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": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_webC | Search web via DuckDuckGo HTML (no API key) |
| scrape_pageC | Scrape URL to markdown |
| extract_insightsD | Extract insights |
| deep_researchC | Orchestrated deep research: search + parallel scrape + synthesize |
| compare_sourcesD | Compare 2-5 URLs |
| fact_check_claimD | Fact-check claim |
| memory_saveC | Save to persistent memory |
| memory_searchD | Search memory |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| deep-dive-research | Create a deep research workflow |
| fact-check | Fact-checking squad |
| compare-narratives | Compare sources |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| research-memory | Persistent research memory |
| research-history | History of all researches |
| research-stats | Stats |
TDQS
Scored across 8 tools
Each tool has a clear, distinct purpose: compare_sources compares URLs, deep_research orchestrates multi-step research, extract_insights extracts insights, fact_check_claim verifies claims, memory_save/search handle persistent memory, scrape_page fetches web content, and search_web performs web searches. No overlap.
All tool names follow a consistent snake_case convention with a clear verb_noun pattern (e.g., compare_sources, memory_save, scrape_page). The naming is predictable and easy to understand.
8 tools are well-scoped for a deep research server. The count is sufficient to cover core capabilities (search, scrape, compare, fact-check, memory) without being overwhelming.
The tool set covers the full research lifecycle: searching, scraping, comparing sources, extracting insights, fact-checking, and saving/retrieving memory. There are no obvious gaps for the intended purpose.