Wren

Created By
Cannera year ago
Overview

what is Wren Engine?

Wren Engine is a semantic engine designed for Model Context Protocol (MCP) clients and AI agents, enabling precise data interactions across enterprise environments.

how to use Wren Engine?

To use Wren Engine, integrate it into your MCP client or AI agent workflow, following the quick start guide available in the documentation.

key features of Wren Engine?

  • Embeddable into any MCP client or AI agent workflow
  • Interoperable with modern data stacks like PostgreSQL, MySQL, and Snowflake
  • Semantic-first design for understanding data models and business logic
  • Governance-ready with user-based permissions and access control

use cases of Wren Engine?

  1. Enhancing AI agents with accurate business context for data retrieval
  2. Automating complex workflows across enterprise data systems
  3. Supporting BI dashboards and CRM updates with precise calculations

FAQ from Wren Engine?

  • What is the Model Context Protocol (MCP)?

MCP is an open standard that connects LLMs with tools, databases, and enterprise systems.

  • Is Wren Engine suitable for all types of businesses?

Yes! Wren Engine is designed to scale AI adoption across various enterprise environments.

  • What is the current status of Wren Engine?

Wren Engine is currently in beta, with ongoing updates and improvements.

Server Config

{
  "mcpServers": {
    "wren": {
      "command": "uv",
      "args": [
        "--directory",
        "/ABSOLUTE/PATH/TO/PARENT/FOLDER/wren-engine/mcp-server",
        "run",
        "app/wren.py"
      ],
      "autoApprove": [],
      "disabled": false
    }
  }
}
Project Info
Created At
a year ago
Updated At
a year ago
Author Name
Canner
Star
-
Language
-
License
-

Recommend Servers

View All
Voyei

3 hours ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

14 hours ago