IFS Cloud Bridge
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
MCP Server for IFS Cloud (Python)
An open source project to connect IFS Cloud to the AI agent you already use. No new platform, no extra product to buy.
This is a standard Model Context Protocol (MCP) server that runs on your own machine. Use it with Claude Code, Codex CLI or any other AI agent that supports MCP. The setup differs per tool; the server is the same.
Version 2 is a Python rewrite of knakit/ifs-mcp-server-local (TypeScript). Tools, skills and the
~/.ifs-mcpconfig and session files are unchanged, so existing setups keep working.
This is anopen source initiative, provided as-is under the MIT license. You are in control of what your AI agent can do with IFS, so be cautious about using it in production: start with a test instance and review what the agent does before it changes data. See Your data and your control.
The idea
Connecting an AI agent to IFS Cloud is hard for one reason: the data. IFS exposes its functionality through projections (OData endpoints), and there are around 5,000 of them, each with its own data structure. Building an agent that knows all of that is practically impossible.
But nobody uses all of IFS. In their day-to-day work, the average user touches only a handful of screens and needs only the data they see on them.
This project doesn't try to teach an agent everything. It gives you a framework to connect IFS Cloud to your AI agent, and lets you build skills for the parts of IFS you actually use. You build a skill once, from your own requirements, and then use it however you like.

Related MCP server: SmartSuite MCP Server
What you can do
Ask in plain language, for example:
"Find the customer Acme and show me their delivery address."
"Run the quick report 'Session Stats'."
"Export all open purchase orders to a CSV."
"I work in the Purchase Order screen every day. Create a skill so you can help me with it."
You can register several IFS instances (dev, test, prod), switch between them and mark any of them read-only.
How it works
The server is a broker between your AI agent and IFS Cloud. It turns requests into IFS API calls and brings the data back. To pick the right endpoint, the agent needs to know your IFS endpoints, and that knowledge lives in skills.
What is a skill?
A skill is a plain Markdown file that describes an IFS area: its endpoints, how to call them and what the data looks like. The agent reads the matching skill before it calls an API, so it doesn't have to guess IFS-specific paths and field names.
It ships with skills for finding the projection behind a screen and running Quick Reports, plus guides for OData syntax and for building skills.
Build your own (no coding needed):
From a screen name: tell the agent which IFS screen you use. It finds the projection behind it, fetches the live OpenAPI spec and drafts the skill. Best for master data such as customers, suppliers and parts. If you already know the projection name, you can give that instead.
From a browser recording: record your workflow in IFS (DevTools → Network → Save as HAR). The agent extracts the API calls and builds the skill with you. Best for multi-step transactions.
Import one: take a skill from a URL or a local file. Share yours, and find others', in the community skills repository.
If no skill matches, the agent finds the projection in the IFS navigator and asks before it creates one.
Skills are saved inside the server's own folder by default, so an update can wipe them. Set askills directory (a folder on your machine, or a git repo) before you start building. See Configuration.
Your data and your control
Runs locally. The server runs on your machine and talks only to your IFS Cloud instance (and to a URL you give it when importing a skill). No telemetry.
Credentials stay local. OAuth tokens are stored only on your machine, are sent only to your IFS Cloud instance, and are never returned to the agent. The server won't accept a client secret in chat. For headless
client_credentialslogin you supply the secret yourself (environment variable orconfig.json).Limit what the agent can do. Mark an environment
readOnlyto block everything except GET. For a hard limit, use a dedicated IFS user with only the permission sets it needs.Know what reaches the AI model. Data that a tool returns into the conversation is sent by your AI agent to its model provider. The server does not control that step. The FAQ lists, action by action, what the model sees and what stays local.
Quick start
You need: an IFS Cloud instance where you can create an OAuth client (or ask your IFS administrator to), an AI agent that supports MCP, and Python 3.10+.
Create an OAuth client in IFS Cloud (IAM → IAM Clients). See Installation, step 1.
Install the server. Clone this repo and create its virtual environment once:
python -m venv .venv .venv/Scripts/python -m pip install -e . # Windows .venv/bin/python -m pip install -e . # macOS / LinuxThen register it with your AI agent:
Tool | How |
Claude Code |
|
Codex CLI |
|
Other MCP tools | Register |
launch.py runs the server inside the repo's .venv. The Claude Desktop one-click .mcpb bundle from the TypeScript version is not offered for v2.
Register your IFS instance by asking the agent to add an environment (how).
Log in: ask the agent to log in to IFS (for a headless
client_credentialsenvironment this happens automatically). A local page shows which environment and instance you are signing in to, and whether it is read-only, before sending you to the IFS sign-in:Sign-in page
After signing in


Build your first skill: ask the agent to create a skill for a screen you use, for example "I work in the Purchase Order screen every day. Create a skill so you can help me with it." It finds the projection behind the screen, fetches the spec from your IFS, asks you a few questions and saves the skill. See Skill Authoring.
Once the skill is saved, ask for what you need in plain language, as in the examples above.
Full steps for each tool are in the installation guide.
Documentation
Document | What's in it | |
Get started | OAuth client, install for each AI agent, first login | |
Several IFS instances, interactive vs headless login, read-only | ||
Skills directory | ||
Guides | Build, update and share skills | |
Data flow and privacy, setup and cleanup | ||
Reference | Every tool and prompt | |
Components and data flows | ||
Project | Share skills, report bugs, develop the server | |
Data handling and vulnerability reporting · privacy policy |
MIT licensed. Not affiliated with IFS. Based on knakit/ifs-mcp-server-local by knak.it. Built with the help of Claude Code.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
Connect any AI agent to 1,000+ apps and 27,000+ actions through one remote MCP server (OAuth).
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceA production-ready MCP server that provides secure, delegated access to Microsoft 365 services including Email, SharePoint, OneDrive, and Calendar. It enables AI models to search messages, browse files, manage calendar events, and parse document contents using OAuth 2.1 authentication.MIT
- AlicenseAqualityCmaintenanceA locally-hosted MCP server enabling AI agents to securely interact with SmartSuite data, with configurable access modes and audit logging.8610MIT
- AlicenseNot gradedqualityDmaintenanceA self-hosted MCP server that enables AI assistants to inspect and manage Microsoft Power Automate cloud flows and Dataverse records locally, using your own Azure identity.MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server for OData v4 endpoints, especially Microsoft Dataverse/Dynamics 365, enabling authentication, schema discovery, querying, CRUD, and more via natural language.MIT