search
Search the web for information on a topic. Returns URLs, titles, snippets, and relevance scores.
LABSCO SUMMARY
Answers where the confidence number is computed from evidence rather than asserted by a model.
What separates this from a search tool is everything after extraction: each claim is decomposed into atomic facts, matched back against the text of the pages it came from, cross-checked across independent sources, and penalised where contradictions appear — so verified, consensus level and source authority arrive as fields an agent can act on rather than as prose. Sessions are the other half: a shared session can be forked, which turns one agent's verified research into another's starting point.
What it is
A research pipeline exposed as tools: search, fetch pages, extract atomic claims, verify each one against the actual source text, and return an answer with citations and a confidence score. Sessions accumulate what has been verified, so later questions build on earlier ones.
What you get
- Web search returning URLs, titles, snippets and relevance scores
- A page fetched and reduced to clean text, with ads, navigation and boilerplate stripped out
- Structured knowledge extracted from a single page — claims with their sources and confidence
- The full pipeline in one call: search, fetch, extract, build the evidence graph, and answer with citations and a confidence score
- Three depth settings — a single pass for quick lookups, an iterative confidence-gated loop for fact-checking, and a multi-step mode with gap analysis for complex questions
- A whole document fact-checked: every atomic claim extracted and verified against live sources
- A raw model answer compared against an evidence-backed one, to show what grounding actually changes
- An anti-hallucination mode that can return only the enhanced prompts, with no model call made at all
- Research sessions created, asked within — recalling prior verified claims — recalled without new searches, exported as accumulated knowledge, shared as a public URL, and forked from someone else's share
- Feedback submitted on a result, or on one specific claim, which tunes the verification thresholds
- Per-claim fields an agent can branch on: verified, verification score, consensus count and level, source authority, and any contradictions detected
Requirements
An API key, free to obtain, passed to the server as LASTSEARCH_API_KEY; the server itself runs over stdio through npx. The verification engine is a hosted service, so calls go out to lastsearch.ai even when the server runs locally — the MCP server and frontend are open source, the engine is not. Sessions need the key, since that is what establishes ownership of one. The free tier covers 100 premium queries a day, with deep queries costing three times as much, and when the quota runs out queries fall back to keyword-only verification rather than failing; it resets every 24 hours.
Setup effort
One command plus a key — npx lastsearch setup, then supply credentials
USE CASES
01
Answering a question you cannot afford to get wrong
Run the full pipeline at a higher depth and read the confidence and per-claim verification, not only the prose.
02
Fact-checking something already written
Hand over the document and get every atomic claim in it verified against live sources.
03
Reading one page properly
Fetch it stripped to clean text, then extract the claims and their sources from it.
04
Building up knowledge across a project
Create a session and ask inside it, so later questions recall what the earlier ones already verified.
05
Handing your research to someone else
Export the accumulated claims, or share the session as a public URL they can fork and carry on from.
06
Checking what grounding is worth on this question
Compare a raw model answer against an evidence-backed one for the same query.
07
Reusing earlier work without spending searches
Recall the relevant verified claims from the session instead of running the pipeline again.
14 tools
Listed in project code.
open
Fetch and parse a web page into clean text using Readability. Strips ads, nav, and boilerplate.
extract
Extract structured knowledge (claims + sources + confidence) from a single web page using AI.
answer
Full deep research pipeline: search the web, fetch pages, extract claims, build evidence graph, and generate a structured answer with citations and confidence score. Use depth='thorough' for auto-retry with rephrased queries when confidence is low. Use depth='deep' for multi-step agentic research that identifies knowledge gaps and runs follow-up searches. Enterprise: use searchProvider to search internal data instead of the public web. DISCLAIMER: Results are AI-generated for informational purposes only — not financial, medical, or legal advice. Confidence scores are algorithmic estimates, not accuracy guarantees. Always verify critical information from primary sources.
compare
Compare a raw LLM answer (no sources) vs an evidence-backed answer. Shows the difference between hallucination-prone and grounded responses.
verify_document
Fact-check an entire document (AI-generated report, competitive analysis, market research, news article). Pass either raw text OR a URL — we'll extract every atomic claim and verify each against live web sources. Returns per-claim verification status with sources, NLI scores, and an overall A-F grade. Use for auditing the accuracy of long-form content from other AI agents.
clarity
Clarity — anti-hallucination answer engine. Three modes: (1) mode='prompt': Returns only enhanced system + user prompts with anti-hallucination techniques. No LLM call, no internet. Use this when you want YOUR OWN LLM (e.g. Claude) to answer using the enhanced prompts. (2) mode='answer' (default): Rewrites prompt, calls LLM with grounding instructions, returns answer with extracted claims. Fast, no internet. (3) mode='verified': Does #2, then runs full browse pipeline (search + extract + verify), fuses best of both — source-backed claims, evidence-based confidence. Use for maximum accuracy.
session_create
Create a new research session. Sessions persist knowledge across multiple queries — each query builds on prior research.
session_ask
Research a question within a session. Recalls prior knowledge, runs the research pipeline, and stores new claims. Later queries in the same session benefit from accumulated knowledge.
session_recall
Query accumulated knowledge from a session without making new web searches. Returns previously verified claims relevant to the query.
session_share
Share a research session publicly. Returns a shareable URL that anyone can view — great for sharing research findings with teammates, in reports, or on social media.
session_knowledge
Export all knowledge from a research session. Returns all verified claims, sources, and confidence scores accumulated across queries.
session_fork
Fork a shared research session to continue building on someone else's research. Creates a copy of all knowledge in your own session.
feedback
Submit feedback on a search result to improve future accuracy. Helps the self-learning engine tune verification thresholds.
BEFORE YOU INSTALL
What to know first
Tools you get
14 tools when we connected.
Requires
- npx on PATH
- LASTSEARCH_API_KEY in your environment
Where it runs
All 3 documented clients run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
npx lastsearch setupMCP Clients
Claude Desktop, Cursor, Windsurf
JSON
{
"mcpServers": {
"lastsearch": {
"command": "npx",
"args": [
"-y",
"lastsearch"
],
"env": {
"LASTSEARCH_API_KEY": "<YOUR_LASTSEARCH_API_KEY>"
}
}
}
}
