MCP for AI agents

Connect Claude, Cursor, ChatGPT, Gemini, or another MCP-compatible assistant to Infinite Audience. Your team can explore customer signals, shape segments, and run approved workflows from a conversation.

Connect the server

Server URL:

https://mcp.infiniteaudience.ai/mcp

Infinite Audience supports OAuth discovery, so compatible clients can open a browser sign-in and manage credentials for you. Add the server with one of the setups below, then choose Authenticate or Sign in when your client prompts you.

Choose your AI workspace

OpenAI

In the ChatGPT desktop app, open Settings → MCP servers, choose Add server, select Streamable HTTP, and enter the server URL above. Save, restart, and authenticate when prompted.

Codex CLI, the Codex IDE extension, and the ChatGPT desktop app share the same configuration. You can also add it to ~/.codex/config.toml:

~/.codex/config.toml

[mcp_servers.infinite_audience]
url = "https://mcp.infiniteaudience.ai/mcp"
auth = "oauth"

Then run codex mcp login infinite_audience. See the official OpenAI MCP guide.

Claude

Claude Code can add the remote server from the command line:

claude mcp add --transport http infinite-audience https://mcp.infiniteaudience.ai/mcp

Open /mcp, select Infinite Audience, and complete sign-in. See Anthropic’s MCP guide.

Cursor

Add the server globally in ~/.cursor/mcp.json, or use .cursor/mcp.json inside one project:

~/.cursor/mcp.json

{
  "mcpServers": {
    "infinite-audience": {
      "url": "https://mcp.infiniteaudience.ai/mcp"
    }
  }
}

Open Cursor’s MCP settings, enable the server, and complete OAuth when prompted. See Cursor’s MCP guide.

Antigravity

Open or create ~/.gemini/antigravity/mcp_config.json:

~/.gemini/antigravity/mcp_config.json

{
  "mcpServers": {
    "infinite-audience": {
      "serverUrl": "https://mcp.infiniteaudience.ai/mcp",
      "transport": "http"
    }
  }
}

In Antigravity, open Settings → Customizations, refresh the installed MCP servers, and authenticate Infinite Audience. See Google’s Antigravity getting-started guide.

If your client only accepts a bearer token

Exchange your API key using the API key guide, then store the returned access token in the client’s secure credential settings as:

Authorization: Bearer <access_token>

The token lasts one hour. Never commit it to a shared configuration file or place it in a prompt.

Start with this prompt

First prompt

List the available read-only Infinite Audience tools and explain three useful ways
they could help a marketing team. Do not create, enrich, deliver, purchase, or modify
anything until I approve the specific action.

Then try a product prompt:

Planning prompt

Help me plan a customer enrichment workflow for a CRM export. First ask what outcome
the marketing team wants, what identity fields the file contains, and which enriched
signals will change a decision. Recommend a simple approach and show any quote before
starting billable work. Wait for my approval before you run it.

Give the agent a good brief

State the business outcome, the source of the customer data, the destination, and any approval boundary. The clearer the brief, the more useful—and less meandering—the agent becomes.

Available tools

The server currently exposes 92 tools. Each tool lists the required token scope; some account operations also require an organization role.

Discovery & Schema

Tool	Scope	What it does
discovery_count	discovery	Count records matching criteria — accepts raw filters, segment_id, audience_id, or segment_ids + set_logic for composition preview.
discovery_lookup	discovery	Return up to 25 anonymized records matching criteria — accepts raw filters, segment_id, audience_id, or segment_ids + set_logic.

Campaigns

Tool	Scope	What it does
list_campaigns	discovery	List all campaigns for the organisation with status and audience count.
create_campaign	purchase	Create a named campaign workspace with an optional brief and goals.
get_campaign	discovery	Retrieve full campaign details including all linked audiences.
update_campaign	purchase	Update a campaign name, brief, or status (active or archived).
archive_campaign	purchase	Soft-archive a campaign. Linked audiences are preserved.
link_audience_to_campaign	purchase	Link an existing audience to a campaign. Each audience can belong to at most one campaign.
unlink_audience_from_campaign	purchase	Remove the link between an audience and a campaign, leaving the audience itself untouched.
get_campaign_operations	discovery	List recent and active operations (segment/audience/match/delivery events) across everything linked to a campaign.

