Writer for AI agents

Writer is an enterprise generative AI platform with knowledge graphs and guardrails, used by companies building AI writing and research tools on their own content. 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.

AI and modelsAPI keyMCP + RESTwriter.com
AUDIT LOG · WRITERPOLICY: acme-support
09:41:07 · claude · u_8f2read
writer.list_files
List Files✓ allowed · 212ms
09:41:08 · claude · u_8f2read
writer.get_file
Get File✓ allowed · 164ms
09:41:09 · claude · u_8f2write
writer.create_knowledge_graph
Create Knowledge Graph✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
writer.delete_file
Delete File✕ blocked · policy: deny
EVERY WRITER CALL, ON THE RECORD
01 · USE CASES

What agents do in Writer.

01

Ask a question of a knowledge graph

Get an answer generated from a company's own documents in a knowledge graph.

02

Generate or rewrite text

Draft or revise a piece of content based on a prompt.

03

Confirm before deleting a knowledge graph

Check with the user before deleting a graph, since all its indexed files go with it.

02 · ACTIONS

23 Writer actions, graded by risk.

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

read

11

Look things up. Allowed by default.

  • writer.get_file
    Get File
  • writer.list_files
    List Files
  • writer.list_graphs
    List Knowledge Graphs
  • writer.list_models
    List Models
  • writer.list_applications
    List Applications
  • writer.parse_pdf
    Parse PDF
  • writer.download_file
    Download File
  • writer.analyze_images
    Analyze Images
  • writer.retrieve_graph
    Retrieve Knowledge Graph
  • writer.translate_text
    Translate Text
  • writer.detect_ai_content
    Detect AI Content

write

9

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

  • writer.update_graph
    Update Knowledge Graph
  • writer.add_file_to_graph
    Add File to Knowledge Graph
  • writer.create_knowledge_graph
    Create Knowledge Graph
  • writer.web_search
    Web Search
  • writer.upload_file
    Upload File
  • writer.chat_completion
    Chat Completion
  • writer.text_generation
    Text Generation
  • writer.medical_comprehend
    Medical Text Comprehension
  • writer.ask_question_to_knowledge_graph
    Ask Question to Knowledge Graph

destructive

3

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

  • writer.delete_file
    Delete File
  • writer.delete_graph
    Delete Graph
  • writer.remove_file_from_graph
    Remove File From Graph
03 · HOW IT WORKS

Writer in three steps.

  1. 01Your users connect WriterThey add their Writer api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Knowledge Graph” can wait for the user, and “delete File” can be denied outright.
  3. 03Any agent can actYour agent calls Writer 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('writer', {
  read: 'allow',
  write: 'ask',        // create_knowledge_graph
  destructive: 'deny',  // delete_file
})

# 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 Writer connects.

Users add their Writer api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Writer 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
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Writer from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Writer and Arc0, answered.

Q01

Can I use Writer with Claude, ChatGPT or Cursor?

Yes. Connect Writer 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 Writer actions you allow.

Q02

How do users connect Writer?

Users add their Writer api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Writer actions can my agent take?

23 in total: 11 read, 9 write and 3 destructive, such as “create Knowledge Graph”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Writer?

Yes. Actions like “delete File” 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 Writer too?

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

Get started

Plug Writer into your agent.

Your users connect Writer once, under your brand. Your agent gets 23 actions behind your policies, with every call on the record.

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