The knowledge layer a firm's AI agents work from: matters, clients, deadlines and invoices from the matter system and billing, certified once and served over MCP from a server in your network. On ibl.ai you own all the code and the data, run it model-agnostic across any LLM, and pay with no per-seat pricing — so you can deploy anywhere, from your own cloud to a fully air-gapped network. No need to choose build vs. buy — you get both.
“ibl.ai does amazing work and are great people.”
Prefer to build together? Our AI Transformation team builds agents and apps with yours, on your systems.
Not a data warehouse and not a copy of your data. ibl.ai's Agentic Ontology reads the systems you already run in place, names the business terms inside them, and serves the terms your people certify to any agent over MCP.
A managed AI vendor's knowledge layer usually means copying your data into the vendor's cloud and renting access to a model of your own organization. Agentic Ontology runs on your server, reads your systems where they are, and the code is yours.
| Agentic Ontology | A managed knowledge layer | |
|---|---|---|
| Where the data goes | Agentic OntologyRead in place by a server in your network; the ontology, passwords and MCP servers stay there. | A managed knowledge layerCopied into the vendor's cloud. |
| Who holds the code | Agentic OntologyYou do: MIT-licensed, built from source on your own server. | A managed knowledge layerThe vendor; you rent access. |
| What an agent can run | Agentic OntologyCertified tools with fixed definitions and fixed SQL; raw SQL only if you add that toolset. | A managed knowledge layerWhatever the vendor's connector exposes. |
| Who sees what | Agentic OntologyOne ibl.ai policy per toolset, callers signed in by ibl.ai, Entra ID or your own OIDC issuer, every call logged. | A managed knowledge layerThe vendor's accounts and service keys. |
| Which agents | Agentic Ontologyibl.ai agents, Claude, Codex, Cursor or any MCP client. | A managed knowledge layerThe vendor's own assistant. |
| Pricing | Agentic OntologyThe ontology is MIT-licensed; the ibl.ai platform is usage or a flat license, with no per-seat pricing. | A managed knowledge layerPer seat, per connector, per year. |
Agentic Ontology is ibl.ai's on-premise knowledge layer: it connects the databases and HTTP APIs your organization already runs, turns them into one set of business terms that your people certify, and publishes those terms as MCP servers any agent can call, from a server inside your network where you own all the code and the data.
It is open source under the MIT license and built from the public source on your own Ubuntu server. The ibl.ai platform supplies sign-in, roles, API keys and agents; your server keeps the ontology, the database passwords and the MCP servers.
An agent never gets arbitrary SQL unless you add the raw toolset: each certified term becomes a tool with a fixed definition and fixed SQL, and each caller sees only the toolsets its grant reaches.
How to connect your legal systems (document management, case management, billing, research) to AI agents — step by step.
Read the GuideFive steps, one page of the ibl.ai ontology console each. The screenshots come from the console's demo mode, which serves fixed sample data, so every name and address in them is made up. Select a screenshot to enlarge it.
Step 1 · Systems
Add a SQL connection or an HTTP API connection. SQL connections use a read-only login, credentials are tested before they are saved, and the password is kept on your server and nowhere else.
Step 2 · Map
The engine reads the tables, profiles the columns and names the business terms above them. The Map draws that semantic layer over the physical one, so you can see which tables each definition came from.
Step 3 · Ontology
Review what was inferred and certify it: object types, their properties, links and metrics. Personal columns are flagged, and only the definitions you certify are compiled into tools.
Step 4 · MCP Gateway, New MCP Server
Pick the toolsets, how callers sign in, and the origins and hosts allowed to reach the server. The config file is shown exactly as it will be written to your server, before anything is deployed.
Step 5 · MCP Gateway, the server
Deploy, attach the server to an ibl.ai agent with a key of its own, or paste a ready-made snippet into Claude, Codex or Cursor, then watch the calls arrive. Each server keeps its revisions, and Roll Back restores the last one.

