OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
MCP & Tooling

Aci

Aci is open-source infrastructure that gives AI agents and agentic IDEs access to external tools through direct function calling or a unified MCP server, with dynamic discovery, multi-tenant authentication, secrets management and granular permissions.

Independent OpenViST project profile, based on linked sources.

Aci — OpenViST project profile in MCP & Tooling.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Aci when an agent needs to work across several external services and the integration should be exposed through MCP or direct function calls. It is especially relevant when authentication, runtime tool selection and permission boundaries are part of the design.

Who it is for

  • Developers building custom AI agents with external service access.
  • Teams integrating agentic IDEs with deployment, infrastructure or SaaS tools.
  • Builders creating assistants, research agents, sales agents or customer-support agents.

Documented uses

  • Connect an agent to a catalog of external tools.
  • Replace separate service-specific API and OAuth integration work with a unified access layer.
  • Expose tools through MCP or direct SDK-based function calls.
  • Discover relevant tools dynamically at runtime.
  • Apply authentication and permission boundaries to agent tool use.
Before you choose

Requirements & limits

The project is available as an Apache-2.0 open-source repository, with cloud, self-hosted and server deployment contexts identified. The repository documents local development through separate backend and frontend README files and links to a managed service.

  • Choose MCP when the consuming agent or IDE supports a unified MCP server; choose an SDK when the application needs direct function calls.
  • The tool catalog, authentication and permissions are central advantages for agents that operate across multiple services.
  • Dynamic discovery can reduce the number of tools exposed to an agent at once.
  • The platform is primarily implemented in Python, while Python and TypeScript SDKs are listed for integration.
  • Local deployment involves separate backend and frontend components, so teams should review both component READMEs before setup.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
2 October 2026
Original website title
aipotheosis-labs/aci · Official homepage title · retained in its source language
How we review sourcesSuggest a correction