Deep Research MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| start_deep_researchB | Conduct comprehensive research on any topic with a systematic, balanced approach. This tool guides thorough research that adapts to question complexity - from simple queries to complex multi-faceted investigations. KEY FEATURES: • Adaptive depth: Automatically scales research based on question complexity (3-8 subquestions) • Source evaluation: Assesses credibility (High/Medium/Low) and evidence strength (Strong/Moderate/Weak/Speculative) • Multiple perspectives: Examines different viewpoints and competing theories when relevant • Critical analysis: Checks logic, identifies biases, and acknowledges limitations • Clear reporting: Structured reports with executive summary, findings, analysis, and conclusions • Confidence levels: Each conclusion includes confidence rating based on evidence quality • Proper citations: All sources properly attributed with URLs Works for any research type: historical events, technical topics, current affairs, comparative analyses, scientific questions, cultural topics, and more. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| deep-research | A prompt to conduct deep research on a question |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Research Process Notes | Notes generated during the research process |
| Research Data | Structured data collected during the research process |
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'start_deep_research' has a clearly defined and distinct purpose for conducting comprehensive research.
Since there is only one tool, naming consistency is inherently perfect. The tool name 'start_deep_research' follows a clear verb_noun pattern that would be consistent if more tools existed.
A single tool is too few for a server named 'Deep Research MCP Server', which suggests a domain requiring multiple operations. While the tool is comprehensive, the lack of supporting tools (e.g., for follow-up queries, source management, or report customization) makes the surface feel incomplete and thin for the apparent scope.
The tool surface is severely incomplete for a deep research domain. There are obvious gaps: no tools for refining research, managing sources, updating findings, or handling different stages of research workflows. The single tool provides a starting point but leaves agents with no way to interact further with the research process.