Deterministic MCP tool flows for AI agents. Remove unnecessary LLM calls between predictable tool steps.
Setup
Choose your client, copy the config, then fill in any required environment variables.
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>"
]
}
}
}