io.github.cyanheads/workflows-mcp-server
Store, query, and create YAML workflow playbooks for LLM agents.
Verdict not yet evaluated for this tool. The hybrid eval runs adversarial cases first; coverage rolls out as the corpus expands. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: hybrid eval, four-state verdict, honest limits.
{
"mcpServers": {
"workflows-mcp-server": {
"command": "npx",
"args": [
"-y",
"@cyanheads/workflows-mcp-server"
],
"env": {
"WORKFLOWS_DIR": "./workflows-yaml",
"GLOBAL_INSTRUCTIONS_PATH": "<global_instructions_path>",
"WATCHER_DEBOUNCE_MS": "500",
"MCP_LOG_LEVEL": "info",
"MCP_HTTP_HOST": "127.0.0.1",
"MCP_HTTP_PORT": "3010",
"MCP_HTTP_ENDPOINT_PATH": "/mcp",
"MCP_AUTH_MODE": "none"
}
}
}
}{
"mcpServers": {
"workflows-mcp-server": {
"command": "npx",
"args": [
"-y",
"@cyanheads/workflows-mcp-server"
],
"env": {
"WORKFLOWS_DIR": "./workflows-yaml",
"GLOBAL_INSTRUCTIONS_PATH": "<global_instructions_path>",
"WATCHER_DEBOUNCE_MS": "500",
"MCP_LOG_LEVEL": "info",
"MCP_HTTP_HOST": "127.0.0.1",
"MCP_HTTP_PORT": "3010",
"MCP_HTTP_ENDPOINT_PATH": "/mcp",
"MCP_AUTH_MODE": "none"
}
}
}
}npx -y @cyanheads/workflows-mcp-serverWORKFLOWS_DIRAbsolute or relative path to the workflows root directory.
GLOBAL_INSTRUCTIONS_PATHPath to the global instructions markdown file. Derives from WORKFLOWS_DIR when not set.
WATCHER_DEBOUNCE_MSMilliseconds to debounce filesystem change events before rebuilding the index.
MCP_LOG_LEVELSets the minimum log level for output (e.g., 'debug', 'info', 'warn').
WORKFLOWS_DIRAbsolute or relative path to the workflows root directory.
GLOBAL_INSTRUCTIONS_PATHPath to the global instructions markdown file. Derives from WORKFLOWS_DIR when not set.
WATCHER_DEBOUNCE_MSMilliseconds to debounce filesystem change events before rebuilding the index.
MCP_HTTP_HOSTThe hostname for the HTTP server.
MCP_HTTP_PORTThe port to run the HTTP server on.
MCP_HTTP_ENDPOINT_PATHThe endpoint path for the MCP server.
MCP_AUTH_MODEAuthentication mode to use: 'none', 'jwt', or 'oauth'.
MCP_LOG_LEVELSets the minimum log level for output (e.g., 'debug', 'info', 'warn').
Focused MCP server for OpenAI image/audio generation (v2.0.0). Wraps endpoints via HAPI CLI.
Public MCP server for the LLM Search Engine
Audit your brand's visibility across ChatGPT, Gemini, Claude, Perplexity + 6 more engines.