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

# NetDocuments connector for AI agents

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

NetDocuments is a cloud document and email management service for law firms and legal departments. Repositories hold cabinets, workspaces, folders and documents with versions, profiles (metadata), access rights and audit history.

## Auth & conventions

- **API:** NetDocuments REST API (REST). REST calls with GET, PUT, POST and DELETE for documents (content, profile, versions, check-in/out), folders, workspaces, cabinets, search, users, groups, lookup tables and repository logs.
- **Access:** Issued by your administrator. API documentation, OAuth guides and sample code sit on the NetDocuments support site and developer portal, which require registration. Integrations run as a customer's users or a registered client; ISVs join the partner program.
- **Auth:** OAuth 2.0. REST apps authenticate with OAuth 2.0 bearer access tokens. Each NetDocuments region (for example US, EU, Canada, Australia) is a separate service, so the client must call the region where the repository lives.
- **Limits:** Search returns up to 500 results per page (default 50) with skiptoken paging. NetDocuments' own Power Platform connector is throttled at 100 calls per connection per 60 seconds; a general REST API limit was not found.
- Keep NetDocuments 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 content, profile (metadata), version list and action history.
- **Search** — Search one or more cabinets with the NetDocuments query syntax; up to 500 results per page with skiptoken paging.
- **Folders and containers** — Folder items and container contents, including subfolders.
- **Workspaces and cabinets** — Workspace information, user cabinets, cabinet settings and custom attributes.
- **Users and groups** — Repository users, groups, group membership and repository logs.

## Writes

- **Documents** — Create a document, add a new version, update content, rename, check in or out.
- **Folders and workspaces** — Create or rename folders, file or unfile documents, get or create workspaces.
- **Secured links** — Generate a link to a document that anyone with the link can open. **Confirm with the user first.**
- **Document and folder delete** — Delete to Deleted Items or permanently. **Confirm with the user first.**
- **Access rights** — Search a cabinet and modify ACLs on matching documents. **Confirm with the user first.**

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

NetDocuments Software, Inc. publishes an official MCP server, NetDocuments MCP (https://www.netdocuments.com/blog/netdocuments-collaborates-with-anthropic-on-legal-industry-mcp/). 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

- "Search the Litigation cabinet for the final settlement agreement with Acme"
- "Pull the last three versions of document 4821-7735-1234 and list the changes"
- "File this memo into the Smith matter workspace under Correspondence"
- "List everything added to the Jones workspace in the past week"

## Guardrails

- Documents and email are client confidential and often privileged or work product; matter-level restrictions, ethical walls and retention policies must be respected.
- Request the narrowest NetDocuments 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.
- Respect the documented limits above: page through results and back off on rate-limit responses instead of retrying in a loop.

## References

- NetDocuments connector reference (Microsoft Learn): https://learn.microsoft.com/en-us/connectors/netdocuments/
- NetDocuments and Anthropic: legal MCP: https://www.netdocuments.com/blog/netdocuments-collaborates-with-anthropic-on-legal-industry-mcp/
- NetDocuments MCP ecosystem expansion: https://www.netdocuments.com/blog/netdocuments-expands-mcp-ecosystem-legal-ai-context/
- NetDocuments MCP: https://www.netdocuments.com/blog/netdocuments-collaborates-with-anthropic-on-legal-industry-mcp/
- This connector on ibl.ai: https://ibl.ai/developer/connectors/netdocuments
- ibl.ai MCP server connections: https://ibl.ai/developer/platform/mcp/mcp-connections