Segments

Tool	Scope	What it does
list_segments	discovery	List all segments for your org. Supports filtering by subtype (filter/matched/similarity/propensity) and status.
get_segment	discovery	Retrieve full segment details including filter_groups, subtype-specific metadata, record_count, and current_version.
create_segment	purchase	Create a typed segment — filter, matched file upload, similarity, or propensity. Matched upload, analysis, and processing are free until the current run first participates in a successful delivery. Supports csv/json/jsonl/avro, optional gzip, and same-format shards.
save_segment	purchase	Persist a new named filter segment with its filter criteria. Shorthand for create_segment with subtype=filter.
bulk_create_segments	purchase	Create multiple segments in a single call (up to 25). Returns an array of created segment IDs.
wait_for_segment	discovery	Block until an async segment (matched/similarity/propensity) reaches active or failed status. Polls every 15s up to 15 min.
archive_segment	purchase	Archive a segment (or restore an archived one with restore: true). Always safe and reversible — never affects audiences that already reference it. Distinct from permanently deleting a segment via the REST API, which does change referencing audiences.
duplicate_segment	purchase	Duplicate a segment with lineage tracking, preserving subtype and all subtype-specific data (data referenced, never recomputed). Filter duplicates start with a null count; other subtypes carry the source counts. 409 if a matched source's data is unavailable.
get_segment_demographics	discovery	Get demographic breakdown (age, geo, behavioral) for a segment, evaluated over its own composition. Works for every subtype — matched/similarity/propensity bridge through a materialized id-set.
get_segment_audiences	discovery	List every audience that references a segment, with campaign linkage. Use before archiving, refreshing, or editing a segment to understand downstream impact.
count_segment	discovery	Recount a segment. Runs a fresh BigQuery count for every subtype — filter counts directly against its own filter definition; matched/similarity/propensity run the same composed count used by audience/delivery counting.

Audiences

Tool	Scope	What it does
list_audiences	discovery	List all saved audience builds with status, segment composition, and record count.
get_audience	discovery	Retrieve details and segment composition for a specific saved audience.
get_audience_demographics	discovery	Get demographic breakdown (age, gender, income, geo) for a saved audience.
create_audience	purchase	Create an audience — a subtype-agnostic composition wrapper. Accepts segment_refs with include/exclude roles and set_logic. Audiences are the delivery payload; use create_segment for typed cohort creation.
save_audience	purchase	Persist a new named audience from a list of segment IDs for quoting and delivery.
patch_audience	purchase	Partially update — rename, add/remove segments, change set_logic (union/intersection), or transition status (active/archived).
recount_audience	discovery	Trigger a fresh record count for an audience after its composition changes.
delete_audience	purchase	Soft-delete a saved audience by ID.
bulk_create_audiences	purchase	Create multiple audiences in a single call (up to 25). Returns an array of created audience IDs.
bulk_patch_audiences	purchase	Update name, status, or set_logic for multiple audiences at once (up to 50).
bulk_archive_audiences	purchase	Soft-delete multiple audiences in a single call (up to 50).
bulk_patch_segments	purchase	Update name and/or status for multiple segments at once (up to 50). Best-effort with per-segment failures.
bulk_archive_segments	purchase	Archive multiple segments in a single call (up to 50). Status-only and reversible — referencing audiences are unaffected.
duplicate_audience	purchase	Duplicate an audience with lineage tracking (parent + root ancestor, segment versions pinned). Carries composition; the duplicate starts with a null record count — recount to populate.
refresh_audience	purchase	Refresh one named member segment (segment_id is required) and bump this audience's version/expiry/status. Matched refreshes accept the established file format, optional gzip compression, and same-format shards. Other member segments and audiences remain untouched; recount separately.
refresh_segment	purchase	Re-derive one segment without touching its audiences. Filter is synchronous; matched returns fresh upload URL(s) for the established format with optional gzip compression and same-format shards; similarity/propensity relaunch their workflow. The response lists affected_audiences.

Enrichment & Catalog

Tool	Scope	What it does
get_field_catalog	discovery	Return enrichment fields, templates, and per-org pricing structure. Call before quote_delivery or deliver_audience to present options.
get_data_release	discovery	Return the platform current data-release version. Compare against a match result's resolution_action to tell whether a direct Refresh returned unchanged data.
analyze_audience_upload	discovery	After uploading a csv/json/jsonl/avro file (plain or gzip) to the presigned URL, run bounded streaming column inference. Returns analysis.columns[], unmapped_columns[], and recommendations[].
confirm_column_mappings	purchase	Confirm column mappings for a staged matched-segment upload, moving the file into place and starting identity resolution.
cancel_matched_upload	purchase	Abort a staged (hitl:true) matched-segment upload without confirming. The segment is left untouched.
discovery_overlap	discovery	Calculate overlap count, percentage, and demographic deltas between two segments or audiences.
discovery_crosstab	discovery	Generate a cross-tabulation pivot table across two demographic dimensions for a segment, audience, or raw filter expression.
match_records	purchase	Synchronous micro-batch identity resolution for up to 100 contact records submitted inline. Returns matched records with iag_person_id and enrichment fields. Records usage per matched record; amount_charged is a pending estimate.
list_match_runs	discovery	List past micro-batch match calls — run_id, match_count, match_rate, conservative pending-usage estimate (amount_charged), field_list, created_at. Cursor-paginated via before= timestamp.
get_match_run	discovery	Retrieve a single micro-batch run by run_id. Returns full details including input_record_count, match_rate, conservative pending-usage estimate (amount_charged), and expires_at.
list_integration_runs	discovery	List safe partnership activity with provenance, counts, selected fields, and billing rail. Supports one indexed filter and cursor pagination.
get_integration_run	discovery	Retrieve one safe partnership-run projection by run_id without exposing private workflow artifacts.
list_saved_integration_matches	discovery	List provider-neutral private saved-match holding collections with aggregate metadata only.
preview_saved_integration_segment	discovery	Preview exact unique, duplicate, expired, suppressed, overlap, and net-addition counts without mutation or usage.
build_saved_integration_segment	purchase	Create a matched segment or extend a compatible standalone matched segment from already-settled integration matches, without rerunning matching or creating an audience.
get_saved_integration_segment_build	discovery	Read aggregate status and the durable segment ID for a queued saved-match materialization.
list_file_match_jobs	discovery	List async file-based identity resolution jobs with status, match rate, and the one-time match estimate once first delivered (amount_charged is null beforehand), plus format/compression and segment/audience IDs.
get_file_match_job	discovery	Get one file match job by match_id (= segment_id), including the one-time match estimate once first delivered (amount_charged is null beforehand), format/compression, matching status, field counts, lineage, audience ID, and errors.

