How do I connect AgentCrew MCP Server to Claude?

Run `claude mcp add agentcrew -- uvx agentcrew-ai` in Claude Code, or add the same command and arguments under mcpServers in Cursor's mcp.json or Claude Desktop's claude_desktop_config.json, then restart the client. The blocks above are ready to paste.

Is AgentCrew MCP Server free?

The listed licence is Apache-2.0. 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 AgentCrew MCP Server do?

AgentCrew MCP Server documents 11 tools to the agent, including adaptive_learning, browser, clipboard. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.

AgentCrew

Unclaimed

by saigontechnology

Chat application with multi-agents system supports multi-models and MCP

Set up this server

Compare servers My Stack

01 / Choose your client

02 / Before you connect

Authentication is not specified. Check the project instructions before connecting.

Install the runtime required by the project and make it available to your client.

Project instructionsEnvironment variable names (optional)

Use names from the project instructions, separated by commas. Enter names only, never secret values.

03 / Add the configuration

Source: generated from public install instructions

claude mcp add --transport stdio 'agentcrew' -- 'uvx' 'agentcrew-ai'

Run in your terminal after replacing any placeholders.

04 / Check it in your client

Open your client’s MCP settings and confirm the server connects and lists its tools. A copied configuration does not confirm a working connection.

ai-agentsai-assistantanthropic-claudemcp-clientmodel-context-protocolmulti-agent-systemsterminal-apptool-use

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

11 of 11 tools

Documented tools (11)

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

adaptive_learning

Learn behavioral patterns from interactions

browser

Full browser automation (navigate, click, form fill)

clipboard

Read/write system clipboard

code_analysis

Read files, grep, analyze repo structure

command_execution

Run shell commands (rate limits, audit logs)

fetch_webpage

Extract content from a URL

file_editing

Write/modify files (search-replace blocks, backups)

memory

Store and retrieve conversation context

transfer

Hand off tasks to other agents

voice

Speak and listen (ElevenLabs or DeepInfra)

web_search

Search the web via Tavily

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 AgentCrew MCP Server

How do I connect AgentCrew MCP Server to Claude?: Run `claude mcp add agentcrew -- uvx agentcrew-ai` in Claude Code, or add the same command and arguments under mcpServers in Cursor's mcp.json or Claude Desktop's claude_desktop_config.json, then restart the client. The blocks above are ready to paste.
Is AgentCrew MCP Server free?: The listed licence is Apache-2.0. 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 AgentCrew MCP Server do?: AgentCrew MCP Server documents 11 tools to the agent, including adaptive_learning, browser, clipboard. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.