Deterministic MCP tool flows for AI agents. Remove unnecessary LLM calls between predictable tool steps.
接入配置
选择客户端，复制配置，再按项目文档补齐环境变量。
claude mcp add chainweaver -- uvx chainweaver '<FLOW_FILE>'~/.codex/config.toml
[mcp_servers.chainweaver]
command = "uvx"
args = ["chainweaver", "<FLOW_FILE>"]
# codex mcp add chainweaver -- uvx chainweaver '<FLOW_FILE>'~/.cursor/mcp.json
{
"mcpServers": {
"chainweaver": {
"command": "uvx",
"args": [
"chainweaver",
"<FLOW_FILE>"
]
}
}
}.vscode/mcp.json
{
"servers": {
"chainweaver": {
"type": "stdio",
"command": "uvx",
"args": [
"chainweaver",
"<FLOW_FILE>"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"chainweaver": {
"command": "uvx",
"args": [
"chainweaver",
"<FLOW_FILE>"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"chainweaver": {
"command": "uvx",
"args": [
"chainweaver",
"<FLOW_FILE>"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"chainweaver": {
"command": "uvx",
"args": [
"chainweaver",
"<FLOW_FILE>"
]
}
}
}