---
name: iblai-connect-imanage
description: "Read and write iManage Work data through the iManage Work API (REST, OAuth 2.0) and expose it to an ibl.ai agent as an MCP tool. Use when the user asks an agent to work with iManage Work data, or to set up an iManage Work MCP connection on ibl.ai."
metadata:
  kind: guide
---

# iManage Work connector for AI agents

> A starting point maintained on ibl.ai at https://ibl.ai/developer/connectors/imanage — not part of the iblai/vibe repository. Checked against iManage's documentation on October 20, 2026; test it against your own iManage Work setup before you rely on it.

iManage Work is a document and email management system used by law firms and legal departments. It stores documents, versions and filed email in libraries organized into matter workspaces and folders, with security and ethical walls.

## Auth & conventions

- **API:** iManage Work API (REST, OAuth 2.0) (REST). REST access to documents (profiles, versions, download, upload), workspaces, folders, search, permissions, users and groups. iManage publishes its own connectors that wrap these operations.
- **Access:** Issued by your administrator. Any custom application must be registered by an iManage Work administrator in Control Center (Applications), which issues the client ID and secret. The full API reference sits on iManage's login-gated support portal.
- **Auth:** OAuth 2.0. Applications are registered in iManage Control Center as Web or Native client applications and obtain OAuth 2.0 access tokens over HTTPS instead of using user credentials. Calls run with the user's iManage permissions.
- Keep iManage Work credentials in environment variables or the ibl.ai credential store. Never print a token in chat and never commit one to a file.
- Destructive or outward-facing calls are marked **Confirm with the user first** — do.

## Reads

- **Documents** — Document profiles, version history and file download.
- **Workspaces** — Matter workspaces, workspace profiles and workspace templates.
- **Folders** — Folder search and the contents of a container.
- **Search** — Search for documents, workspaces and folders the user is allowed to see.

## Writes

- **Documents** — Upload a new document to a folder, create a new version, update the profile.
- **Workspaces** — Create a workspace from a template.
- **Document moves and copies** — Copy or move a document to another folder or library.
- **Document delete** — Delete a specified document. **Confirm with the user first.**

## Expose it to an ibl.ai agent (MCP)

iManage publishes an official MCP server, iManage MCP Server (https://docs.imanage.com/ai/mcpserver-user-help/en-US/Introduction_to_iManage_MCP_Server.html). Register it below as-is, or host your own server that wraps the calls in this skill.

First install the ibl.ai platform skills and connect your organization (writes `IBLAI_ORG`, `IBLAI_USERNAME` and `IBLAI_API_KEY` to `.env`):

```bash
npx skills add iblai/vibe --all
# then, in your coding agent:
/iblai-api-login
```

Every call below sends `Authorization: Api-Token $IBLAI_API_KEY`.

1. **Register the server** — `POST https://api.iblai.app/dm/api/ai-mentor/orgs/$IBLAI_ORG/users/$IBLAI_USERNAME/mcp-servers/` with `name`, `url`, `transport` (`sse` | `websocket` | `streamable_http`) and `auth_type` (`none` | `token` | `oauth2`). Capture the returned `id`.
   - For an API key or service credential use `auth_type=token` with `auth_scope=platform` for one key across the organization, or scope it to a single agent for one key per agent.
2. **Create the connection** — `POST https://api.iblai.app/dm/api/ai-mentor/orgs/$IBLAI_ORG/users/$IBLAI_USERNAME/mcp-server-connections/` with `server`, `scope` (`platform` | `mentor` | `user`), `auth_type`, and either `credentials` + `authorization_scheme` or a `connected_service` id for OAuth. Credentials are masked on read; never send a masked value back.
3. **Enable it on the agent** — `GET https://api.iblai.app/dm/api/ai-mentor/orgs/$IBLAI_ORG/users/$IBLAI_USERNAME/mentors/{agent_id}/settings/`, add `mcp-tool` to `tool_slugs` and the server id to `mcp_servers`, then `PATCH` the full lists back. They are replaced, not merged.

Full reference: https://ibl.ai/developer/platform/mcp/mcp-connections and the `/iblai-api-agent-mcp` skill.

## Example prompts

- "Find the latest version of the share purchase agreement in the Acme acquisition workspace"
- "List documents added to matter 1234-0001 this week"
- "Save this redline as a new version of document 456789"
- "Create a new matter workspace for Beta Corp from the litigation template"

## Guardrails

- Firm documents and filed email are client confidential and frequently privileged or work product; matter-level security and ethical walls must be honored.
- Request the narrowest iManage Work scopes or role the task needs, and prefer a read-only credential for agents that only answer questions.
- Return the fields the user asked for, not whole records; do not paste personal data into chat that the user did not request.
- Before any write, show the user exactly what will change and wait for a yes.
- Page through large result sets and back off on rate-limit responses instead of retrying in a loop.

## References

- Introduction to iManage MCP Server: https://docs.imanage.com/ai/mcpserver-user-help/en-US/Introduction_to_iManage_MCP_Server.html
- Control Center: registering applications: https://docs.imanage.com/cc-help/10.5.0/en-US/Applications.html
- iManage MCP Server administration: https://docs.imanage.com/ai/mcpserver-admin-help/en-US/iManage_MCP_Server_Administration_Help.html
- iManage MCP Server: https://docs.imanage.com/ai/mcpserver-user-help/en-US/Introduction_to_iManage_MCP_Server.html
- This connector on ibl.ai: https://ibl.ai/developer/connectors/imanage
- ibl.ai MCP server connections: https://ibl.ai/developer/platform/mcp/mcp-connections