MCP UI Research
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_UI_DATA_DIR | Yes | Directory where MCP UI Research stores its data (SQLite database, etc.). | |
| MCP_UI_HTTP_TIMEOUT | No | Timeout in seconds for HTTP requests to external sites. |
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
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| research_nicheB | Research a niche and return references, design patterns, guidance, and original components. |
| inspect_referenceA | Inspect one public page for metadata and aggregate visual/UI patterns. |
| remember_deliveryB | Persist what the agent implemented so later reviews can compare intent and delivery. |
| recall_projectB | Recall prior research, delivery summaries, and reviews for a project. |
| review_implementationB | Run a deterministic HTML quality review and remember actionable feedback. |
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 5 tools
Each tool targets a distinct phase: research, inspection, memory, recall, and review. There is no overlap or ambiguity between them.
All tool names follow a consistent verb_noun pattern (research_niche, inspect_reference, remember_delivery, recall_project, review_implementation).
Five tools perfectly cover the core workflow without unnecessary extras, fitting well within the ideal range.
The tool surface covers the full research-to-review lifecycle: gather info, store delivery, recall past work, and assess implementation. No obvious gaps.