AGY Visual Witness MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AGY_BIN | No | Path to the agy executable. Overrides default lookup. | |
| AGY_VISUAL_MODEL | No | Model to use for provider execution. Defaults to gemini-3.6-flash-low. | gemini-3.6-flash-low |
| AGY_VISUAL_ROOTS | No | Allowed root directories for image access. Images must stay under this path or the roots passed by the caller. | |
| AGY_VISUAL_EXPECTED_SHA256 | No | Expected SHA-256 hash of the agy binary for identity verification. Required for comparison operations on non-test builds. | |
| AGY_VISUAL_ALLOW_UNVERIFIED_COMPARE | No | Set to '1' to allow comparison operations without verified agy identity. Output will report OBSERVED_NOT_PINNED. |
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 |
|---|---|
| describe_image_geminiB | Return QA-only visual evidence; never a deterministic acceptance verdict. |
| agy_visual_doctorC | Report agy/npx runtime presence and non-secret identity evidence. |
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 analyzes images via Gemini, the other checks runtime presence and identity evidence. There is no overlap or ambiguity between them.
The naming conventions are inconsistent: 'describe_image_gemini' follows a verb_noun_model pattern, while 'agy_visual_doctor' uses a product-prefixed noun phrase with no verb. This makes the set feel disjointed.
With only two tools, the server is minimal but still coherent with its stated 'Visual Witness' purpose. It feels slightly thin but not unreasonable for a specialized utility.
The tools cover image description and runtime diagnostics, but the 'Visual Witness' domain might benefit from additional operations like image comparison or evidence storage. There is no obvious dead end, but the surface is narrow.