Skip to main content
Glama
jnilrac
by jnilrac

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
SECANT_AGENT_RESEARCH_API_BASE_URLNoBase URL for the live Secant Agent Research API.https://agentic.secantoutreach.com

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

CapabilityDetails
tasks
{
  "list": {},
  "cancel": {},
  "requests": {
    "tools": {
      "call": {}
    },
    "prompts": {
      "get": {}
    },
    "resources": {
      "read": {}
    }
  }
}
tools
{
  "listChanged": true
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
searchA

Run ranked web search for autonomous agents.

Unpaid calls return the upstream HTTP 402/x402 payment requirement before execution. Paid retries with a valid payment proof return structured search results from the live Secant Agent Research API.

research_packA

Run the full paid research workflow: search, extraction, JSON, and citations.

Use this when an agent needs a compact source-backed research packet rather than raw search results. Unpaid calls return x402 payment terms; paid retries return normalized results and extraction details.

extract_pageA

Extract readable content, metadata, links, and hashes from page URLs.

Use this when the caller already knows which pages matter and only needs cleaned extraction output. Blocked or failed pages are returned as extraction errors by the upstream API.

monitor_diffA

Check whether a page changed since a previous hash or text snapshot.

Use this for lightweight monitoring of docs, pricing pages, competitor pages, status pages, or other URLs an agent revisits. Unpaid calls return x402 payment terms before execution.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4.1/5.0

Scored across 4 tools

Disambiguation4/5

The tools are distinct in purpose: search for web searching, extract_page for content from known URLs, monitor_diff for change detection, and research_pack as a higher-level combined workflow. While research_pack encompasses search and extraction, it is presented as a different service level, so confusion is minimal.

Naming Consistency4/5

Three tools follow a verb_noun pattern (extract_page, monitor_diff, research_pack), with 'research_pack' being noun_noun but still clear. 'search' is a single verb, slightly deviating but acceptable. Overall pattern is recognizable and consistent.

Tool Count5/5

Four tools is an appropriate number for a research-focused server, covering key operations (search, extraction, monitoring, and a bundled paid workflow) without being overbearing or insufficient.

Completeness4/5

Core research workflows (search, extract, monitor, full research pack) are covered. Minor gaps exist, such as lacking a tool to list or retrieve previous research packs, but the set is functional for autonomous agents.

Maintenance

ActivityInactive
ResponsivenessNo issues