Stash MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FAVORITES | No | Filter resources by favorites only | true |
| LOG_LEVEL | No | Log level: DEBUG, INFO, WARNING, ERROR | INFO |
| STASH_API_KEY | Yes | Required API key (mandatory) | |
| STASH_ENDPOINT | No | Stash server endpoint | http://localhost:6969 |
| STASH_CONNECT_RETRIES | No | Initial connection retries | 3 |
| STASH_CONNECT_DELAY_SECONDS | No | Delay between retries (seconds) | 1.5 |
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
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_performer_infoB | Return detailed information for a single performer |
| get_all_performersA | Return a list of performers with advanced filtering options |
| get_all_scenesB | Return all scenes from Stash with advanced filtering options |
| get_all_scenes_from_performerA | Return all scenes for a given performer |
| health_checkA | Return basic health/connectivity information for the MCP server |
| advanced_performer_analysisC | Advanced performer analysis with progress reporting and contextual logging |
| batch_performer_insightsC | Generates insights for multiple performers with detailed progress |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| analyze-performer | Generates a complete analysis of a performer including statistics, popular scenes, frequent tags and similar recommendations |
| library-insights | Generates insights about the library: trends, metadata gaps, organization recommendations |
| recommend-scenes | Based on user preferences, recommends specific scenes with explanation of why each recommendation |
| discover-performers | Discover performers based on specific user criteria |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| All performers | List of all favorite performers in the Stash database |
| Performers Statistics | Statistical summary of all performers in the database |
| All studios | List of all favorite studios in the Stash database |
| Studios Statistics | Statistical summary of all studios in the database |
| All tags | List of all favorite tags in the Stash database |
| Tags Statistics | Statistical summary of all tags in the database |
TDQS
Scored across 7 tools
There is some overlap between get_all_scenes and get_all_scenes_from_performer, as the former likely supports filtering by performer. The two analysis/insight tools also have similar purposes, which could cause selection confusion.
Tool names largely follow a consistent get_ prefix pattern for retrieval operations, but health_check and the analysis tools (advanced_performer_analysis, batch_performer_insights) deviate from this convention. Overall, naming remains predictable and readable.
With 7 tools, the server is well-scoped for its domain. Each tool serves a distinct function, and the count is appropriate for a focused MCP server without being excessive or too sparse.
The server covers performer retrieval and analysis well, but scene support is incomplete: there is no get_single_scene equivalent to get_performer_info. Missing CRUD operations or other resource types like tags or studios also create notable gaps for a comprehensive Stash interface.