MCP server · Avalix

avalix-ai-mcp.yml

Avalix operates ONE remote MCP server at https://avalix.ai/autonoma/mcp — the same origin as its website, the Autonoma OpenAPI and the A2A JSON-RPC endpoint. It is POST-only Streamable HTTP (a GET returns the JSON 404 {"error": "not found"}), reports MCP protocol version 2025-11-25, identifies itself as serverInfo {name: ai.avalix/autonoma, title: Avalix Autonoma Agent Services, version: 1.0.0, websiteUrl: https://avalix.ai/autonoma/}, and answers initialize and tools/list anonymously with six tools carrying real inputSchemas. resources/list and prompts/list return -32601 Method not found. The server's own initialize instructions read: "Avalix-owned service endpoint. Discover fixed-price services, run free previews, and request paid work. Never provide secrets." The tool names and descriptions are Autonoma-specific (list_offers, trust_preview, quote_task with an authorization_attestation const, request_service keyed on offer_slug) and match no shared platform fingerprint — a provider-built server. No MCP host of its own exists (mcp.avalix.ai does not resolve); the MCP resource host is the apex.

Open docs → Avalix provider profile

One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.

Provider: Avalix Type: Documentation link Transport: Host: avalix.ai

Documentation

https://avalix.ai/autonoma/mcp

Documentation link · transport

Tools

compatibility_check — Run deterministic static checks against one public URL or supplied non-sensitive JSON document.
list_offers — Return current fixed-price services and verified performance totals.
trust_preview — Run a free deterministic preview of supplied agent evidence.
task_capabilities — List bounded digital work this agent can quote and deliver.
quote_task — Classify and price a bounded task. Requires authority to commission the work and a target scope.
request_service — Request a service. Without payment_reference, returns exact Base USDC payment requirements; retry with the confirmed transaction hash.

About MCP

The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.

Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.

Work with this as data

Every MCP server here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for mcp servers

4 MCP tools reach this

find_mcpBrowse and filter every MCP server in the catalog.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This MCP server

curl "https://apis.io/api/v1/mcp/avalix-ai-mcp-yml"

All mcp servers

curl "https://apis.io/api/v1/mcp?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.