Built on NVIDIA and Google. NVIDIA's auto-ontology engine infers the terms and Google's MCP Toolbox serves the tools, both running on your own server beside the ibl.ai console.

Install the Ontology on Your Own Server and Connect a Database to an Agent (12:39, YouTube)
A 12-minute walkthrough on the ibl.ai YouTube channel, from a fresh Ubuntu server to an ibl.ai agent answering questions about a CRM: the four-block install, connecting the CRM's database, the Map, publishing an MCP server and attaching it to the agent.
Agentic Ontology by ibl.ai gives a law firm one set of definitions over the systems it already runs: a matter is the same matter in the matter system, billing and the docketing calendar.
It reads those databases and HTTP APIs in place, your team certifies the terms it finds, and each caller sees only the toolsets its grant reaches.
Open source under the MIT license, and yours, including full code access.
Get started
$0per
month
No credit card required
Get Started FreeThis includes:
For one person trying things out
For everyday work
$15per
month
Billed monthly
Subscribe to ProEverything in Free, plus:
For professionals and small teams running agents every day
For all-day work
$50per
month
Billed monthly
Subscribe to MaxEverything in Pro, plus:
For teams and departments that depend on agents
For your largest deployments
$100per
month
Billed monthly
Subscribe to UltraEverything in Max, plus:
For organizations formalizing agents across many teams
This includes:
Enterprise — Own the Platform. Own the entire platform. We transfer the full source under a perpetual license and deploy it on-premise, in your cloud, or air-gapped — zero vendor lock-in, run any LLM. Start with a pilot, then scale with our engineers wiring it into your data and systems.
Self-serve prices in USD, billed monthly; change or cancel your plan anytime from Billing in the app. Enterprise is scoped with our team: a pilot from $15K, a one-time deployment, or full codebase ownership on a custom quote.
Agentic Ontology is ibl.ai's on-premise knowledge layer. It connects the databases and HTTP APIs an organization already runs, names the business terms and relationships inside them, and publishes the terms your people certify as MCP servers that any agent can call.
It is open source under the MIT license (github.com/iblai/ontology).
No. The ontology runs on a server inside your network and reads your systems in place. The ontology, the database passwords and the MCP servers stay on that server, and the console keeps no database of its own.
PostgreSQL, MySQL, Snowflake and ClickHouse are dissected into terms and served as tools. Any system with an HTTP API can be served as tools today, from an OpenAPI document or endpoints you name.
Trino and Databricks are mapped but not served; DuckDB, HeavyDB, Kyuubi, SQLite, SQL Server, Oracle and BigQuery are coming soon.
Not by default. SQL connections use a read-only login. With an HTTP API connection you can choose to allow writes: those endpoints go in a toolset of their own, which an agent reaches only when you grant it by name.
ibl.ai agents, attached in one dialog with a key of their own; Claude Desktop and Claude Code; Codex CLI; Cursor and Windsurf; your own code with the MCP SDK; and cURL. Each caller sees only the toolsets its grant reaches.
No. Connecting a system, the Map, certifying terms and the tools all work without one. An OpenAI API key, or any gateway that speaks OpenAI's API, turns on inferred joins and questions in plain words.
Ubuntu 22.04, 24.04 or 26.04 on x86-64, 4 GB of memory, 15 GB free and ports 80 and 443 open. The install is four blocks to paste, and the console is built on the server from the public source.
You do. The ontology is MIT-licensed and runs on your server; the ibl.ai platform it signs in with is priced on usage or a flat license, with no per-seat pricing. On ibl.ai you own all the code and the data.
Bring us a hard problem. Keep the code.
Start free on our cloud today, or take the whole codebase into your own infrastructure. Either way our engineers work alongside your team, and you own all the code and the data.
ibl.ai is family-owned and operated from New York, NY — a U.S.-headquartered, domestically-owned long-term partner, not a vendor that sells licenses and moves on. · SOC 2 Type II certified