Company research
The gateway exposes two read-only workflow boundaries on the primary API host:
GET https://api.replynodes.com/v1/company-research?domain=<domain>GET https://api.replynodes.com/v1/competitor-research?domain=<domain>&competitors=<host,host,...>
Each workflow admits exactly once per valid request, then performs a server-owned, read-only fan-out over url-to-markdown, brand-kit, and brand-logo primitives. The response is a composed JSON dossier; malformed input is rejected before admission.
Anonymous quota (Tier C)
Keyless callers share 3 valid requests per trusted client IP per UTC calendar day
for each workflow (company-research and competitor-research capabilities). The
gateway returns X-RateLimit-Limit, X-RateLimit-Remaining, and X-RateLimit-Reset
(Unix seconds for the next UTC midnight). Redis or quota degradation returns 503.
Presenting an API key or OAuth access token moves the call onto the authenticated path; package credit pricing for these workflows is not set yet (see capabilities discovery).
MCP
The MCP tool names match the OpenAPI operation IDs:
anonymous_company_research→GET /v1/company-researchanonymous_competitor_research→GET /v1/competitor-research
MCP tool calls require a ReplyNodes API key or OAuth access token issued for MCP
(https://mcp.replynodes.com/mcp). The tools forward to the same gateway routes above.
Skill attribution
Downstream producers may send X-ReplyNodes-Skill: company-research on workflow or
primitive calls so api_request analytics carry skill=company-research and
surface=skill. Only that exact header value is accepted; unknown values are ignored.
Related guides
- Competitor research for the same workflow across 1 to 5 competitor domains
- Brand intelligence for the primitives composed inside the workflow
- Web context for crawl/scrape primitives agents may chain manually