A Model Context Protocol (MCP) server that enables **multi-agent orchestration** using Claude AI through Claude Desktop. Create, manage, and
A Model Context Protocol (MCP) server that enables multi-agent orchestration using Claude AI through Claude Desktop. Create, manage, and coordinate specialized
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| create_agent | Create a new specialized agent |
| list_agents | View all saved agents |
| chat_with_agent | Interact with specific agents |
| delete_agent | Remove an agent permanently |
| create_finance_team | Generate complete financial analysis team |
| get_conversation_history | View chat history and agent transfers |
| reset_conversation | Clear conversation history |
{
"mcpServers": {
"claude-swarm": {
"command": "python3",
"args": [
"/path/to/claude-swarm-mcp/claude_swarm_mcp_server.py"
],
"env": {
"ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| ANTHROPIC_API_KEY | Declared in the maintainer’s client configuration. | Check documentation |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
1. **analyze_prompt**: Analyzes prompt quality and identifies issues 2. **optimize_prompt**: Applies specific optimization strategies 3.
Use the following npx invocation as the MCP server command in your client's configuration:
MCP server: Russian market analytics (fl.ru + Petrovich). 11 tools, 6 skills, x402
A document reading, search, and metadata server to provide access to PDFs (and, in the future, other formats) to LLMs via the Model Context Protocol