MCP.so
Sign In

turva.dev

@erekola

About turva.dev

The public read-only MCP server for turva.dev, live at mcp.turva.dev/mcp. Published in the official MCP registry as dev.turva/turva-mcp.

Connection details

https://mcp.turva.dev/mcp

Setup

claude mcp add turva --transport http https://mcp.turva.dev/mcp

Tools

4

Returns turva.dev's service catalog: agent-readiness audit, advisory, implementation, agent operations, and MCP server design, plus the engagement model and pricing (fixed list prices for audit, advisory and implementation; agent operations and MCP server design on request). Use this when a user asks what turva.dev offers, what it costs, or how an engagement works. Read-only: returns static JSON and changes nothing.

Returns turva.dev's own agent-readiness score from an independent public scanner (isitagentready.com), including category sub-scores, with the measurement date and verification links. Use this when a user asks how turva.dev scores, whether its claims are verifiable, or what proof backs the audit service. Read-only: returns static JSON and changes nothing.

Returns the latest public web-security scan results for turva.dev's own domain (Hardenize, Internet.nl), with the scan date. Use this when a user asks about turva.dev's own security posture or wants evidence beyond agent-readiness scores. Read-only: returns static JSON and changes nothing.

Returns turva.dev's engagement principles: async-only, least access, the result shows up in scanner numbers, and open and verifiable. Use this when a user asks how turva.dev works with clients or what rules an engagement follows. Read-only: returns static JSON and changes nothing.

Overview

What is turva.dev?

turva.dev is a public, read-only Model Context Protocol (MCP) server for the turva.dev agent-readiness audit and advisory service. It lets AI agents query turva.dev’s service catalog, its own agent-readiness scores, public web-security scan results for its domain, and its engagement principles – all as structured JSON instead of scraped HTML.

How to use turva.dev?

Point any MCP client that supports Streamable HTTP at https://mcp.turva.dev/mcp. An example client configuration is provided. No authentication or API key is required.

Key features of turva.dev

  • Four read-only tools returning structured JSON.
  • Tools: get_services, get_agent_readiness, get_security_evidence, get_principles.
  • Data served from static TypeScript objects; every response is deterministic.
  • Scores include a measurement date and live verification links.
  • Public and auditable – no authentication needed.
  • Built on Cloudflare Workers, independent from the main turva.dev site.

Use cases of turva.dev

  • AI agents querying turva.dev’s service catalog and pricing.
  • Verifying turva.dev’s own agent-readiness score from an independent scanner.
  • Checking public web-security scan results for the turva.dev domain.
  • Understanding turva.dev’s engagement principles (async-only, least access, etc.).

FAQ from turva.dev

What data does turva.dev expose?

Four read-only tools: service catalog (audit, advisory, implementation, agent operations, MCP server design), an agent-readiness score from one independent scanner (isitagentready.com), public web-security scan results (Hardenize, Internet.nl), and engagement principles.

Does turva.dev require authentication or an API key?

No. All exposed data is public and read-only. No authentication or API key is required.

How is the data served?

Data is bundled as static TypeScript objects in a Cloudflare Worker, so responses are deterministic and depend on no external state.

How can I verify the scores?

Each tool response includes a measurement date and links to the independent scanner reports (isitagentready, Hardenize, Internet.nl) so you can re-run any scan and compare.

What transport does turva.dev use?

Streamable HTTP on POST /mcp. No SSE transport. Server card JSON is available at GET / and GET /.well-known/mcp.

Frequently asked questions

What is the turva.dev remote MCP server?

The turva.dev remote MCP server is a hosted Model Context Protocol endpoint at https://mcp.turva.dev/mcp, so AI assistants can connect to it without installing or running anything locally.

How do I connect to the turva.dev MCP server?

Add the endpoint https://mcp.turva.dev/mcp to any MCP-compatible client such as Claude Code, Cursor, or VS Code. The setup snippets on this page configure each client in one step.

Does the turva.dev MCP server require authentication?

No. turva.dev's MCP server does not require authentication — you can connect directly with the endpoint URL.

Which transport does the turva.dev MCP server use?

turva.dev exposes a stdio endpoint, the transport used by remote MCP servers and supported by all major MCP clients.

Comments