Connect one Proofable profile to any supported MCP client. Your agents can reuse current proofs, read their permissions, and use protected tools without carrying credentials in prompts.
Add the hosted endpoint to your MCP client and finish sign-in:
Then ask:
Show my Proofable profile and the proofs I can reuse.
Proofable returns Passed, Action needed, or Blocked. It reuses a current proof before starting another verification.
Connect your client
What agents can do
- Check whether you already hold the proof a task requires.
- Show the next verification step only when a current proof is missing.
- Load an agent’s current identity, permissions, skills, and selected context.
- Save credentials in encrypted Vault records without returning their values in chat.
- Read the same authorized profile and proofs across supported MCP clients.
Call proofable_context once after connecting. Use the MCP tool reference for exact inputs and result shapes.
Build with Proofable
Use the JavaScript SDK, HTTP API, or hosted verification to add Proofable to your product. Servers, CI, and headless agents use access keys against the same hosted MCP endpoint.
The Proofable SDK on GitHub includes the CLI and application examples.
Privacy
Proofable returns the result and its proof, not the private data used to complete the check. Proofs are private by default. Each connected client or runtime remains responsible for enforcing the returned result and permissions.
When authorized, agents can read:
- The signed-in profile and current agent permissions
- Approved tools, skills, and selected context
- Current proofs and verification status
- Vault record metadata without stored secret values
To load one registered agent into a project, see Connect agent context. Last modified on October 8, 2026
