Quick Index & Predictable Endpoints
All endpoints are keyless, unauthenticated, and return structured payloads with standard RFC rate limit headers:
Query 233,000+ indexed academic papers via OpenAlex with cursor pagination.
100% typed response schemas, RFC rate limit headers, and parameter documentation.
Direct AI agent tools for research papers, essays, glossary, and scanner.
Agent tools to retrieve documentation, OpenAPI specs, and course curricula.
Audit any domain across 61 machine discovery, MCP, and security checks.
Standardized machine discovery catalog for all public API endpoints.
Instant notification stream of new research essays and publications.
Index of all 490+ canonical public URLs with modification timestamps.
Structured index for AI crawlers with links to full-text digest.
Machine-readable agent guidance, tools, and operational boundaries.
Keyless access guidelines and security verification standards.
Cryptographic security contacts and vulnerability disclosure policy.
Accept: text/markdown on any page to fetch its clean Markdown twin.Developer Support →Report Search API & REST Endpoints
Search 233,000+ indexed academic papers across the AI and Web3 corpora, backed by OpenAlex and sorted by citations. Results are cached for one hour.
GET /api/reports/search?q=stablecoin+regulation&corpus=ai&page=1&per_page=20Parameters: q (required, min 2 chars), corpus (ai or web3), page, per_page (max 200), cursor (for cursor pagination). Full schema lives in the OpenAPI 3.1 Specification.
Model Context Protocol (MCP) Servers
Vedang runs dual, production-ready MCP servers over Streamable HTTP (JSON-RPC 2.0) with zero authentication required:
1. Product MCP Server (Action & Research)
Endpoint: https://veda.ng/.well-known/mcp (also at /api/mcp)
search_reports— Query 233k+ papers via OpenAlexsearch_essays— Find technical essays in Essays Libraryget_essay— Fetch full Markdown text of any essaysearch_glossary— Search 100+ terms in Glossary Indexscan_agent_readiness— Audit websites on Agentic Scanner
2. Documentation MCP Server (Knowledge & Docs)
Endpoint: https://veda.ng/.well-known/mcp/docs (multi-server manifest: /mcp.json)
get_api_docs— Fetch developer documentation (/developers & /docs)get_openapi_spec— Fetch full OpenAPI schema (/openapi.json)get_auth_guide— Keyless access guidelines (/auth.md)get_course_data— Full curricula for Prompt, Web3, MCP, Agentic
curl -X POST https://veda.ng/.well-known/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize",
"params":{"protocolVersion":"2025-06-18","capabilities":{},
"clientInfo":{"name":"my-client","version":"1.0"}}}'OpenAPI 3.1 Specification
The machine-readable OpenAPI specification documents 100% typed response schemas, RFC rate-limit headers, cursor pagination, batch execution, and async polling:
Multi-Language SDK Packages & Tooling
Programmatic SDK packages and CLI tools for Python, TypeScript/JavaScript, and Go:
pip install vedang-cli
npm install vedang
Generate typed API clients for Go, Rust, Java, Swift, or Ruby using the OpenAPI specification:
npx @openapitools/openapi-generator-cli generate -i https://veda.ng/openapi.json -g typescript-fetch -o ./sdk
Authentication & Security Protocols
All public reading and search APIs on veda.ng are keyless and require no API token. The complete WorkOS-format authentication specification is documented at /auth.md (interactive page at /auth). Security vulnerability disclosure instructions are published at /.well-known/security.txt.
Markdown Content Negotiation
Every essay, every glossary term, and key pages serve clean Markdown twins to autonomous machines. Send an Accept: text/markdown header instead of parsing heavy HTML:
curl -H "Accept: text/markdown" https://veda.ng/agentstack
Explore live Markdown twin endpoints: /agentstack (.md), /about (.md), /glossary/mcp (.md), and /developers (.md).
Discovery Feeds & Machine Manifests
Standardized machine endpoints and discovery catalogs for autonomous agents and web spiders: