← All integrations

Truvera MCP server

28 operations0 webhooks

Create DIDs, issue and revoke verifiable credentials, manage schemas and revocation registries, and verify credentials.

Try Truvera with your agent

Connect Truvera, then paste this into Claude, ChatGPT or Cursor. For ideas from other apps, see the use cases.

Using Corsair, show me what you can do in Truvera on my account, then run one read-only example and show me the result.

Runs once, when you ask

Truvera tools and triggers

Tools are what your agent can do in Truvera through Corsair's MCP server. Triggers are the Truvera events a routine can start from.

Credentials

  • DeleteDestructive

    Delete a credential metadata record; this does not revoke the credential

    credentials.delete

  • GetRead-only

    Read one credential metadata, and its contents when it was persisted

    credentials.get

  • IssueDestructive

    Issue and sign a verifiable credential, optionally distributing it to a holder, persisting it, or making it revocable

    credentials.issue

  • ListRead-only

    List the credential metadata on the account, with offset paging

    credentials.list

  • RevokeDestructive

    Revoke a credential, which makes every verification of it fail

    credentials.revoke

  • UnrevokeDestructive

    Unrevoke a credential, which restores it as valid

    credentials.unrevoke

Registries

  • CreateDestructive

    Create a revocation registry

    registries.create

  • DeleteDestructive

    Delete a revocation registry, which removes every credential status it held

    registries.delete

  • GetRead-only

    Read one revocation registry

    registries.get

  • ListRead-only

    List the revocation registries on the account

    registries.list

  • Revocation StatusRead-only

    Read whether one credential in a registry is revoked

    registries.revocationStatus

  • RevokeDestructive

    Revoke or unrevoke several credentials in one registry in one call

    registries.revoke

Connect Truvera to Claude, ChatGPT or Cursor

  1. 1

    Connect Truvera in Corsair

    Add your Truvera API key once in Corsair. Corsair stores the credential encrypted and makes the Truvera API calls for your agent, so it never goes into a prompt or a config file. Connect Truvera

    If your link lets the agent add apps, you can skip this: it gives you a sign-in link the first time it needs Truvera. On a ChatGPT personal plan, connect Truvera here first.

  2. 2

    Add Corsair's MCP server to your agent

    Every client uses the same address:

    https://mcp.corsair.dev/mcp
    Open Customize → Connectors → Add custom connector, paste the address, then select Connect.

    Codex, Gemini CLI, VS Code, Zed and other clients with OAuth sign-in work the same way. Clients without it, such as GitHub Copilot's coding agent, use a link's own address and an API key. Setup for every client

  3. 3

    Sign in and choose what needs your approval

    Your client opens Corsair to sign in. Pick a link: the apps your agent can use and a mode that decides what it may do without asking. In the default Cautious mode, Truvera's read and write operations run right away and its 12 destructive operations wait for your approval. Strict mode asks before every write and refuses destructive operations, and Read mode allows reads only.

FAQ

Install corsair and @corsair-dev/truvera, add the Truvera plugin, and connect with an API key. Then call methods like corsair.truvera.api.credentials.delete() from your app. Corsair keeps each tenant isolated.

Yes. Truvera requires an API key from your Truvera account or developer dashboard. Create credentials with access that matches what you automate, then paste them into Corsair or connect through managed auth in Hub.

Yes. One Corsair client can hit Truvera, GitHub, Notion, Stripe, and the rest. Trigger Truvera from a webhook, push updates to Slack, or chain actions across plugins. Same tenant context across integrations, plain TypeScript.

Teams use Corsair for create DIDs, issue and revoke verifiable credentials, manage schemas and revocation registries, and verify credentials. Common builds include sync jobs, admin tooling, and agents that call Truvera APIs from your backend.

The SDK is open source. Self-host and you pay Corsair nothing for the integration layer. Hub bills for hosted auth and execution, not per Truvera API call. Hub has a generous free tier. For hobby projects you can probably run the whole thing on free. Paid plans start to matter with more tenants or heavier traffic.

We maintain @corsair-dev/truvera in the open repo. When Truvera ships API changes, upgrade the package. Your call sites stay typed. You should not need to rewrite the integration layer each time.

No. Corsair does not read your Truvera data or hold individual access credentials. Credentials stay in your database. API calls run on your instance. We do not store Truvera data on your behalf.

Yes. Add https://mcp.corsair.dev/mcp as a custom connector or MCP server in Claude, ChatGPT, Cursor, VS Code, Claude Code, Codex or any client that supports remote MCP servers with OAuth sign-in, then sign in to Corsair. On ChatGPT personal plans, custom servers currently get read tools only.

Yes. Put Truvera on a link in Strict mode and every write waits for your approval, while destructive actions are refused. The default Cautious mode asks only before the 12 destructive Truvera operations. You can change a link's mode at hub.corsair.dev/me.