# RelativityOne MCP Server & Agent Skill > Source: https://ibl.ai/developer/connectors/relativity Connector · E-discovery and legal review platform Last updated: October 20, 2026 **ibl.ai publishes a free RelativityOne agent skill: a SKILL.md that teaches an AI agent to read and write RelativityOne data and expose it as an MCP tool. Download it, connect your own RelativityOne credentials, and run the agent on ibl.ai Agentic OS, where you own all the code and the data.** Relativity is an e-discovery platform for litigation, investigations and review. Workspaces hold collected documents, coding fields, productions, users, groups and matters. RelativityOne has been renamed Relativity aiR. ## What is the RelativityOne API, and what can an agent read from it? JSON REST services per business domain. Object Manager reads, queries, creates, updates and deletes any object (including documents and fields) in a workspace; other services cover workspaces, usage and OAuth2 clients. - API: Relativity REST APIs (Object Manager and other Kepler services) (REST) - Access: Issued by your administrator - Base URL: https://{host}/Relativity.REST/api/{business-domain}/v{n}/ e.g. /Relativity.Rest/api/Relativity.ObjectManager/v1/workspace/{workspaceID}/object/query - Authentication: OAuth 2.0 client credentials; Basic authentication A Relativity administrator creates an OAuth2 client under Home > Authentication > OAuth2 Client Manager to issue a client ID and secret. Developer documentation is public at platform.relativity.com. POST grant_type=client_credentials, scope=SystemUserInfo, client_id and client_secret to {host}/Relativity/Identity/connect/token; send Authorization: Bearer {token}. Every request also needs the X-CSRF-Header header. ### What can an agent read from RelativityOne? - **Documents and objects** — Object Manager /object/query, /queryslim and /read on any object type in a workspace, including Document. - **Fields and coding** — Field values returned by Object Manager queries, such as responsiveness or privilege coding. - **Workspaces** — Workspace Service API for workspace details; admin-level Object Manager calls use workspace ID -1. - **Usage reports** — Usage Report REST API for system consumption. ### What can an agent write to RelativityOne? - **Objects (create and update)** — Object Manager /create and /update, including mass operations on one object type. - **Long text fields** — /updatelongtextfromstream for values over the inline size limit. - **Objects (delete)** — Object Manager /delete, single or mass. Confirm with the user first. Limits: Object Manager uses a dynamic, global rate limit shared by all consumers. On HTTP 429, wait for the seconds in the RateLimit-Reset header and retry. Send X-Kepler-Referrer with your application GUID. Review sets contain client documents, privilege calls and attorney work product; privilege coding and productions must be protected from waiver. ## How do I connect RelativityOne to an AI agent over MCP? Relativity publishes an official MCP server: [Relativity MCP](https://help.relativity.com/RelativityOne/Content/Relativity/MCP/Relativity_MCP.htm). Relativity-hosted, OAuth 2.0, System Administrators only; client ID from Relativity support. Admin tools for matters, workspaces, permissions, groups and usage; not document review. You can register that server on ibl.ai as it is, or use the SKILL.md below when you want the agent to call the Relativity REST APIs (Object Manager and other Kepler services) directly. On ibl.ai an MCP connection is three records, and a working integration always needs all three: 1. **Register the server** — `POST …/mcp-servers/` with its URL, a transport (`sse`, `websocket` or `streamable_http`) and an `auth_type` of `none`, `token` or `oauth2`. 2. **Create a connection** that holds the credential, scoped to the whole organization (`platform`), to a single agent, or to each user (`user`). 