Conversion Tools for AI agents
Conversion Tools converts documents between formats like PDF, Word, Excel, and CSV, giving a workflow a way to change file types without manual exporting. 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.
What agents do in Conversion Tools.
Convert a file to a new format
Create a conversion task turning a Word document into plain text or PDF.
Check a conversion's status
Check a conversion task's current status before downloading its finished converted output file.
Download a converted file
Download the finished converted file once its conversion task has fully completed.
11 Conversion Tools actions, graded by risk.
Every Conversion Tools action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
8Look things up. Allowed by default.
- conversion_tools.get_configGet Conversion Config
- conversion_tools.list_tasksList Conversion Tasks
- conversion_tools.get_auth_infoGet Auth Info
- conversion_tools.get_file_infoGet File Info
- conversion_tools.get_task_statusGet Task Status
- conversion_tools.download_fileDownload Converted File
- conversion_tools.convert_word_to_textConvert Word to Text
- conversion_tools.convert_excel_to_htmlConvert Excel to HTML
write
3Create and change things. Allow, or ask the user first.
- conversion_tools.create_taskCreate Conversion Task
- conversion_tools.update_task_retentionUpdate Task Retention
- conversion_tools.upload_fileUpload File
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Conversion Tools in three steps.
- 01Your users connect Conversion ToolsThey add their Conversion Tools api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “create Conversion Task” can wait for the user to approve.
- 03Any agent can actYour agent calls Conversion Tools through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('conversion_tools', { read: 'allow', write: 'ask', // create_task destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Conversion Tools connects.
Users add their Conversion Tools 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 Conversion Tools 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
Use Conversion Tools from any agent.
Conversion Tools and Arc0, answered.
Can I use Conversion Tools with Claude, ChatGPT or Cursor?
Yes. Connect Conversion Tools 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 Conversion Tools actions you allow.
How do users connect Conversion Tools?
Users add their Conversion Tools 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.
Which Conversion Tools actions can my agent take?
11 in total: 8 read, 3 write and 0 destructive, such as “create Conversion Task”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Conversion Tools?
Yes. Allow read actions and deny writes in the Conversion Tools policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Conversion Tools too?
Yes. The same Conversion Tools connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Conversion Tools into your agent.
Your users connect Conversion Tools once, under your brand. Your agent gets 11 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan