superlenz
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| EXA_API_KEY | No | Exa Search API key | |
| OUTPUT_PATH | No | Output directory for saved documents (default: ./output) | ./output |
| GITHUB_TOKEN | No | GitHub token for repository search | |
| ANTHROPIC_API_KEY | No | Enables LLM-based verification (rounds 9-10) | |
| BRAVE_SEARCH_API_KEY | No | Brave Search API key | |
| SEMANTIC_SCHOLAR_API_KEY | No | Semantic Scholar API key (improves rate limits) |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| start_researchA | Start a new research session with automatic multi-source search, collection, and cross-verification |
| search_sourcesB | Search for sources across multiple providers (web, academic, GitHub, etc.) |
| get_research_statusB | Get the current status of a research session |
| list_sessionsB | List all research sessions with optional filtering |
| cross_verifyA | Cross-verify a list of claims against optional source URLs. Returns verification confidence and conflict analysis. |
| save_to_storageA | Save a previously generated research document to a specific storage provider (markdown or json) |
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 6 tools
Each tool has a distinct role: starting a session, searching sources, checking status, listing sessions, cross-verifying claims, and saving output. Potential overlap between start_research and search_sources is resolved by start_research being a higher-level session creation, while search_sources is a standalone utility.
All tool names follow a clear verb_noun pattern in snake_case (start_research, search_sources, get_research_status, list_sessions, save_to_storage). Even cross_verify is a verb phrase, maintaining a consistent action-oriented style.
With 6 tools, the set is well-scoped for a research workflow without being too small or bloated. Each tool addresses a specific step in the process, making the count feel appropriate and complete.
The domain covers starting research, searching, checking status, listing sessions, cross-verifying, and saving. However, there is no direct way to retrieve the generated research document content; the agent must rely on save_to_storage to access results, which is a notable gap in the output lifecycle.