Binoculars Local MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BINOCULARS_PROFILE | No | Selects the model profile (e.g., qwen2.5-0.5b). | |
| BINOCULARS_OBSERVER_MODEL | No | Local directory path to the observer model weights. | |
| BINOCULARS_PERFORMER_MODEL | No | Local directory path to the performer model weights. |
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 |
|---|---|
| binoculars_statusC | Check local model configuration and the scoped Python socket guard. |
| binoculars_analyze_textB | Assess text using pre-existing local models; never proof of authorship. |
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 clearly distinct purposes: one performs text analysis, while the other reports local model configuration and socket guard status. There is no plausible overlap or risk of misselection.
Both tools consistently use the `binoculars_` prefix followed by a clear snake_case action/object name. The convention is predictable and uniform across the entire surface.
Two tools is borderline thin for a server that could reasonably expose model listing, configuration, or batch analysis operations. The count is defensible for a very narrow utility, but it feels under-scoped.
The surface covers the core analyze operation and a status check, but lacks obvious companion operations such as listing available models, inspecting a specific model, or configuring local model settings. Agents may hit dead ends when they need to discover or modify model configuration.