3. **Enable it on the agent** — `mcp-tool` in `tool_slugs` and the server id in `mcp_servers`. Both lists are replaced, not merged, so read the settings first. For an API key or a service credential, one `token` connection at `platform` scope serves the whole organization; scope a connection to a single agent when that agent needs narrower access than the rest. The field reference is in [MCP server connections](https://ibl.ai/developer/platform/mcp/mcp-connections), and the [/iblai-api-agent-mcp](https://ibl.ai/developer/skills/iblai-api-agent-mcp) skill runs all three steps from a coding agent. ## What does the RelativityOne agent skill do? The RelativityOne skill is one SKILL.md file named `iblai-connect-relativity`. It gives an agent the auth conventions, what to read, which writes need a person's confirmation, the ibl.ai MCP wiring, example prompts and guardrails. [Download the RelativityOne SKILL.md](https://ibl.ai/developer/connectors/relativity/SKILL.md) Save it as `.claude/skills/iblai-connect-relativity/SKILL.md`, or in your agent's skills folder. The ibl.ai platform skills it calls come from one install: ``` npx skills add iblai/vibe --all ``` This connector skill is a starting point maintained on ibl.ai, not part of the iblai/vibe repository. It was checked against Relativity's documentation on October 20, 2026. Test it against your own RelativityOne setup before you rely on it. ### What can I ask a RelativityOne agent to do? - “How many documents in workspace 1017456 are coded Responsive but not yet reviewed for privilege?” - “List all workspaces created for client Acme this quarter” - “Add reviewer jdoe to the Second Level Review group in the Smith matter” - “Show last month's usage report for our instance” ## How do I run a RelativityOne agent on ibl.ai? [Agentic OS](https://ibl.ai/product/agentic-os) is where the agent runs on ibl.ai: it holds the RelativityOne MCP connection, the model the agent uses, its instructions and its conversation history. 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. - [AI agents for Legal](https://ibl.ai/solutions/legal) — what ibl.ai deploys in this sector ### Which ibl.ai agents work with RelativityOne data? - [Discovery](https://ibl.ai/solutions/legal/agent/discovery-agent) — Legal ### Which ibl.ai platform skills does a RelativityOne agent use? - [/iblai-api-agent-mcp](https://ibl.ai/developer/skills/iblai-api-agent-mcp) — MCP connectors for ibl.ai agents, end to end - [/iblai-vibe-agent-mcp](https://ibl.ai/developer/skills/iblai-vibe-agent-mcp) — Add the agent MCP tab (Model Context Protocol connector management with featured connectors, custom connectors, OAuth,… - [/iblai-api-agent-tool](https://ibl.ai/developer/skills/iblai-api-agent-tool) — Enable or disable an ibl.ai agent's tools via the platform API ## What else should I know before connecting RelativityOne to an AI agent? ### Is there an official RelativityOne MCP server? Yes. Relativity publishes [Relativity MCP](https://help.relativity.com/RelativityOne/Content/Relativity/MCP/Relativity_MCP.htm). You can register it on ibl.ai as an MCP server, or use the SKILL.md when you want the agent to call the Relativity REST APIs (Object Manager and other Kepler services) directly. ### Who can get RelativityOne API credentials? A Relativity administrator creates an OAuth2 client under Home > Authentication > OAuth2 Client Manager to issue a client ID and secret. Developer documentation is public at platform.relativity.com. ### Does RelativityOne data leave my infrastructure when an ibl.ai agent uses it? On ibl.ai, you own all the code and the data. Self-hosted in your cloud or data center, the agent, its MCP connections and its conversation logs stay inside your perimeter. Because the platform is model-agnostic, you can point the agent at a model you host, so RelativityOne records need not reach a third-party model provider. ### Is the RelativityOne agent skill free to use? Yes. The SKILL.md is a free download with no sign-up. It assumes you already have RelativityOne credentials, and your agreement with Relativity still governs how you use its API. ## Which other data sources can an AI agent connect to alongside RelativityOne? ### Which other Legal systems have a connector? - [Clio Manage](https://ibl.ai/developer/connectors/clio) — Legal practice management system - [Docusign eSignature](https://ibl.ai/developer/connectors/docusign) — Electronic signature platform - [iManage Work](https://ibl.ai/developer/connectors/imanage) — Legal document and email management system - [Ironclad](https://ibl.ai/developer/connectors/ironclad) — Contract lifecycle management system - [LexisNexis](https://ibl.ai/developer/connectors/lexisnexis) — Legal research content and AI API - [NetDocuments](https://ibl.ai/developer/connectors/netdocuments) — Cloud legal document management system - [PACER](https://ibl.ai/developer/connectors/pacer) — U.S. federal court records system - [Westlaw](https://ibl.ai/developer/connectors/westlaw) — Legal research platform Every connector, grouped by sector, is on the [connectors hub](https://ibl.ai/developer/connectors).