Get started

Lucid for AI agents

Lucid is a visual collaboration suite for building diagrams, flowcharts, org charts, and mind maps that teams share and edit together. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Connect LucidSee the 35 actions ↓
ProductivityOAuth 2.0 (MCP)MCP + RESTlucid.co
AUDIT LOG · LUCIDPOLICY: acme-support
09:41:07 · claude · u_8f2read
lucid.list_document_threads
List document threads✓ allowed · 212ms
09:41:08 · claude · u_8f2read
lucid.fetch
Fetch✓ allowed · 164ms
09:41:09 · claude · u_8f2write
lucid.post_document_thread_comment
Post document thread comment✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
lucid.lucid_add_block
Lucid add block✕ blocked · policy: deny
EVERY LUCID CALL, ON THE RECORD
01 · USE CASES

What agents do in Lucid.

01

Generate a diagram from a spec

Create a flowchart or sequence diagram from a written description for a design review.

02

Search for an existing document

Search a workspace's documents to find a diagram relevant to a question, read-only.

03

Approve before deleting items

Require approval before deleting shapes or items from a shared document that others rely on.

02 · ACTIONS

35 Lucid actions, graded by risk.

Every Lucid action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

5

Look things up. Allowed by default.

  • lucid.get_mcp_resource
    Get mcp resource
  • lucid.list_document_threads
    List document threads
  • lucid.list_document_thread_comments
    List document thread comments
  • lucid.fetch
    Fetch
  • lucid.search
    Search

write

28

Create and change things. Allow, or ask the user first.

  • lucid.post_document_thread_comment
    Post document thread comment
  • lucid.lucid_add_line
    Lucid add line
  • lucid.lucid_edit_item
    Lucid edit item
  • lucid.lucid_create_erd
    Lucid create erd
  • lucid._lucid_create_embed
    lucid create embed
  • lucid.lucid_create_folder
    Lucid create folder
  • lucid.lucid_shape_details
    Lucid shape details
  • lucid.lucid_shape_library
    Lucid shape library
  • lucid.lucid_update_folder
    Lucid update folder
  • lucid.lucid_create_mind_map
    Lucid create mind map
  • lucid.lucid_search_document
    Lucid search document
  • lucid.lucid_submit_feedback
    Lucid submit feedback
  • lucid.lucid_update_document
    Lucid update document
  • lucid.lucid_create_org_chart
    Lucid create org chart
  • lucid.lucid_fetch_item_image
    Lucid fetch item image
  • lucid.lucid_add_dynamic_table
    Lucid add dynamic table
+ 12 MORE

destructive

2

Delete, cancel or archive. Ask first, or deny outright.

  • lucid.lucid_add_block
    Lucid add block
  • lucid.lucid_delete_items
    Lucid delete items
03 · HOW IT WORKS

Lucid in three steps.

  1. 01Your users connect LucidThey sign in to Lucid on Arc0 Connect, under your brand, and approve the access you ask for.
  2. 02You set the rulesReads run, writes like “post document thread comment” can wait for the user, and “lucid add block” can be denied outright.
  3. 03Any agent can actYour agent calls Lucid through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('lucid', {
  read: 'allow',
  write: 'ask',        // post_document_thread_comment
  destructive: 'deny',  // lucid_add_block
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Lucid connects.

Lucid runs its own MCP server behind OAuth. Arc0 registers the client, users approve access on Arc0 Connect, and your agent reaches Lucid through the same endpoint, policies and audit log as every other app.

The same Lucid connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
OAuth 2.0 (MCP)
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Lucid from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More productivity apps.

Notion57 actionsAirtable27 actionsConfluence70 actionsClickUp164 actionsAmazing Marvin10 actionsRentman130 actionsHub Planner122 actionsCoda110 actions
ALL PRODUCTIVITY APPS →
07 · FAQ

Lucid and Arc0, answered.

Q01

Can I use Lucid with Claude, ChatGPT or Cursor?

Yes. Connect Lucid to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Lucid actions you allow.

Q02

How do users connect Lucid?

Lucid runs its own MCP server behind OAuth. Arc0 registers the client, users approve access on Arc0 Connect, and your agent reaches Lucid through the same endpoint, policies and audit log as every other app.

Q03

Which Lucid actions can my agent take?

35 in total: 5 read, 28 write and 2 destructive, such as “post document thread comment”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Lucid?

Yes. Actions like “lucid add block” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Lucid too?

Yes. The same Lucid connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Lucid into your agent.

Your users connect Lucid once, under your brand. Your agent gets 35 actions behind your policies, with every call on the record.

Connect LucidBrowse all apps →

Free to build · MCP + REST · Audit log on every plan