Model Context Protocol

Audience intelligence, inside your agent.

Connect Claude, Cursor, or Windsurf to the same audience model behind Sovrn AI. Ask who, how large, or what is related without leaving the conversation.

Connect your client See all 13 tools

Browser sign-in for interactive clients. No key to paste. Grounded in a model representing 118M+ people.

https://sovrn.ai/api/mcp

Claude

Cursor

Windsurf

OAuth

Connected

Sovrn AI

10 typed tools · read-only access

FindSizeCompare

Connect

Add one URL. Sign in in your browser.

Choose your client for the exact setup. OAuth is the default; API keys appear only on the HTTP path for scripts and CI.

Add the server

terminal

claude mcp add --transport http sovrn-lbm https://sovrn.ai/api/mcp

Run once, restart Claude Code, then type /mcp and pick Authenticate. Your browser opens the Sovrn sign-in.

Sign in when prompted

No key needed. Your browser opens Sovrn sign-in, then asks you to approve read-only tool access.

Ask for an audience

“Size an audience of sneaker buyers who follow streetwear releases.”
“Who overlaps between my ski buyers and luxury travelers?”

You describe the people. Your agent chooses the tool.

Live tool catalog

Thirteen tools. One audience model.

This list mirrors the server's registered tools. The exact list a client receives can be smaller when a role or plan does not include a tool.

Start here

Find the audience in one call.

search_audience

Describe who you need in plain English. The server returns the match, estimated scale, behavioral evidence, and related groups. Follow-up tools compare, refine, or inspect the result.

estimate_audience_sizeFind

Estimate its size

Run a calibrated count with a confidence interval when the number needs to travel.

discover_cohortsFind

Explore related groups

Test themes against an audience and see which groups genuinely over-index.

audience_time_seriesCompare

See change over time

Compare audience interest by hour or day with coverage-normalized periods.

compute_overlapCompare

Compare two audiences

Measure the observed intersection and its share of each audience.

search_audience_excludeCompare

Remove a group

Find an audience, subtract an unwanted cohort, and keep the cleaner result.

sample_usersInspect

Quality-check a match

Inspect a small sample from a result to verify the behavioral evidence behind it.

describe_userInspect

Inspect one result

Read the behavioral metadata for one pseudonymous result from an earlier search.

get_capabilitiesLearn

Read the server guide

Load the data model, limitations, metric definitions, and additional-skill manifest.

read_skill_docLearn

Open a skill document

Fetch a Sovrn reference document when the client cannot read MCP resources directly.

Census context, where present, describes areas in aggregate—not individual traits. Audience sizes are estimates, and small groups are directional.

Reference library

Current Google Ads guidance, available on demand.

The server also carries a maintained Google Ads guide. Your agent reads the relevant reference when you ask—not a stale answer from model memory.

Correct stale advice

See what replaced retired match types, account structures, and bidding practices.

Audit in the right order

Start with measurement, then settings, structure, bidding, and keywords.

Ground the audience

Use observed sites and interests as planning inputs for work in your own ad tools.

This is reference material, not an activation tool. Connect Google Ads in Settings → Connectors to use list_accessible_customers, search, and get_resource_metadata. Those tools read the account you connected; they do not create campaigns.

For scripts and builders

Use the protocol directly when you need to.

Plain HTTP

JSON-RPC 2.0 over POST. This secondary path uses an API key because scripts cannot complete browser sign-in.

API keys

curl

curl -X POST https://sovrn.ai/api/mcp -H "Authorization: Bearer YOUR_KEY" -H "Content-Type: application/json" -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"search_audience","arguments":{"prompt":"people shopping for trail-running gear and reading endurance training"}}}'

Built to be discovered

A client can learn the server without a separate SDK or hardcoded integration guide.

tools/list: Typed schemas filtered to the account’s permissions and plan.
resources/list: Skill and data-model documents the agent can read when needed.
pending → retry: Long searches continue server-side; retry the call to collect the result.

Ready to connect

Bring your next audience question into the tool you already use.

Add the server, sign in in your browser, and ask in plain English.

Connect your client