Documentation

Visit the login page and create your account using one of three methods:

• Google Sign-In -- One-click sign up with your Google account. Fastest way to get started.

• iCloud Sign-In -- Sign up with your Apple ID for seamless iCloud integration.

• Email & Password -- Create an account with any email address and a secure password.

All new accounts start with a free tier. No credit card required.

After signing in, navigate to the sidebar and connect your first service. We recommend starting with Gmail as it unlocks both email and calendar capabilities:

Navigate to the Chat page and start a conversation. Cognitia adapts to natural language -- just tell it what you need:

MCP & backups is where you extend Cognitia with external MCP (Model Context Protocol) servers and import assistant memory (ChatGPT, Claude, Gemini). MCP is an open standard that lets AI assistants interact with external services through a unified protocol. By connecting external MCP servers, you can add tools for services like Notion, Slack, databases, and many more — all without any coding.

There are two ways to add external MCP servers:

Once connected, each server appears as a card on the MCP & backups page showing its status, tool count, and last connection time. You can:

There is no additional credit cost for using external MCP tools. The only cost is the normal LLM token usage that applies to every message — tool definitions and results are part of the token count, just like built-in tools.

If an external server provides tools that overlap with a built-in Cognitia integration (e.g., a Gmail MCP server when you already have Gmail connected natively), the built-in integration takes priority automatically. This ensures you always get the best experience with native integrations while still being able to extend with external tools for services Cognitia doesn't cover natively.

The MCP Memory Layer lets you use the personal memory you've built with Cognitia from any external MCP-compatible client — including Cursor, Claude Desktop, Claude Code, Windsurf, and more. Your knowledge graph, conversation history, emails, files, financial data, social media, and multimodal identity data are all accessible through a single unified endpoint.

Instead of your memory being locked inside Cognitia, external AI agents can query it as context. For example, a coding agent in Cursor could retrieve your project-related knowledge, or Claude Desktop could recall your preferences and recent conversations.

Connecting takes one step — add the Cognitia MCP endpoint URL to your client. OAuth handles everything else automatically.

Cognitia's MCP server supports OAuth 2.1 with PKCE, the same industry-standard protocol used by Notion, Linear, and other MCP services. Clients that support OAuth (Cursor, Claude Desktop, Claude Code) handle the entire flow automatically.

External OAuth clients and personal API keys may call exactly three memory tools. Specialty tools (identity search, memory_as_of / memory_diff, share cards) stay on the first-party app session.

Identify-a-photo, person media galleries, cloned-voice playback, memory_as_of / memory_diff, and shareable memory cards remain available in the Cognitia app and first-party sessions. They are not on the external MCP allowlist.

When a new client connects via OAuth, you choose how much of each origin that app may see. Each client has its own grants. Change them later from MCP & backups or by calling unified_memory_agent_config.

Every origin has a fidelity: off (hidden), kg (synthesized graph only), or raw (graph plus vectors and live APIs). Default is raw. Writes from connected apps land on the mcp origin.

The host never picks sub-tools. Routing (named people, time windows, email/file/DM hits) happens inside unified_memory_agent and is filtered by those origin grants.

Go to MCP & backups to see all external apps that have been granted access to your memory layer. Each connected app shows:

Click Revoke to immediately disconnect an app and invalidate all its tokens. The app will need to re-authorize through the OAuth flow to regain access.

External MCP tool calls that run LLM agents (like unified_memory_agent) are billed based on actual token usage. The same per-model pricing as chat applies, with no free input token allowance. Tools that don't run LLMs (unified_memory_agent_config, unified_memory_store) are free.

Internal calls from the Cognitia web and mobile apps are not double-billed — credit deduction only applies when the request comes from an external OAuth client.

A rate limit of 60 requests per minute is applied per user across all MCP endpoints to prevent abuse.

When an external client calls unified_memory_agent, the request flows through several layers:

The Q&A response includes a synthesized context summary, structured entities/facts/signals, and optional source_cards when requested. Token usage metadata is stripped before the response reaches the client.

All endpoints are served from the base URL https://www.cognitia-ai.com/api/mcp. The server supports both the JSON-RPC 2.0 protocol and direct REST-style routes.

The authorization flow follows the OAuth 2.1 Authorization Code grant with PKCE (S256). Most MCP clients handle this automatically — the details below are for client developers and advanced users.

unified_memory_agent — Input

unified_memory_agent — Output

unified_memory_agent_config — Input (list)

unified_memory_agent_config — Output (list)

unified_memory_agent_config — Input (update)

unified_memory_agent_config — Output (update)

unified_memory_store — Input

unified_memory_store — Output

All MCP endpoints return standard HTTP status codes. The 401 response includes a WWW-Authenticate header pointing to the authorization server metadata, allowing clients to auto-discover the OAuth flow.

Rate Limits

When you send a message, Cognitia's orchestrator analyzes your request and determines which tools and agents are needed. For complex requests, it breaks the task into parallel operations:

Cognitia can browse the web on your behalf using a server-side browser agent. This agent can navigate pages, click buttons, fill forms, extract data, and complete multi-step flows like making reservations or signing up for services.

For complex multi-step tasks, Cognitia can create persistent workflow agents that track progress across steps, maintain state, and report back when complete. These agents use a built-in todo and memory system to break down large tasks into manageable steps and execute them sequentially or in parallel.

Generate professional documents directly from your conversations. Cognitia can create files in multiple formats and optionally upload them to your connected cloud storage.

Your memory graph is an asset you own — and you can optionally earn from it. When you enroll, vetted businesses can query consented data: research / HF buyers see Aggregate cohorts; brands that already have you as a customer may request Individual enrichment. Name, email, phone, and address are never shared. Nothing is listed until you opt in, and you can revoke at any time.

Open Data Platform → Marketplace and create a listing. You decide:

Aggregate queries only ever see anonymized cohorts across many enrolled users — never your identity. Individual enrichment additionally requires you to approve an explicit, per-business consent request. Identity fields are never in the payload. You can revoke any consent or unlist entirely at any time; revocation takes effect immediately and stops all future access.

The Marketplace API lets vetted businesses source consented personal-memory data — either research / HF Aggregate cohorts, or Individual enrichment for a person they already have as a customer. Every query is metered, logged, and pays the contributing users automatically. Name, email, phone, and address are never returned.

After access is approved, register with the activation code we send, complete verification, and generate a business API key (prefixed cog_biz_). Authenticate every request with Authorization: Bearer cog_biz_.... The marketplace tools are also available to MCP agents via marketplace_discover_providers, marketplace_aggregate_query, and marketplace_request_consent.

Buyers query one of three memory layers, scoped to users who have enrolled (research / HF Aggregate) or granted consent (merchant enrichment):

Research / HF results are always anonymized aggregates — no identity fields. Individual enrichment returns anonymous attributes for a person the merchant already has; name, email, phone, and address are never returned.

Approved businesses query against a prepaid balance. Every transaction is recorded and contributing users are paid automatically.

All routes require Authorization: Bearer cog_biz_... and are subject to per-business rate limits.

Enrichment query — Request

Enrichment query — Response

Research / HF query — Request