Distri: A Composable Agent Framework MCP Server

@distrihub

Repository Homepage

Basic information

About Distri: A Composable Agent Framework MCP Server

Distri is A2A compatible OpenClaw like agent framework built in Rust.

#mcp #openai #anthropic #agentic #deepseek

Distri: A Composable Agent Framework MCP Server config

No standard config provided

This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.

Repository

Distri: A Composable Agent Framework MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Distri?

Distri is an open-source AI agent framework built in Rust. It lets you define agents in markdown, connect product functions as tools, and run them from the CLI, as an API server, or embedded in a React UI.

How to use Distri?

Install via the curl script or Homebrew, then run distri serve to start the server and web UI on port 7777 (default). Use distri run <agent> --task "..." to execute built-in or custom agents, or define agents in markdown files and push them to Distri Cloud.

Key features of Distri

Agents defined in markdown with TOML frontmatter.
Built-in tool system: builtins, dynamic HTTP, external client-side, MCP.
Skills: on-demand knowledge documents loaded at runtime.
Sub-agents for delegation with isolated context and token budgets.
Remote execution in sandboxed containers.
Self-hosted with SQLite, no external dependencies required.

Use cases of Distri

Run web search and scraping agents.
Sandboxed code execution.
Multi-phase research with sub-agent delegation.
Embed agent chat into React applications.
Design and push custom agents to a cloud service.

Frequently asked questions

Does Distri require a runtime like Node.js or Python?

No. Distri is a single compiled binary and requires no external runtime. It only needs SQLite for storage.

How do I define my own agent?

Create a markdown file with TOML frontmatter specifying the agent’s name, tools, and system prompt. Run it with `distri run --agent my_agent --task "..."` or push it to Distri Cloud.

Can I trace agent executions?

Yes. Distri provides a trace viewer and the `distri traces list/show` CLI command, showing full traces from agent to steps to LLM and tools with token/cost/latency data.

What is the default port for the server?

The default port is 7777. You can change it with `--port 8080` or any other port.

Is there a cloud service for Distri?

Yes, Distri Cloud allows you to push agents and skills,

Comments

More AI & Agents MCP servers

fhirHydrant

faulkj

Open-source Node.js FHIR MCP server with SMART Backend Services, metadata-aware search/CRUD tools, compact responses, FHIRPath filtering, safe pagination, audit events, and terminology lookup.

AgentRisk M2M

Neurobyteio

AgentRisk M2M 🛡️ The Security & Trust Layer for Autonomous Agents on Base. Stop letting your trading agents get rekt by stealth honeypots, dynamic sell-blocks, and rugpulls that pass every static check. ⚡ The Problem

OpenZiti MCP Gateway

openziti

NetFoundry MCP Gateway enables secure, isolated access to Model Context Protocol (MCP) tools across distributed systems without exposing public endpoints. Zero trust gateway for MCP servers. Aggregate, filter, and secure

Poly-Glot AI Workspace

hmoses

1,000+ fully localized prompt templates across 40+ categories. Compare Mode — send the same prompt to up to 9 AI providers (ChatGPT, Claude, Gemini, Grok, Groq, Copilot, Mistral, Perplexity, DuckDuckGo AI) and compare an

hausverbot

eliduarte37

BERGHAIN MCP server — sovereign AI stress-testing mcp / ai / multi-agent / adversarial / stress-test / claude