MCP.so
Sign In

Inistate

@Inistate

Repository

About Inistate

Inistate is a process platform where AI agents and humans share the same workflow primitives — same forms, same state transitions, same audit trail. Connect any MCP client (Claude, Cursor, Gemini CLI, custom agents) to design modules, run state transitions, query entries, and upl

#ai#nocode#aiteammate

Basic information

Category

AI & Agents

Transports

stdio

Publisher

Inistate

Submitted by

dylon-inistate

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "Inistate": {
      "type": "streamable-http",
      "url": "https://mcp.inistate.com/mcp",
      "note": "For Streamable HTTP connections, add this URL directly in your MCP Client"
    }
  }
}

Tools

16

List workspaces the user has access to

Set the active workspace

List all discoverable modules in the workspace

Get the canvas schema (basic or extended tier)

Get full module definition with stable IDs (round-trippable)

Query entries with filters, sorting, and pagination

Read a single entry by ID

Get form fields and defaults for an activity

Create, edit, delete, or run custom activities

Get entry audit trail and comments

Upload a file to S3 storage

Download a file (returns pre-signed URL)

Generate a scaffolded module template from a description

Validate a module schema before creating or updating

Create a new module with schema

Update an existing module's schema

Overview

What is Inistate?

An MCP server for the Inistate platform that enables module discovery, entry management, and activity submission for developers and users of the Inistate system.

How to use Inistate?

Install via npx -y inistate-mcp or globally with npm install -g inistate-mcp. Set the INISTATE_API_TOKEN environment variable, then configure your MCP client (e.g., Claude Desktop or Claude Code) to launch the server. Invoke tools like list_workspaces, list_modules, and submit_activity to interact with the Inistate API.

Key features of Inistate

  • List and switch between workspaces.
  • Discover modules and retrieve their schemas.
  • Create, read, update, and delete entries.
  • Submit activities and manage entry lifecycle.
  • Upload and download files via S3 storage.
  • Design and validate FACTSOps module workflows.

Use cases of Inistate

  • Designing a custom workflow module for approvals or pipelines.
  • Browsing and managing entries in a workspace.
  • Automating entry creation and updates via activity submission.
  • Investigating entry history and audit trails.
  • Validating a module schema before deploying it.

FAQ from Inistate

What environment variables are required?

INISTATE_API_TOKEN is required for authentication. INISTATE_API_BASE is optional and defaults to https://api.inistate.com.

How do I install Inistate?

Run npx -y inistate-mcp to fetch and run the package on demand, or install globally with npm install -g inistate-mcp and execute inistate-mcp.

Which tools are available?

The server provides 17 tools, including list_workspaces, set_workspace, list_modules, get_module_schema, get_entry, submit_activity, upload_file, design_workflow, validate_design, create_module, and update_module.

Do tests require an API token?

No. Integration tests spin up the server as a child process and verify tool discovery, resource reads, and prompt retrieval without any API token.

What transports does Inistate support?

It uses stdio by default and supports HTTP transport in production (e.g., with PM2). Authentication uses a Bearer token set via the INISTATE_API_TOKEN environment variable.

Comments

More AI & Agents MCP servers

Web Agent Protocol

OTA-Tech-AI

🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support

500

Sequential Thinking Multi-Agent System (MAS)

FradSer

An advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP.

306

Model Context Protocol Server for Home Assistant

tevonsb

A MCP server for Home Assistant

574

欢迎来到 智言平台

Shy2593666979

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

797

Just Prompt - A lightweight MCP server for LLM providers

disler

just-prompt is an MCP server that provides a unified interface to top LLM providers (OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama)

733