Signpath for AI agents
SignPath is a code signing service that plugs into a build pipeline to automatically sign software artifacts. Development teams use it to keep releases authenticated and tamper-evident. 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 Signpath.
Check certificates before a release
List the certificates available to a project as a read-only check before a signing run.
Review a project's signing policy
Retrieve a signing policy's details so a release can be checked against it before approval.
Confirm service health before signing
Check the system health status to make sure signing is available before kicking off a build.
5 Signpath actions, graded by risk.
Every Signpath action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
5Look things up. Allowed by default.
- signpath.list_projectsList Projects
- signpath.get_health_checkGet Health Check
- signpath.list_certificatesList Certificates
- signpath.retrieve_system_infoRetrieve System Info
- signpath.retrieve_signing_policy_detailsRetrieve Signing Policy Details
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.
Signpath in three steps.
- 01Your users connect SignpathThey add their Signpath 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 Signpath through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('signpath', { 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 Signpath connects.
Users add their Signpath 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 Signpath 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 Signpath from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraphMore security and identity apps.
Signpath and Arc0, answered.
Can I use Signpath with Claude, ChatGPT or Cursor?
Yes. Connect Signpath 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 Signpath actions you allow.
How do users connect Signpath?
Users add their Signpath 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 Signpath actions can my agent take?
5 in total: 5 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Signpath?
Yes. Allow read actions and deny writes in the Signpath policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Signpath too?
Yes. The same Signpath connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Signpath into your agent.
Your users connect Signpath once, under your brand. Your agent gets 5 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan