Aziel Runtime logo - MCP Servers AI tool

Aziel Runtime

MCP ServerFree

Aziel Runtime connects AI assistants to software catalog discovery and execution tools through the Model Context Protocol. It supports remote and local connection modes, with public remote access requiring no API key or OAuth.

Last updated:

  • Official. Built and maintained by the company or project behind the service, so usually kept in step with it. Not audited by us.

  • Community. Built and maintained by an independent developer or group, not by the company behind the service. The company has not reviewed it, and updates depend on its author.

Aziel Runtime screenshot - MCP Servers interface and features overview

About Aziel Runtime

Aziel Runtime is an MCP server that connects an AI assistant to software catalog discovery and execution tools. Through that connection, an assistant can inspect catalog entries, look up libraries, check registry information, and call supported operations. The service also exposes tools for proposal checks, ledger operations, adaptive memory, and mesh-related work. What is available to call depends on the specific operation and product; some catalog entries cannot be executed through the public endpoint.

What can Aziel Runtime do?

The server groups discovery and execution capabilities around software catalogs. An assistant can inspect available entries, request descriptions, call supported operations, and use verification tools. Library search and proposal checks provide additional ways to look up information and evaluate proposed actions.

  • Discover software and inspect catalog descriptions.
  • Call supported operations and verify registry entries.
  • Search libraries and check proposals.
  • Use ChainLock ledger operations, adaptive memory, and mesh-related tools.
  • Use operation previews, confirmation-gated writes, background jobs, and receipt-related outputs where supported.

These capabilities do not mean every listed item is executable remotely. Some entries are stubs or local-only, and public execution depends on the operation and product.

How Aziel Runtime connects and authenticates

Aziel Runtime can run as a local stdio MCP server through the project’s CLI packaging, or connect remotely over Streamable HTTP at its public MCP endpoint. Public remote access is described as requiring no API key or OAuth; a runtime token can be configured for protected deployments. The project documents Claude Desktop, Cursor, Grok, ChatGPT GPT Actions, and Venice, and also describes support for other clients that work with MCP or OpenAPI. For hosted calls, payloads are sent to a third-party Worker operated for the project.

Who is Aziel Runtime best for?

Aziel Runtime is suited to people who want an AI assistant to discover and call supported software operations, search libraries, check proposals or registry entries, or use its ledger, memory, and mesh-related tools. The verified information identifies a free open-source option and does not identify a required vendor account or separate vendor service plan. Choose the local stdio route when running the project’s CLI packaging; choose the public remote endpoint when a compatible client should connect over HTTP.

What Aziel Runtime can access and change

The assistant can request catalog descriptions, library lookups, registry verification, and other information exposed by supported tools. It can also invoke supported operations that change state, including ledger-related operations; mutating calls require explicit confirmation or dry-run behavior. Some entries are stubs or local-only and refuse public execution, so access and changes are operation- and product-specific. When using the hosted endpoint, call payloads are sent to the project-operated third-party Worker.

Alternatives to Aziel Runtime

For assistants focused on connecting to other software services, GitHub MCP is an alternative for GitHub-related work, while Supabase MCP Server is an alternative for Supabase-related work. These are adjacent choices when the target service, rather than a general software catalog, determines which MCP server fits the task.

Key Features

Discover software catalogs and inspect available entries with catalog and description tools.

Call supported operations and use verification tools to check registry entries.

Search libraries and access proposal checks, ledger operations, adaptive memory, and mesh-related tools.

Use the public remote MCP endpoint over Streamable HTTP without an API key or OAuth.

Run a local stdio MCP option through the project’s CLI packaging.

Preview operations; mutating calls require confirmation or dry-run behavior.

Use supported background jobs and receipt-related outputs where available.

Connect with Claude Desktop, Cursor, Grok, ChatGPT GPT Actions, Venice, and other compatible clients.

Before you installSecurity checklist for MCP servers

An MCP server runs code and gives your AI assistant access to files, accounts or data. A few minutes of checking is worth it.

  1. Check the source. Make sure the repository belongs to the vendor or author you expect, that the vendor's own documentation links to it, and that it is actively maintained. Beware of lookalike names.
  2. Read what it can do. Look at the tools the server exposes and the permissions or scopes it asks for. Start with read-only access where the server allows it.
  3. Use the least access that works. Give it a dedicated API key or a narrowly scoped token, ideally on a test project or sandbox, not your production credentials.
  4. Pin versions and review updates. Install a specific version, read changes before upgrading, and do not run copied commands you do not understand.
  5. Treat what it returns as untrusted. Documents, web pages and tool results can contain text that tries to steer your AI assistant. Keep confirmation switched on for actions that write, delete, send or spend.
  6. Know where your data goes. Find out whether the server runs on your machine or is hosted, and what it sends to the vendor or to third parties.
  7. Keep a way back. Know how to revoke the key and remove the server from your client's configuration.

This page is general information, not security or legal advice, and listing a server is not an endorsement or a security review. We do not create, host or control MCP servers, and listing details such as commands, permissions or pricing can be out of date, so check the official source. You install and use MCP servers at your own risk. See the section on third-party products in our Terms of Service.

Pricing Plans

Free (open source)

Free

  • The project repository is available under an open-source license.
  • The public MCP endpoint requires no API key.
  • No separate vendor service plan or required vendor account was identified.

Pricing information last updated: October 20, 2026

FAQs

Does the public endpoint require an API key or OAuth?

No. The public remote endpoint is described as requiring neither. A runtime token may be configured for protected deployments.

Can I run Aziel Runtime locally?

Yes. The repository provides a local stdio MCP option through its CLI packaging.

Which clients are documented?

The project documents Claude Desktop, Cursor, Grok, ChatGPT GPT Actions, and Venice. Other MCP- or OpenAPI-capable clients are also described.

Can every catalog entry be executed through the public endpoint?

No. Some entries are stubs or local-only and refuse public execution; availability depends on the operation and product.

How are mutating operations handled?

Mutating calls require explicit confirmation or dry-run behavior; the endpoint specifies c or dry_run=true.