Exist MCP server for AI agents

Live

OAUTH 2.0

PERSONAL ANALYTICS

Analytics

Exist gives your agent personal analytics from each user's Exist account: read tracked attributes and daily values, correlations, insights, and weekly averages, and log values to attributes your app owns.

  • Per-user credentials: each call uses the actual user's token, never a shared bot.
  • Encrypted per-tenant vault: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: pre-call scope check, 90-day SIEM-exportable audit chain.
Exist
agent · Acme Q3
Run
What correlates with my sleep?
S
exist_correlations_list
102ms
Wellbeing agent
Exist found 3 strong correlations with your sleep. You sleep longer on days with more than 8,000 steps.
Sources: Exist correlations, 3 results
exist
3 correlations
18:29
Message Claude...

Tools your wellbeing agent reaches for on Exist, scoped per user.

CALL ANY TOOL
15 tools for personal analytics in Exist: read attributes, daily values, averages, correlations, and insights, and create, own, and update the attributes your app tracks.
exist_attribute_templates_list
List attribute templates
List the attribute templates Exist supports (its built-in attribute types, such as steps, sleep or mood). Returns a paged object with count, next, previous and results; each template has name, label, group, priority, value_type and value_type_description. Use exist_attribute_templates_list to find a template name to pass to exist_attributes_create or exist_attributes_acquire. Use exist_attributes_list for the attributes this user actually has.
Parameters
Name
Type
Required
Description
groups
string
Optional
Comma-separated attribute group names to filter by, such as activity, productivity, mood, sleep, workouts, events, finance, food, health, location, media, social, weather, symptoms, medication or custom. Example: activity,workouts.
include_low_priority
boolean
Optional
Set to true to also return low-priority attributes (priority 10 or higher). Leave empty to leave them out.
limit
integer
Optional
Number of results per page. Leave empty to use Exist's default page size. Example: 50.
page
integer
Optional
Page number of results to return, starting at 1. Leave empty for the first page. Use the 'next' URL's page number from the previous response to fetch the next page. Example: 2.
exist_attribute_values_get
Get attribute values
exist_attribute_values_increment
Attribute values increment
exist_attribute_values_update
Update attribute values
exist_attributes_acquire
Attributes acquire
exist_attributes_create
Create attributes
exist_attributes_list
List attributes
exist_attributes_release
Attributes release
exist_attributes_with_values_list
List attributes with values
exist_averages_list
List averages
exist_correlation_get
Get correlation
exist_correlations_list
List correlations
exist_insights_list
List insights
exist_owned_attributes_list
List owned attributes
exist_profile_get
Get profile
Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Exist tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["exist"], toolNames: [
    "exist_attributes_with_values_list",
    "exist_correlations_list",
    "exist_attribute_values_increment"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Log 20 minutes of meditation and tell me what correlates with my mood" }] });
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["exist"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Log 20 minutes of meditation and tell me what correlates with my mood" }],
  tools,
});

// Execute the tool call with the user's vaulted Exist OAuth token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["exist"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Log 20 minutes of meditation and tell me what correlates with my mood" }],
  tools,
});

// Tool call runs with the user's vaulted Exist OAuth token
await sk.tools.executeTool(msg.content, "user_123");
import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["exist"] }, pageSize: 100,
});

const agent = new Agent({
  name: "wellbeing_agent",
  model: "gemini-2.5-pro",
  instruction: "Exist tools scoped to this user",
  tools,
});

await agent.run("Log 20 minutes of meditation and tell me what correlates with my mood");
Try these prompts
Copy any prompt into your agent. Each maps directly to a Exist tool. Click to copy, paste into your agent, done.
Tracked data
Copy the prompt
Copied
List the attributes I track in Exist.
Copy the prompt
Copied
Show my daily step count for the last 14 days.
Copy the prompt
Copied
What were my weekly averages last week?
Patterns
Copy the prompt
Copied
What correlations has Exist found for my mood?
Copy the prompt
Copied
How strongly is coffee correlated with my sleep?
Copy the prompt
Copied
Show the insights Exist generated this week.
Logging
Copy the prompt
Copied
Create a custom attribute called Meditation minutes.
Copy the prompt
Copied
Add 20 to today's Meditation minutes.
Copy the prompt
Copied
Set today's Meditation minutes to 30.
SEE HOW AUTH WORKS
Each user signs in to Exist once, and Scalekit stores and refreshes their tokens. Credentials stay vaulted, every call is scope checked, and every action is logged.
1
Authorize
Your user connects
Exist
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
Exist
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
Exist
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
Exist
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
See the same per-user auth pattern across other analytics and productivity connectors.
Support and Ops Teams
Meeting prep
Pulls agenda, participant context, and open action items before every meeting.
Test other agents
See the same per-user auth pattern across other analytics and productivity connectors.
OPS
Meeting prep agent
Assemble the agenda, HubSpot attendee history, and open action items from Gmail before every meeting on the calendar.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared Exist token looks fine in a demo. In production every logged value looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.
// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Exist today. Ten connectors tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access Exist as the user or through a shared service account?
As the user. Each user signs in to Exist once, and Scalekit stores and refreshes their tokens. Values the agent logs are attributed to that user in your audit trail, not a shared service account.
Where is the Exist OAuth token stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.
Can I limit what the agent does in Exist?
Yes. Filter by tool name in listScopedTools to expose only what you want, for example the read tools without exist_attribute_values_update, which overwrites a day's value, or exist_attributes_release. Scalekit also enforces scope checks before every API call.
What happens when a user revokes Exist access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.
Can the agent write to any Exist attribute?
Only to attributes your app owns. exist_attributes_create makes new attributes owned by the app, exist_attributes_acquire takes ownership of existing ones so the app can write their values, and exist_owned_attributes_list shows which attributes it owns. exist_attributes_release gives ownership back.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""exist"": {
""url"": ""https://mcp.scalekit.com/exist"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.exist]
url = ""https://mcp.scalekit.com/exist""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""exist"": {
""url"": ""https://mcp.scalekit.com/exist"",
""type"": ""http""
}
}
}