MCP Claude Desktop
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Set the logging level. Use 3 for debug logging to see detailed execution information. | 1 |
| SKIP_CLAUDE_POLLING | No | Disable response polling to improve stability. When enabled, the server will send messages to Claude Desktop but won't try to read the response. | false |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| askC | Send a prompt to Claude Desktop and get a response |
| get_conversationsB | Get a list of available conversations in Claude Desktop |
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 2 tools
The two tools have completely distinct purposes with no overlap: 'ask' is for sending prompts and getting responses, while 'get_conversations' is for retrieving conversation lists. An agent can easily tell them apart as they target different actions and resources.
The naming is mostly consistent with a verb-based pattern ('ask', 'get_conversations'), but there is a minor deviation: 'ask' uses a simple verb while 'get_conversations' follows a verb_noun format. This slight inconsistency is noticeable but does not hinder readability.
With only 2 tools, the count feels thin for a Claude Desktop server, which might be expected to handle more interactions like managing conversations or settings. While it covers basic prompt and conversation listing, the scope seems limited, bordering on under-scoped for the apparent domain.
There are significant gaps in the tool surface for a Claude Desktop server. It lacks operations for managing conversations (e.g., delete, rename), handling settings, or interacting with specific conversation details. This incomplete coverage could lead to agent failures when trying to perform common desktop tasks beyond basic prompting and listing.