Get started

PromptLayer for AI agents

PromptLayer is a prompt management and observability platform for versioning, evaluating, and analyzing LLM applications. AI teams use it to track how prompts change and perform over time. 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 PromptLayerSee the 16 actions ↓
AI and modelsAPI keyMCP + RESTpromptlayer.com
AUDIT LOG · PROMPTLAYERPOLICY: acme-support
09:41:07 · claude · u_8f2read
promptlayer.list_tables
List Tables✓ allowed · 212ms
09:41:08 · claude · u_8f2read
promptlayer.get_table
Get Table✓ allowed · 164ms
EVERY PROMPTLAYER CALL, ON THE RECORD
01 · USE CASES

What agents do in PromptLayer.

01

Check a prompt template read-only

Look up a prompt template's current version before using it in a workflow.

02

Search request logs

Search past LLM request logs to debug an unexpected model response.

03

Check a workflow's configuration read-only

Look up a workflow's setup before triggering it or handing it off for review.

02 · ACTIONS

16 PromptLayer actions, graded by risk.

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

read

16

Look things up. Allowed by default.

  • promptlayer.get_table
    Get Table
  • promptlayer.list_tables
    List Tables
  • promptlayer.get_workflow
    Get Workflow
  • promptlayer.list_workflows
    List Workflows
  • promptlayer.get_request_log
    Get Request Log
  • promptlayer.list_table_rows
    List Table Rows
  • promptlayer.list_table_sheets
    List Table Sheets
  • promptlayer.list_table_columns
    List Table Columns
  • promptlayer.get_prompt_template
    Get Prompt Template
  • promptlayer.get_registered_tool
    Get Registered Tool
  • promptlayer.search_request_logs
    Search Request Logs
  • promptlayer.get_skill_collection
    Get Skill Collection
  • promptlayer.list_folder_entities
    List Folder Entities
  • promptlayer.list_prompt_templates
    List Prompt Templates
  • promptlayer.list_registered_tools
    List Registered Tools
  • promptlayer.list_skill_collections
    List Skill Collections

write

0

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

  • No write actions.

destructive

0

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

  • No destructive actions.
03 · HOW IT WORKS

PromptLayer in three steps.

  1. 01Your users connect PromptLayerThey add their PromptLayer api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
  3. 03Any agent can actYour agent calls PromptLayer 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('promptlayer', {
  read: 'allow',
  write: 'ask',        
  destructive: 'deny',  
})

# 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 PromptLayer connects.

Users add their PromptLayer 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 PromptLayer 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 PromptLayer from any agent.

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

More ai and models apps.

Perplexity AI9 actionsAffinda119 actionsAgent Mail5 actionsAI/ML API30 actionsAivoov1 actionsAll Images AI7 actionsAltText.ai10 actionsAltTextLab2 actions
ALL AI AND MODELS APPS →
07 · FAQ

PromptLayer and Arc0, answered.

Q01

Can I use PromptLayer with Claude, ChatGPT or Cursor?

Yes. Connect PromptLayer 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 PromptLayer actions you allow.

Q02

How do users connect PromptLayer?

Users add their PromptLayer 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 PromptLayer actions can my agent take?

16 in total: 16 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in PromptLayer?

Yes. Allow read actions and deny writes in the PromptLayer policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call PromptLayer too?

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

Get started

Plug PromptLayer into your agent.

Your users connect PromptLayer once, under your brand. Your agent gets 16 actions behind your policies, with every call on the record.

Connect PromptLayerBrowse all apps →

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