relevant background information

debate_code_review

Start a code review debate session

debate_start

Start a structured 4-round debate (Advocate→Critic→Response→Judge)

decision_log

Log a decision to the cockpit timeline

default

core groups only (task,team,memory,infra,reports = 29 tools, hard-capped at <=50)

ecosystem

failure_analysis

Failure Alchemy — analyze root causes, generate antibody/vaccine/catalyst

link_query

Query the cross-domain reference graph by node (what references this / what does this reference)

link_trace

Trace a reference chain from any OS ID (wfid / commit / task uuid) with evidence snippets

meeting_conclude

Summarize meeting conclusions

meeting_create

Create a structured meeting (8 templates, keyword auto-select)

meeting_list

List all meetings

meeting_read_messages

Read meeting records

meeting_send_message

Send a meeting message

meeting_template_list

Get available meeting template list

meeting_update

Update meeting metadata

memory_add

Write a direction-layer memory (preference/correction/design intent, 4 kinds; bucket quotas 1200/1500/300 chars, <=400 chars per entry, supersedes swap)

memory_invalidate

Explicitly invalidate a direction-layer memory (by id or unique substring; invalidate, never delete — auditable)

memory_list

List valid direction-layer entries (kind filter; data source for both injection hooks)

memory_reconcile_apply

Apply agent-confirmed reconcile operations (merge / invalidate / score / promote); idempotent, size guardrails enforced on promote

memory_reconcile_candidates

On-demand reconcile coarse pass (zero-LLM): BM25-paired candidate groups + direction-layer inventory + promotion material + operation guide

memory_search

Search team memory — recency-window recall within scope + pure-Python BM25 rerank (Chinese bigram, no embeddings)

task_create

Create a new task (autostart supported; tasktype is accepted but retired — a no-op kept for backward compatibility)

task_list_project

List all tasks under a project

task_memo_add

Add an execution memo to a task

task_memo_read

Read task history memos

task_run

Execute a task with full execution recording

task_status

Query task execution status

task_update

Partial update of task fields with auto timestamps

team_briefing

Get a full team panorama in one call (members + events + meetings + todos)

team_list

List all teams

team_status

Get team details and member status

unified_search

Three-arm RRF search across memos / reports / tasks — BM25 full-text + knowledge-graph fanout + exact ID match

Tool change history

Compared across complete checks of the same configuration. Tools were listed, not invoked. Input-schema changes are not measured here.

No complete tool checks yet.

FAQ

Questions about AI Company MCP Server

How do I connect AI Company MCP Server to Claude?: The listing records `pip install uv` as its setup step. Run it, then follow the repository's instructions for the client configuration; the listing names Claude Code, Cursor as compatible clients.
Is AI Company MCP Server free?: The listed licence is MIT. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.
What can AI Company MCP Server do?: AI Company MCP Server documents 40 tools to the agent, including agent_list, agent_template_list, agent_template_recommend. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.