AI and MCP integration

Connect Entity Intelligence to AI agents through its secured MCP server.

6 minDocs version 2.7

In this guide

1Connect the MCP server
2Grant least-privilege scopes
3Approve write operations

In this guide

1Connect the MCP server
2Grant least-privilege scopes
3Approve write operations

Connect the MCP server

The server is available at https://enrich.nordicdevhouse.com/api/mcp. Remote clients discover OAuth automatically and request only the scopes required by the selected tools.

JSON

{
  "type": "mcp",
  "server_label": "data-enrichment-mcp",
  "server_url": "https://enrich.nordicdevhouse.com/api/mcp",
  "require_approval": {
    "always": {
      "read_only": false
    },
    "never": {
      "read_only": true
    }
  }
}

Client-specific setup

ChatGPT: In ChatGPT developer mode, create a custom MCP connection and paste the endpoint below. OAuth starts automatically.

URL

https://enrich.nordicdevhouse.com/api/mcp

Claude / Claude Code: Add the remote HTTP server in Claude or Claude Code, then complete OAuth with /mcp.

Shell

claude mcp add --transport http data-enrichment-mcp https://enrich.nordicdevhouse.com/api/mcp

Cursor: Add this server to your project or user MCP configuration.

JSON

{
  "mcpServers": {
    "data-enrichment-mcp": {
      "url": "https://enrich.nordicdevhouse.com/api/mcp"
    }
  }
}

VS Code: Add this server to .vscode/mcp.json or your user MCP configuration.

JSON

{
  "servers": {
    "data-enrichment-mcp": {
      "type": "http",
      "url": "https://enrich.nordicdevhouse.com/api/mcp"
    }
  }
}

Codex: Add the remote Streamable HTTP server with the Codex CLI. Codex stores the connection in your MCP configuration.

Shell

codex mcp add data-enrichment-mcp --url https://enrich.nordicdevhouse.com/api/mcp

OpenAI Responses API: Use the remote MCP tool in the Responses API and keep approval enabled for non-read operations.

JSON

{
  "type": "mcp",
  "server_label": "data-enrichment-mcp",
  "server_url": "https://enrich.nordicdevhouse.com/api/mcp",
  "require_approval": {
    "always": {
      "read_only": false
    },
    "never": {
      "read_only": true
    }
  }
}

Generated tools

Tool	Mode	Scope	Approval
resolve_entity	write	entities:resolve	required
evaluate_entity_resolution	write	entities:resolve	required
detect_workspace_entity_duplicates	write	identity:write	required
decide_workspace_entity_duplicate	write	identity:write	required
split_workspace_entity_identity	write	identity:write	required
list_workspace_entity_identity_history	read	identity:read	never
submit_enrichment_job	write	enrich:write	required
list_enrichment_jobs	read	jobs:read	never
get_enrichment_job	read	jobs:read	never
get_enrichment_job_trace	read	jobs:read	never
list_enrichment_records	read	jobs:read	never
get_record_evidence	read	evidence:read	never
validate_knowledge_graph_query	write	graph:read	required
format_knowledge_graph_query	write	graph:read	required
translate_knowledge_graph_query	write	graph:read	required
verify_knowledge_graph_translation	write	graph:read	required
migrate_knowledge_graph_queries	write	graph:read	required
create_knowledge_graph_migration_run	write	graph:read	required
list_knowledge_graph_migration_runs	read	graph:read	never
get_knowledge_graph_migration_run	read	graph:read	never
retry_knowledge_graph_migration_run	write	graph:read	required
cancel_knowledge_graph_migration_run	write	graph:read	required
export_knowledge_graph_migration_run	read	graph:read	never
query_knowledge_graph	write	graph:read	required
submit_knowledge_graph_query_job	write	graph:read	required
get_knowledge_graph_query_job	read	graph:read	never
list_knowledge_graph_query_job_dead_letters	read	graph:read	never
cancel_knowledge_graph_query_job	write	graph:read	required
retry_knowledge_graph_query_job	write	graph:read	required
explain_knowledge_graph_query	write	graph:read	required
publish_knowledge_graph_claims	write	graph:write	required
list_knowledge_graph_releases	read	graph:read	never
get_knowledge_graph_release	read	graph:read	never
diff_knowledge_graph_release	read	graph:read	never
activate_knowledge_graph_release	write	graph:write	required
export_knowledge_graph_release_delta	read	events:read	never
publish_knowledge_graph_ontology	write	ontology:write	required
list_knowledge_graph_ontologies	read	ontology:read	never
get_active_knowledge_graph_ontology	read	ontology:read	never
create_knowledge_graph_ontology_draft	write	ontology:write	required
validate_knowledge_graph_ontology	write	ontology:write	required
activate_knowledge_graph_ontology	write	ontology:write	required
export_knowledge_graph_ontology	read	ontology:read	never
import_knowledge_graph_ontology	write	ontology:write	required
migrate_knowledge_graph_ontology	write	ontology:write	required
list_knowledge_graph_events	read	events:read	never
stream_knowledge_graph_events	read	events:read	never
create_knowledge_graph_event_subscription	write	events:write	required
list_knowledge_graph_event_deliveries	read	events:read	never
retry_knowledge_graph_event_delivery	write	events:write	required
create_graph_ingestion_source	write	ingestion:write	required
list_graph_ingestion_sources	read	ingestion:read	never
run_graph_ingestion_source	write	ingestion:write	required
list_graph_ingestion_runs	read	ingestion:read	never
list_graph_ingestion_dead_letters	read	ingestion:read	never
retry_graph_ingestion_dead_letter	write	ingestion:write	required
create_change_subscription	write	changes:write	required
list_change_subscriptions	read	changes:read	never
get_change_subscription	read	changes:read	never
update_change_subscription	write	changes:write	required
delete_change_subscription	destructive	changes:write	required
scan_change_subscription	write	changes:write	required
list_observed_changes	read	changes:read	never
get_observed_change	read	changes:read	never
create_alert_rule	write	alerts:write	required
list_alert_rules	read	alerts:read	never
get_alert_rule	read	alerts:read	never
update_alert_rule	write	alerts:write	required
delete_alert_rule	destructive	alerts:write	required
list_alerts	read	alerts:read	never
get_alert	read	alerts:read	never
acknowledge_alert	write	alerts:write	required
list_alert_deliveries	read	alerts:read	never
retry_alert_delivery	write	alerts:write	required
download_enrichment_artifact	read	jobs:read	never
list_review_cases	read	evidence:read	never
decide_review_case	write	enrich:write	required
create_enrichment_webhook	write	webhooks:write	required
delete_enrichment_webhook	destructive	webhooks:write	required
list_enrichment_webhook_deliveries	read	webhooks:write	never

MCP 2026 runtime

The server is stateless. Use server/discover, follow long-running operations through the Tasks extension, and answer input_required confirmations without changing the sealed requestState value.

Safety model

1
Grant only the API scopes the agent needs
2
Keep the API key server-side
3
Fulfil the signed confirmation round for write and destructive tools
4
Honor returned quota, retry, and circuit-breaker metadata
5
Preserve request and trace identifiers for auditing

Was this page helpful?