Shelv MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SHELV_API_KEY | Yes | API key for Shelv shelf operations. Required for stdio mode or as a fallback in HTTP mode. | |
| SHELV_MCP_HTTP_HOST | No | The host address to bind for HTTP transport. Defaults to 127.0.0.1. | 127.0.0.1 |
| SHELV_MCP_HTTP_PORT | No | The port to bind for HTTP transport. Defaults to 3334. | 3334 |
| SHELV_MCP_TRANSPORT | No | MCP transport protocol to use (stdio or http). Defaults to stdio. | stdio |
| SHELV_MCP_READ_MAX_BYTES | No | The maximum number of bytes to read from a single file. Defaults to 250000. | 250000 |
| SHELV_MCP_SEARCH_MAX_BYTES | No | The maximum number of total bytes for a search operation. Defaults to 5000000. | 5000000 |
| SHELV_MCP_SEARCH_MAX_FILES | No | The maximum number of files to include in a search. Defaults to 500. | 500 |
| SHELV_MCP_ENABLE_WRITE_TOOLS | No | Set to 'true' to enable tools like create_shelf and hydrate_shelf. | |
| SHELV_MCP_SEARCH_MAX_MATCHES | No | The maximum number of matches to return in a search. Defaults to 200. | 200 |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_shelvesA | List shelves available to the authenticated user |
| get_shelf_treeA | Get the full file tree and file contents for a shelf |
| read_shelf_fileB | Read a single file from a shelf |
| search_shelfB | Search for text across files in a shelf |
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: list_shelves enumerates available shelves, get_shelf_tree retrieves a full shelf's structure and contents, read_shelf_file accesses a single file, and search_shelf performs text searches across files. There is no overlap in functionality, making tool selection straightforward for an agent.
All tool names follow a consistent verb_noun pattern using snake_case (e.g., list_shelves, get_shelf_tree, read_shelf_file, search_shelf). The naming is predictable and readable, with verbs like 'list', 'get', 'read', and 'search' appropriately describing the actions.
With 4 tools, the server is well-scoped for its purpose of managing shelves and files. Each tool serves a distinct and necessary function, covering listing, retrieval, reading, and searching without being overly sparse or bloated.
The toolset provides strong coverage for core operations like listing, reading, and searching shelves and files. However, there are minor gaps in CRUD/lifecycle coverage, such as no tools for creating, updating, or deleting shelves or files, which agents might need to work around for full management tasks.