Skip to content

Custom Agents

PT | EN

Integrate Vectora with custom agents in Python, Node.js, Go, or any language that supports HTTP.

Integration Options

MethodUse CaseComplexity
MCPAgent runs locally in Go/Rust[x]
REST APIRemote agent in Python/Node/Go[x]
ACP (Beta)Distributed inter-agent communicationBeta

REST API (Recommended to Start)

Vectora exposes a REST API (beta) that any agent can call:

curl -X POST https://vectora.app/api/search \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "How to validate JWT tokens?",
    "namespace": "your-project",
    "top_k": 5
  }'

MCP for Custom Agents

If your agent is written in Go/Rust, you can use MCP directly:

Your Agent (Python/Node) ↔ MCP Client ↔ Vectora MCP Server

See MCP Integration for details.

Get Started

  1. Obtain an API token at console.vectora.app
  2. Configure your agent to call /api/search
  3. Test locally with curl
  4. Integrate into your workflow

Full Reference


Need a specific integration? Open an Issue

External Linking

ConceptResourceLink
MCPModel Context Protocol Specificationmodelcontextprotocol.io/specification
MCP Go SDKGo SDK for MCP (mark3labs)github.com/mark3labs/mcp-go
JWTRFC 7519: JSON Web Token Standarddatatracker.ietf.org/doc/html/rfc7519

Part of the Vectora ecosystem · Open Source (MIT) · Contributors