What can AI agents do with Socure RiskOS through Ferentin?

Through Ferentin, agents can use Socure RiskOS for documentation qa, webhook management, webhook event discovery, workflow listing, usecase listing, integration checklist and test case lookup. Every call is checked against your Ferentin policies first.

How is Socure RiskOS access secured?

Requests through the Socure RiskOS integration are covered by API key authentication, tenant encrypted credentials, tool level policy recommended and audit logging. These controls are applied by Ferentin, not by Socure RiskOS, so they hold across every connected agent.

How do I connect Socure RiskOS to Ferentin?

Open the Ferentin admin console, add Socure RiskOS as a new connection and authenticate with API key. You then choose which permissions and which tools your agents may use, and the connection goes live for everyone covered by your policies.

Is the Socure RiskOS integration generally available?

Yes. The Socure RiskOS integration is generally available on Ferentin, including the free tier.

Socure RiskOS

Generally Available

With a tenant-bound RiskOS MCP Server Key, an agent can answer RiskOS API questions, inspect configured workflows, use cases and webhook events, walk the integration checklist, and register or update webhook endpoints — shortening a RiskOS integration without handling any end-user identity data.

Socure
Identity Verification
Fraud Prevention

Configure Socure RiskOS

Authentication: API key
Hosting: Vendor-hosted endpoint

How it works

Every agent request passes through Ferentin policy before it reaches Socure RiskOS.

AI agentAsks for something
Ferentin policies
- API key authentication
- Tenant encrypted credentials
- Tool level policy recommended
- Audit logging
Socure RiskOS MCP serverAuthorized connection
Governed resultMasked, logged, returned

What you can do with Socure RiskOS

Documentation qa
Webhook management
Webhook event discovery
Workflow listing
Usecase listing
Integration checklist
Test case lookup

Before you connect

This is a RiskOS INTEGRATION-ASSISTANT server, not the identity-verification API. It does not run KYC, document verification, or fraud scoring — those remain REST calls to RiskOS (see https://help.socure.com/riskos/reference/postevaluation). What it does is answer documentation questions and read/edit your RiskOS integration configuration.
Two environments, two endpoints, two keys: https://mcp.riskos.socure.com/prod (Ferentin's default) and https://mcp.riskos.socure.com/sandbox. list_testcases and integration_checklist are documented as SANDBOX-ONLY, so an instance pointed at prod will not expose them.
SECURITY — add_webhook and update_webhook are configuration-mutating tools that register a destination URL for RiskOS event delivery. A prompt-injected agent could point production identity-decision webhooks at an attacker-controlled endpoint, or silently redirect existing ones. Grant them deliberately.
RECOMMENDED POLICY — for read-only use, grant an ALLOW policy listing deny_toolsets: ["add_webhook", "update_webhook"], which keeps ask_docs and the list_* tools. Do NOT use a deny-effect policy for this: instance-level deny precedence removes the whole server, not just the named tools.

3 more technical notes

Authentication is a static Bearer key, not OAuth — the server publishes no .well-known OAuth metadata (every path on the host returns 403 without an Authorization header), so there is no user-mode consent flow. The key is org-scoped, so all Ferentin users of this instance act as the same RiskOS principal; user attribution comes from Ferentin's audit log, not from Socure.
MCP Server Keys work for SSO-based organizations. Socure deprecated username/password authentication for this server on 2026-07-21 — a card or client still configured that way will fail.
Tool catalog is from Socure's published documentation, not a live connection (the endpoint rejects unauthenticated discovery). It populates for real on first authenticated connection.

About Socure RiskOS

Socure is an identity-verification and fraud-prevention platform. RiskOS is its orchestration layer for identity workflows, and its MCP server exposes RiskOS documentation and integration configuration to agents.

Website Developer docs

Frequently asked about Socure RiskOS

What can AI agents do with Socure RiskOS through Ferentin?: Through Ferentin, agents can use Socure RiskOS for documentation qa, webhook management, webhook event discovery, workflow listing, usecase listing, integration checklist and test case lookup. Every call is checked against your Ferentin policies first.
How is Socure RiskOS access secured?: Requests through the Socure RiskOS integration are covered by API key authentication, tenant encrypted credentials, tool level policy recommended and audit logging. These controls are applied by Ferentin, not by Socure RiskOS, so they hold across every connected agent.
How do I connect Socure RiskOS to Ferentin?: Open the Ferentin admin console, add Socure RiskOS as a new connection and authenticate with API key. You then choose which permissions and which tools your agents may use, and the connection goes live for everyone covered by your policies.
Is the Socure RiskOS integration generally available?: Yes. The Socure RiskOS integration is generally available on Ferentin, including the free tier.

Related integrations

Jamf Developer Portal

Navigate Jamf's OpenAPI specs to find the right endpoint and generate integration code.

MCP Servers

View

Context7

Pull current, version-accurate library and framework documentation into an agent's context for reliable AI-assisted coding.

MCP Servers

View

Microsoft Learn

Semantic search over official Microsoft/Azure docs and code samples — public and read-only.

MCP Servers

View