solodot-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SUPABASE_URL | No | Supabase project URL (required for remote HTTP mode). | |
| VERTEX_API_KEY | No | API key for Vertex AI. | |
| SOLODOT_MCP_PORT | No | Port for HTTP server (optional, default 8787). | |
| ANTHROPIC_API_KEY | No | API key for Anthropic. | |
| SUPABASE_SECRET_KEY | No | Supabase secret key (required for remote HTTP mode). | |
| SOLODOT_MCP_API_KEYS | No | Bearer token for HTTP mode authentication. | |
| SOLODOT_MCP_ENV_FILE | No | Absolute path to .env file for container run (optional). | |
| SOLODOT_DEFAULT_PROVIDER | No | The default AI provider, either 'anthropic' or 'vertex'. |
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": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| route_painpointB | Diagnose the active solo-founder painpoint, select exactly one Solodot execution pack, and return a lightweight action preview. This does not perform external actions. |
| generate_execution_assetA | Generate one concrete, preview-only execution asset for the pack already selected by route_painpoint. The routed pack cannot be changed by this tool. |
| review_execution_assetA | Record approve, revise, or reject for a generated Solodot asset. Approval records acceptance only and never executes the asset externally. |
| get_solodot_runA | Return the authenticated founder's diagnosis, generated assets, approval history, and latest recommended step. |
| export_solodot_runA | Return an approved execution asset as Markdown or JSON. The tool returns content only; it does not write files, post messages, or publish. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| execution-packs | The six workflows available to the painpoint router. |
| approval-boundaries | Actions that Solodot must never perform silently. |
| product-context | The product promise and role of the intake/router. |
TDQS
Scored across 5 tools
Each tool has a clearly distinct purpose: route_painpoint diagnoses and selects a pack, generate_execution_asset creates a preview asset, review_execution_asset records approval/revision/rejection, export_solodot_run returns the approved asset, and get_solodot_run retrieves the current state. No two tools overlap in functionality.
All tool names follow a consistent verb_noun pattern using snake_case: route_painpoint, generate_execution_asset, review_execution_asset, export_solodot_run, get_solodot_run. The verbs are distinct and the nouns are domain-specific, making the pattern predictable and clear.
With 5 tools, the server is well-scoped for the solo founder painpoint workflow. Each tool represents a key step in the process (diagnosis, generation, review, export, status retrieval) without unnecessary duplication or omission.
The tool set covers the core lifecycle: route_painpoint starts, generate_execution_asset creates, review_execution_asset evaluates, export_solodot_run delivers, and get_solodot_run provides status. A minor gap is the lack of a tool to update or delete assets or runs, but the workflow is essentially complete for a linear process.