Secant Agent Research Pack
RemoteAbout Secant Agent Research Pack
Secant Agent Research Pack is a paid web research API wrapped as an MCP server for autonomous agents. It combines ranked search, page extraction, normalized results, citations, and page-change checks, with payment discovery and retry through x402.
Key features
- 01Ranked web search
- 02Research packs with citations
- 03Readable page text and metadata extraction
- 04Page change checks
- 05x402 payment requirement discovery
Use cases
- 01Searching the web for agent research
- 02Extracting pages into readable text and metadata
- 03Checking whether a page has changed
MCP support
Exposes search, research_pack, extract_page, and monitor_diff tools to MCP clients. Unpaid calls return the payment requirement; clients can retry with an x402 payment proof.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://agentic.secantoutreach.com/mcp/claude mcp add --transport http jnilrac-secant-agent-research https://agentic.secantoutreach.com/mcp/{"mcpServers":{"jnilrac-secant-agent-research":{"type":"http","url":"https://agentic.secantoutreach.com/mcp/"}}}Open in Cursor{"servers":{"jnilrac-secant-agent-research":{"type":"http","url":"https://agentic.secantoutreach.com/mcp/"}}}Open in VS Code{"mcpServers":{"jnilrac-secant-agent-research":{"type":"http","url":"https://agentic.secantoutreach.com/mcp/"}}}{"mcpServers":{"jnilrac-secant-agent-research":{"serverUrl":"https://agentic.secantoutreach.com/mcp/"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
6| Parameter | Type | Required | Description |
|---|---|---|---|
| query | string | Yes | Search query to run through the paid research API. |
| payment | object | Yes | x402 payment proof payload containing resource, amount, wallet, and settlement metadata. |
| max_results | integer | No | Maximum number of ranked search results to return. |
| facilitator_id | string | No | Settlement facilitator id. Use evm-base for Base USDC payments. |
| payment_identifier | any | No | Optional idempotency key. Reuse it on retries to return the cached paid result. |
Details
From the project READMESecant Agent Research MCP
MCP wrapper for the Secant Agent Research Pack, a paid x402 research API for autonomous agents.
The server exposes tools for:
search: ranked web search.research_pack: search, selected page extraction, normalized JSON, and citations.extract_page: readable page text and metadata extraction.monitor_diff: page change checks.
Tool Behavior
All tools use the same retry-safe x402 pattern:
- Call the tool without
paymentto receive the upstream payment requirement. - Pay the quoted Base USDC requirement with an x402-compatible client.
- Retry with the payment proof and, when available, the same
payment_identifier.
The wrapper returns payment_required: true and the upstream 402 body for unpaid calls. It does not execute paid work until the live API accepts the payment proof.
The native paid API uses HTTP 402 and Base USDC over x402. If you call a tool without a payment proof, the tool returns the upstream payment requirement so an agent can pay and retry. If you include a valid payment proof, the tool forwards it to the live API.
Run
docker build -t secant-agent-research-mcp .
docker run --rm -i secant-agent-research-mcp
Environment
| Variable | Default | Description |
|---|---|---|
SECANT_AGENT_RESEARCH_API_BASE_URL | https://agentic.secantoutreach.com | Base URL for the live Secant Agent Research API. |
Canonical Discovery
- Buyer page: https://agentic.secantoutreach.com/agent-research
- Smithery listing: https://smithery.ai/servers/hello-j2mo/secant-agent-research-pack
- x402 manifest: https://agentic.secantoutreach.com/.well-known/x402.json
- OpenAPI: https://agentic.secantoutreach.com/openapi.yaml
- Agent card: https://agentic.secantoutreach.com/agent-card.json
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.