searchLABSCO SUMMARY
Pay-per-call research, with the payment inside the protocol.
There is no key to provision and no plan to choose: the first call comes back with a price, the client pays it in USDC on Base, and the retry carries the proof. That makes cost a per-call decision and makes the failure mode legible — an agent that cannot pay gets a requirement back rather than a wrong answer.
What it is
An MCP wrapper around the Secant Agent Research Pack, a paid research API built for autonomous agents. Four tools cover search, extraction, a bundled research run and change monitoring, and payment is part of the call rather than a subscription arranged beforehand.
What you get
- Ranked web search —
search - Search, selected page extraction, normalized JSON and citations in one run —
research_pack - Readable page text and metadata from a URL —
extract_page - Page change checks between visits —
monitor_diff - The same retry-safe payment shape on every tool: call without
paymentto get the upstream requirement back, pay it, then retry with the proof and the samepayment_identifier
Requirements
Every tool is paid. The API quotes a requirement in Base USDC over x402 and returns HTTP 402 until a valid proof arrives, so the client has to be x402-capable and funded; an unpaid call comes back with payment_required: true and the upstream body, and nothing paid runs until the live API accepts the proof. Run it from the image — docker build -t secant-agent-research-mcp . then docker run --rm -i secant-agent-research-mcp. The package is secant-agent-research-mcp (version 0.1.1), and its server.json also lists a Streamable HTTP endpoint at https://agentic.secantoutreach.com/mcp/. SECANT_AGENT_RESEARCH_API_BASE_URL overrides the API base.
Setup effort
One command — docker run --rm -i secant-agent-research-mcp
USE CASES
01
Answering a question that needs sources
Run the bundled research pack to get search, extracted pages and citations back as one normalized result.
02
Reading one page cleanly
Pull readable text and metadata from a URL instead of handing the model raw HTML.
03
Watching a page for changes
Re-check the page and get back what moved since the last look.
04
Finding candidates before paying to read them
Run ranked search first, then extract only the pages worth the cost.
4 tools
Listed in project docs. Your client may show a different list.
research_packextract_pagemonitor_diffBEFORE YOU INSTALL
What to know first
Tools you get
4 tools named in the project's documentation.
Requires
docker on PATH
INSTALLATION
Connect your client
Add the block to your client, or run the command directly.
Server setup
Configuration file
JSON
{
"mcpServers": {
"docker": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"secant-agent-research-mcp"
]
}
}
}docker
TERMINAL
docker run --rm -i secant-agent-research-mcpHosted endpoint
ENDPOINT URL
https://agentic.secantoutreach.com/mcp/Add this hosted endpoint to your MCP client.
