LastSearch-AI
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SERP_API_KEY | No | Tavily API key for web search (not needed if using BROWSE_API_KEY) | |
| BROWSE_API_KEY | No | BrowseAI Dev API key (replaces SERP_API_KEY and OPENROUTER_API_KEY) | |
| OPENROUTER_API_KEY | No | OpenRouter API key for LLM (not needed if using BROWSE_API_KEY) |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| browse_searchC | Search the web for information on a topic. Returns URLs, titles, snippets, and relevance scores. |
| browse_openB | Fetch and parse a web page into clean text using Readability. Strips ads, nav, and boilerplate. |
| browse_extractC | Extract structured knowledge (claims + sources + confidence) from a single web page using AI. |
| browse_answerB | Full deep research pipeline: search the web, fetch pages, extract claims, build evidence graph, and generate a structured answer with citations and confidence score. |
| browse_compareC | Compare a raw LLM answer (no sources) vs an evidence-backed answer. Shows the difference between hallucination-prone and grounded responses. |
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 has a clearly distinct purpose with no overlap: browse_answer handles full research pipelines, browse_compare compares answer types, browse_extract extracts from single pages, browse_open fetches/parses pages, and browse_search performs web searches. The descriptions clearly differentiate their scopes and workflows.
All tools follow a consistent 'browse_verb' pattern (browse_answer, browse_compare, browse_extract, browse_open, browse_search), using snake_case uniformly. This predictable naming makes it easy for agents to understand and select tools based on their action verbs.
With 5 tools, this server is well-scoped for web research and browsing tasks. Each tool earns its place by covering distinct aspects of the domain (searching, fetching, extracting, comparing, and full research), avoiding bloat while providing comprehensive functionality.
The tool set covers core web research workflows effectively, including search, page retrieval, extraction, and answer generation/comparison. A minor gap exists in operations like updating or managing saved data, but agents can work around this for most research tasks.