Polar Signals for AI agents

Polar Signals is a continuous profiling platform that helps engineers diagnose performance regressions and find optimization opportunities. Engineering teams use it to investigate CPU and memory issues in production. 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.

DevOps and monitoringAPI keyMCP + RESTpolarsignals.com
AUDIT LOG · POLAR SIGNALSPOLICY: acme-support
09:41:07 · claude · u_8f2read
polar_signals.list_projects
List projects✓ allowed · 212ms
09:41:08 · claude · u_8f2read
polar_signals.query_profile_table
Query profile table✓ allowed · 164ms
EVERY POLAR SIGNALS CALL, ON THE RECORD
01 · USE CASES

What agents do in Polar Signals.

01

Query a profile flamegraph

Pull a flamegraph for a service to identify which functions are consuming the most CPU.

02

Check profile labels read-only

Look up available profile labels to narrow a query to a specific deployment or version.

03

List monitored projects

List projects read-only to confirm which services have continuous profiling enabled.

02 · ACTIONS

8 Polar Signals actions, graded by risk.

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

read

8

Look things up. Allowed by default.

  • polar_signals.list_projects
    List projects
  • polar_signals.query_profile_table
    Query profile table
  • polar_signals.query_profile_types
    Query profile types
  • polar_signals.query_profile_labels
    Query profile labels
  • polar_signals.query_profile_source
    Query profile source
  • polar_signals.query_profile_sandwich
    Query profile sandwich
  • polar_signals.query_profile_flamegraph
    Query profile flamegraph
  • polar_signals.query_profile_label_values
    Query profile label values

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

Polar Signals in three steps.

  1. 01Your users connect Polar SignalsThey add their Polar Signals 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 Polar Signals 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('polar_signals', {
  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 Polar Signals connects.

Users add their Polar Signals 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 Polar Signals 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 Polar Signals from any agent.

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

Polar Signals and Arc0, answered.

Q01

Can I use Polar Signals with Claude, ChatGPT or Cursor?

Yes. Connect Polar Signals 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 Polar Signals actions you allow.

Q02

How do users connect Polar Signals?

Users add their Polar Signals 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 Polar Signals actions can my agent take?

8 in total: 8 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 Polar Signals?

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

Q05

Can my own backend call Polar Signals too?

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

Get started

Plug Polar Signals into your agent.

Your users connect Polar Signals once, under your brand. Your agent gets 8 actions behind your policies, with every call on the record.

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