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.
What agents do in Polar Signals.
Query a profile flamegraph
Pull a flamegraph for a service to identify which functions are consuming the most CPU.
Check profile labels read-only
Look up available profile labels to narrow a query to a specific deployment or version.
List monitored projects
List projects read-only to confirm which services have continuous profiling enabled.
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
8Look things up. Allowed by default.
- polar_signals.list_projectsList projects
- polar_signals.query_profile_tableQuery profile table
- polar_signals.query_profile_typesQuery profile types
- polar_signals.query_profile_labelsQuery profile labels
- polar_signals.query_profile_sourceQuery profile source
- polar_signals.query_profile_sandwichQuery profile sandwich
- polar_signals.query_profile_flamegraphQuery profile flamegraph
- polar_signals.query_profile_label_valuesQuery profile label values
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Polar Signals in three steps.
- 01Your users connect Polar SignalsThey add their Polar Signals api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 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.
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
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
Use Polar Signals from any agent.
Polar Signals and Arc0, answered.
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.
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.
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.
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.
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.
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