MCP Server

The Strise MCP server exposes Strise's compliance intelligence to AI assistants that speak the Model Context Protocol. Connect Claude or any other MCP-aware client to your Strise tenant and run KYB/KYC, screening, monitoring, and review workflows directly from chat.

The server uses the same data, authorization, and audit trail as the Strise web app. Every tool call goes through your Strise team's permissions and is logged in Compliance Memory.

Server endpoint

Field	Value
Streamable HTTP URL	`https://mcp.strise.ai/mcp`
Discovery	`https://mcp.strise.ai/.well-known/oauth-protected-resource`
Tool reference (markdown)	`https://mcp.strise.ai/docs`
Health check	`https://mcp.strise.ai/healthz`

Authentication

The MCP server is an OAuth 2.0 resource server. Authorization is handled by Strise's identity provider, Auth0 — the same login as the Strise web app — which issues the access tokens and owns client registration, redirect URI validation and the consent screen. Clients find the authorization server through the protected-resource metadata above, or from the WWW-Authenticate header on any unauthenticated request to /mcp.

OAuth property	Value
Authorization server	`https://login.strise.ai/`
Resource identifier	`https://mcp.strise.ai/mcp`
Grant types	`authorization_code`, `refresh_token`
Token endpoint auth	`none` (public client with PKCE) or `private_key_jwt` (confidential)
Scopes	`openid`, `profile`, `email`

Clients identify themselves with a Client ID Metadata Document (CIMD) — a JSON document the client hosts, listing its redirect_uris and metadata, whose HTTPS URL is the client ID. No registration request is needed: the authorization server fetches the document and validates the redirect URI against it. Claude publishes its own document, so the Claude connector works without any setup on your side.

Users see a consent screen naming the client the first time they connect.

Each request to /mcp must include a verified Strise access token as Authorization: Bearer <token>. The user must belong to at least one Strise team. For team-scoped tools, pass teamId or configure X-Strise-Team: <teamId>. The server uses your only team when there is exactly one; if you belong to several teams, you must select one. Use list_my_teams to see your choices.

Setup

Claude (web and desktop)

Open the Claude connector directory.
Add the Strise connector.
Sign in with your Strise account when prompted.
The Strise tools become available in Claude.

Custom connector in Claude

In Claude's Settings > Connectors, add a custom connector with the URL https://mcp.strise.ai/mcp, then sign in with your Strise account. Organization settings may require an owner to enable it. Follow Claude's remote connector guide for the current setup steps.

Codex (CLI and app)

codex mcp add strise --url https://mcp.strise.ai/mcp
codex mcp login strise

The URL must be exactly https://mcp.strise.ai/mcp — path included, no trailing slash. Codex sends it as the RFC 8707 resource parameter and the authorization server resolves it to the token audience, so any other spelling fails the token request.

Codex picks CIMD automatically when it can. If login fails with a registration error, force it:

codex mcp login strise --oauth-client-registration cimd

Strise does not support Dynamic Client Registration, so a Codex build predating its CIMD support cannot complete the login. Upgrade Codex if --oauth-client-registration cimd is not a recognised flag.

Cursor / other MCP clients

Any client that supports remote MCP servers with OAuth can connect to https://mcp.strise.ai/mcp. Refer to your client's documentation for the exact configuration format. Choose a client with remote Streamable HTTP support; this service does not provide a local stdio entrypoint.

Capabilities

Tools are grouped by surface area. The full reference with parameters, return shapes, and per-tool example prompts lives at mcp.strise.ai/docs.

Category	What it covers
Search & lookup	Search companies, business persons, and private persons by name or registration number; lookup by national identifier
Entity details	Company, person, and private-person profiles — addresses, identifiers, citizenship, industry, corporate purpose
Risk & compliance	Calculated Risk score, sanctions screening, PEP screening, adverse media (AMS) events, review history
Company data	Financials, ownership, holdings, real estate, collateral, credit and CCJ reports, registers, documents, branches
Entity structure	Beneficial ownership (UBO) with configurable threshold, ownership charts, board roles, signatories, connected entities
Monitoring & alerts	List alerts, get alert change details, portfolio briefing, resolve alerts
Review management	Create company and private-person reviews with audit risk and review status
Adverse media	Disposition AMS events as confirmed true/false; create custom AMS events
Editing	Edit ownership and roles, manage custom registers, connect or disconnect custom entities, update entity status
Workflows	Order credit and CCJ reports; send customer-facing forms; log team activities

Example workflows

Compliance review of a Norwegian company

Look up the Norwegian company with org number 923609016. Give me the calculated risk score, beneficial owners at 25% threshold, and any sanctions or PEP hits.

The model calls lookup_company, get_entity_risk_summary, and get_entity_ownership, then synthesizes a written summary.

Sanctions and PEP screening of a person

Search for "Ivan Petrov" and check whether any match has sanctions or PEP flags.

The model calls search_entities (or search_private_persons), then get_entity_risk_summary for each promising match.

Portfolio alert triage

Show this week's high-severity monitoring alerts and explain what triggered each.

The model calls get_portfolio_briefing and then get_alert_changes for individual alerts to surface the underlying change.

Onboard and approve a customer

Approve company abc-123 as low risk with the comment "KYC verified" and set status to ACCOUNT.

The model calls get_entity_risk_summary to confirm the current risk level, create_company_review with reviewStatus: APPROVED, auditRisk: LOW, and update_entity_status to set the final status.

Add a private person to perpetual monitoring

Search for "Jane Doe" in Sweden, screen her, and add her to perpetual monitoring.

The model calls search_private_persons, get_entity_risk_summary, and add_private_person_to_monitoring.

Working with the MCP and Connect API together

Use MCP when an AI assistant should drive a workflow using your Strise account. Use the Strise Connect GraphQL API for a direct integration with its own API credentials. MCP uses the Internal API under your user permissions; Connect has a separate schema and authentication contract. Check each interface for the operations and fields your integration needs.

Limits and behaviour

Tool surface is curated. The available tools depend on your account and permissions. Some tools change team settings; inspect the tool description and requested changes before approving a call.
Destructive tools are marked. Tools that delete data (custom registers, custom entity connections, ownership/role resets, status removal, monitoring removal) are flagged as destructive: true in the tool reference. Models should require explicit confirmation before calling them.
Sessions are stateless across reconnects. Each initialize produces a new session ID. Tokens and team context are resolved per request.
Read-after-write consistency. Mutations write to Spanner and return the updated resource; subsequent reads observe the change immediately.

Support

API access and onboarding: tech@strise.ai
Customer support: support@strise.ai
Full GraphQL reference: graphql.strise.ai/connect/docs
Tool reference: mcp.strise.ai/docs

On this page