Novelty Research MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| EXA_API_KEY | No | API key for Exa, used as web and patent search fallback. | |
| GOOGLE_CSE_ID | No | Custom Search Engine ID for Google Custom Search. | |
| TAVILY_API_KEY | No | API key for Tavily, used as web and patent search fallback. | |
| GOOGLE_CSE_API_KEY | No | API key for Google Custom Search, used as primary web search backend. | |
| SEMANTIC_SCHOLAR_API_KEY | No | API key for Semantic Scholar, provides higher rate limits for publication search. |
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 |
|---|---|
| research_session_startC | Vytvorí alebo aktualizuje SQLite research session a vráti jej identifikátor. |
| research_session_understand_queryC | Rozloží a uloží očistené údaje dotazu pre výskumnú reláciu. |
| patent_evidence_to_sessionC | Získa patentové dôkazy a uloží kompaktný výsledok do SQLite session. |
| publication_evidence_to_sessionC | Získa publikačné dôkazy a uloží kompaktný výsledok do SQLite session. |
| web_evidence_to_sessionC | Získa webové dôkazy a uloží kompaktný výsledok do SQLite session. |
| research_session_checklistC | Skontroluje, či má research session dosť dôkazov na finalizáciu. |
| research_session_user_answerC | Vráti finálny používateľský report z dôkazov uložených v SQLite. |
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 7 tools
Each tool targets a distinct phase of the research pipeline: session creation, query decomposition, three evidence sources (patent/publication/web), readiness checking, and final report generation. The three evidence tools differ only by source type, which is an intentional and clear parallel structure rather than a source of confusion.
Tool names follow two clear patterns: research_session_* for lifecycle operations and {source}_evidence_to_session for evidence gathering, all in snake_case. Minor deviation: research_session_checklist and research_session_user_answer use nouns rather than verbs, breaking the otherwise consistent verb-first convention.
Seven tools map cleanly onto the novelty research workflow with no redundancy. Each tool earns its place in the pipeline, and the count is well within the ideal 3-15 range for a focused server.
The full research workflow is covered: start session, decompose query, gather evidence from three sources, check readiness, and produce the final report. Minor gaps exist—no way to delete/reset a session or remove incorrectly stored evidence—but these are edge cases rather than workflow-breaking omissions.