Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work
Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks. Exposed over MCP by the crewai mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.
Homepage · Open Source · Docs · Start Cloud Trial · Blog · Forum
Everything the assistant can do here goes through one of these:
Purpose — built architecture**: Designed specifically for agent orchestration, with a lightweight Python core and clean primitives for real-world automationFine — grained control over execution paths for real-world scenariosAgent — ready capabilities**: Use tools, memory, knowledge, checkpointing, async execution, and MCP/A2A support for more capable production agentsProduction — ready patterns**: Add deterministic steps, human input, structured outputs, and checkpointing as your system growsor_ — Triggers when any of the specified conditions are metSkill — When it runsgetting-started — Scaffolding new projects, choosing between LLM.call() / Agent / Crew / Flow, wiring crew.py / main.pydesign-agent — Configuring agents — role, goal, backstory, tools, LLMs, memory, guardrailsdesign-task — Writing task descriptions, dependencies, structured output (output_pydantic, output_json), human reviewask-docs — Querying the live CrewAI docs MCP server for up-to-date API detailsYou will need 2 environment variables: OPENAI_API_KEY, SERPER_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Installation goes through your MCP client rather than a global install: point it at skills on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
Among the planning and project tracking options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Crewai's toolset — Purpose, Fine, Agent and 7 more — is a fair guide to whether it matches your workflow.
This entry was verified against Crewai's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Purpose | built architecture**: Designed specifically for agent orchestration, with a lightweight Python core and clean primitives for real-world automation. |
| Fine | grained control over execution paths for real-world scenarios |
| Agent | ready capabilities**: Use tools, memory, knowledge, checkpointing, async execution, and MCP/A2A support for more capable production agents. |
| Production | ready patterns**: Add deterministic steps, human input, structured outputs, and checkpointing as your system grows. |
| or_ | Triggers when any of the specified conditions are met. |
| Skill | When it runs |
| getting-started | Scaffolding new projects, choosing between LLM.call() / Agent / Crew / Flow, wiring crew.py / main.py |
| design-agent | Configuring agents — role, goal, backstory, tools, LLMs, memory, guardrails |
| design-task | Writing task descriptions, dependencies, structured output (output_pydantic, output_json), human review |
| ask-docs | Querying the live [CrewAI docs MCP server](https://docs.crewai.com/mcp) for up-to-date API details |
{
"mcpServers": {
"crewai": {
"command": "npx",
"args": ["-y", "skills"],
"env": {
"OPENAI_API_KEY": "your-value",
"SERPER_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| OPENAI_API_KEY | Credential the server authenticates with. | Yes |
| SERPER_API_KEY | Credential the server authenticates with. | Yes |
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Your assistant inside the workspace — read channels, search history, post messages and tame the noise.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.