Secant Agent Research
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SECANT_AGENT_RESEARCH_API_BASE_URL | No | Base 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
| Capability | Details |
|---|---|
| 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
| Name | Description |
|---|---|
| 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
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
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.
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.
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.
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.