workflows-mcp
by qtsone
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MEMORY_DB_HOST | No | PostgreSQL hostname or IP (enables memory features) | |
| MEMORY_DB_NAME | No | Target database name | memory_db |
| MEMORY_DB_PORT | No | PostgreSQL port | 5432 |
| MEMORY_DB_USER | No | Database username | |
| AUDIT_FAIL_CLOSED | No | When true, audit-logging failures abort memory operation | false |
| MEMORY_DB_PASSWORD | No | Database password | |
| WORKFLOWS_LOG_LEVEL | No | Logging level (DEBUG, INFO, WARNING, ERROR, CRITICAL) | INFO |
| WORKFLOWS_LLM_CONFIG | No | Optional path override for LLM config | |
| MEMORY_DB_AUTO_CREATE | No | Auto-create the target database on first boot | true |
| WORKFLOWS_JOB_TIMEOUT | No | Default async timeout in seconds | 3600 |
| MEMORY_DB_ADMIN_DATABASE | No | Admin database used for CREATE DATABASE | postgres |
| WORKFLOWS_TEMPLATE_PATHS | No | Comma-separated workflow directories to load | |
| WORKFLOWS_JOB_HISTORY_MAX | No | Max retained job records | 1000 |
| WORKFLOWS_JOB_HISTORY_TTL | No | Job retention TTL in seconds | 86400 |
| WORKFLOWS_IO_QUEUE_ENABLED | No | Enable serialized I/O queue | true |
| WORKFLOWS_JOB_QUEUE_ENABLED | No | Enable async job queue | true |
| WORKFLOWS_JOB_QUEUE_WORKERS | No | Queue workers | 3 |
| WORKFLOWS_MAX_CONCURRENT_JOBS | No | Max active + queued jobs | 500 |
| WORKFLOWS_MAX_RECURSION_DEPTH | No | Max workflow composition depth | 50 |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/qtsone/workflows-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server