Great AI needs more than a great model
AI can reason, explain and recommend. But without access to accurate financial information, it lacks the context to deliver meaningful financial experiences.
Anessa connects AI assistants and agents to customer-consented financial data, enabling them to work with actual holdings, balances and financial information rather than assumptions.
curl https://api.anessa.co/v1/accounts \
-H "Authorization: Bearer $TOKEN"
Editor note (hidden on the live site): paste code in the Code field on the right and set the card header in Code Title / Code Meta (leave both empty to hide it). Lines starting with // are comments; a quoted line that isn't a key (a chat question or answer) shows as text. Colours and line numbers only appear on the published page.
curl https://api.anessa.co/v1/accounts \
-H "Authorization: Bearer $TOKEN"
Editor note (hidden on the live site): paste code in the Code field on the right and set the card header in Code Title / Code Meta (leave both empty to hide it). Lines starting with // are comments; a quoted line that isn't a key (a chat question or answer) shows as text. Colours and line numbers only appear on the published page.
Access financial data with customer consent
Customers select the financial institutions they want to connect and authorise access to their information.
Anessa retrieves and structures the data, making it available to supported AI assistants and agents through MCP.
Anessa MCP
// Advisor asks in Claude
"Compare the fees on this client's pension
and investment account. Is she overpaying?"
// Claude calls Anessa
get_holdings_and_fees({ "collection_id": "c-7f3a91" })
// Anessa returns consented data
{
"pension": {
"value": 125900, "fee": 0.0042,
"feesLastYear": 553, "movable": true
},
"investments": { "value": 55680, "fee": 0.0020 }
}
// Claude answers
"Yes, on the pension. She pays 0.42% there
against 0.20% in her investment account.
Moving it would save about 280 EUR a year."
Editor note (hidden on the live site): paste code in the Code field on the right and set the card header in Code Title / Code Meta (leave both empty to hide it). Lines starting with // are comments; a quoted line that isn't a key (a chat question or answer) shows as text. Colours and line numbers only appear on the published page.
Put MCP to work
Financial AI
Financial advisory
FAQ
What is MCP?
A standard that lets an AI assistant or agent query an external data source conversationally, without the builder constructing that integration layer.
Is this live?
Yes. Anessa’s MCP server is live and works with any assistant or agent that supports MCP. Talk to us to get access.
Can an assistant get Intelligence outputs through MCP?
Yes. Intelligence insights on fees, portfolio composition and peer benchmarks are available through Anessa’s MCP server, alongside the customer’s financial data. Your assistant can use calculated figures in its answers instead of working them out itself. Access is enabled on request, so talk to us to get started.
Is it secure and consented?
Yes. Nothing is collected until the customer has given their consent and authorised Anessa’s assisted access to their financial service provider. Anessa uses the customer’s credentials only to carry out the data collection and discards them immediately afterwards. They are never shared and never reach your systems. All data is encrypted in transit and at rest and stored in the EU, and Anessa is ISO 27001 certified.