serum-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SAMPLE_BANK_PATH | No | Root path to a sample bank directory for list_sample_files default browsing. | |
| SERUM_TABLES_PATH | No | Path to Serum's Tables folder. Derived from SERUM_PRESETS_PATH if unset. | |
| SERUM_PRESETS_PATH | No | Path to Serum 2 Presets/User folder. Falls back to default install locations if unset. | |
| SERUM_SAMPLES_PATH | No | Path to Serum's Samples folder. Derived from SERUM_PRESETS_PATH if unset. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_presetA | Write a new Serum 2 preset built from |
| edit_presetA | Apply a partial |
| list_parametersA | Return the full documented Serum 2 parameter schema (modules, value ranges, units, enum values, and how confidently each was verified) as JSON. Call this before proposing an edit so you know what parameter names and ranges are actually valid. |
| describe_presetA | Return a human-readable summary of an existing preset's sound-shaping parameters (oscillators, filters, envelopes, FX chain, mod routes, globals). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: create a new preset, edit an existing one, list the parameter schema, and describe a preset. There is no overlap or ambiguity.
All tools follow a consistent verb_noun pattern in snake_case (generate_preset, edit_preset, list_parameters, describe_preset), making the interface predictable.
With only 4 tools, the server is well-scoped for generating and editing Soundserum 2 presets. Each tool serves a necessary function without redundancy.
The tool set covers the core lifecycle (create, edit, describe, schema), but lacks a tool to list available presets or delete them. This minor gap does not significantly impair the primary workflow.