exa-research

Exa Research

Neural web search via BlockRun. Understands meaning, not keywords. Four distinct actions for different research modes.

How to Call from MCP

As of v0.14.1 the blockrun_exa tool is path-based. Pass the endpoint name as path and the request as body:

blockrun_exa({ path: "search",       body: { query: "AI agent frameworks 2026", numResults: 10 } })
blockrun_exa({ path: "answer",       body: { query: "What is speculative decoding?" } })
blockrun_exa({ path: "contents",     body: { urls: ["https://example.com/a", "https://example.com/b"] } })
blockrun_exa({ path: "find-similar", body: { url: "https://arxiv.org/abs/2401.12345", numResults: 5 } })

Quick Decision Table

Costs below are what you are actually CHARGED — the $0.001 transaction fee is already included (it applies once per call, not per result).

User wants...	Path	Body	Cost
Relevant URLs on a topic	search	{ query, numResults?, category? }	$0.0110/call
Cited answer to a question	answer	{ query }	$0.0110/call
Full text of URLs	contents	{ urls: [...] }	$0.002/URL + $0.001 → 1 URL $0.0030, 3 URLs $0.0070
Pages like a given URL	find-similar	{ url, numResults? }	$0.0110/call
Recent news	search + category: "news"	–	$0.0110/call
Academic papers	search + category: "research paper"	–	$0.0110/call
Company info	search + category: "company"	–	$0.0110/call

contents bills per URL, so batching URLs into ONE call is markedly cheaper than one call each: 3 URLs together cost $0.0070, but three separate calls cost $0.0090 — you pay the flat fee three times instead of once.

Valid category values for search: "news", "research paper", "company", "tweet", "github", "pdf".

Python SDK Instructions

1. Initialize (Python SDK)

from blockrun_llm import setup_agent_wallet

chain = open(os.path.expanduser("~/.blockrun/.chain")).read().strip() if os.path.exists(os.path.expanduser("~/.blockrun/.chain")) else "base"
if chain == "solana":
    from blockrun_llm import setup_agent_solana_wallet
    client = setup_agent_solana_wallet()
else:
    from blockrun_llm import setup_agent_wallet
    client = setup_agent_wallet()