Delivery

Tool	Scope	What it does
quote_delivery	discovery	Quote a download with explicit output_format and output_compression axes. Returns itemized cost, balance sufficiency, and already_delivered for a free re-export of the same paid audience/version/template.
deliver_audience	purchase	Deliver a download with explicit output format/compression. CSV/JSON/JSONL may use gzip; Avro uses native DEFLATE and rejects outer gzip. LiveRamp/Narrative stay unavailable until their partner pushes confirm egress.
bulk_deliver_audiences	purchase	Deliver up to 25 audience downloads with shared fields and explicit output format/compression; artifact-axis-only re-exports are not rebilled.
deliver_file_match	purchase	Trigger download delivery for a matched audience with explicit output format/compression. Returns a processing delivery_id; follow with wait_for_delivery.
wait_for_delivery	discovery	Block until a delivery completes or fails (polls every 15 s, up to 15 min). Call after deliver_audience or deliver_file_match when status is processing. Returns download_urls[] on success.
list_deliveries	discovery	List audience deliveries with status, cost, output format/compression, exact output bytes, and timestamps.
list_file_match_deliveries	discovery	List deliveries for a file match, including output format/compression and exact output bytes.
list_all_deliveries	discovery	List org deliveries with optional status, destination, and audience filters, including artifact axes and bytes.
get_delivery	discovery	Get delivery status, artifact axes, exact bytes, and every output part URL. Download URLs are regenerated on each GET; do not cache them.

Workflows

Tool	Scope	What it does
wait_for_workflow	discovery	Block until a similarity or propensity audience workflow completes. Returns completed status with audience_id, or paused gate info when hitl=true.
respond_to_workflow_gate	purchase	Submit a user response to a paused HITL gate in a running workflow. Only used when hitl=true on audience creation.
get_workflow_status	discovery	Check current step, status, and gate info for a running workflow.

Billing

Tool	Scope	What it does
check_balance	account	View the routed billing projection: contract, rated current-period spend, credits, automatic recharge, safety overlays, payment readiness, and staleness.
buy_credits	account	Begin an idempotent, payment-gated credit top-up for a self-billed prepaid org. Returns a durable request ID and status.
check_topup_status	account	Read verified durable status for a top-up and return a payment action URL only when customer action is required.
manage_subscription	account	Open the Stripe Billing Portal for payment-method management and invoice history only. Returns portal_url.
change_subscription_tier	account	Schedule a tier and/or cadence change at the next billing period without proration. Owner only.
cancel_subscription	account	Schedule the billing contract for cancellation at its verified boundary. Owner only.
revert_cancellation	account	Revert a previously scheduled subscription cancellation. Owner only.
get_account_usage	account	Retrieve operational counts, rated current-period spend and projection time, and compute ceiling usage.

Team & Org

Tool	Scope	What it does
org_list_members	account	View all active and suspended members in your account.
org_change_role role: owner	account	Promote or demote a member between admin and member roles.
org_suspend_member role: owner/admin	account	Temporarily block a member from accessing the platform.
org_reinstate_member role: owner/admin	account	Restore access for a previously suspended member.
org_remove_member role: owner/admin	account	Permanently remove a member from your account.
org_list_invites role: owner/admin	account	See all outstanding invites that have not yet been accepted.
org_create_invite role: owner/admin	account	Send an email invite link. Links expire after 7 days.
org_revoke_invite role: owner/admin	account	Cancel a pending invite so it can no longer be used.
org_list_api_keys role: any member	account	View all API keys for your account. Key values are never returned.
org_create_api_key	account	Generate a new API key. The full key is shown only once — store it securely.
org_revoke_api_key	account	Permanently deactivate an API key immediately.
org_get_settings	account	Get org settings: name, invite code, webhook config, delivery destinations, and billing preferences.
org_update_settings role: owner/admin	account	Update webhook config, delivery destinations, or billing preferences.
org_rename role: owner	account	Rename the organisation.
org_rotate_invite_code role: owner/admin	account	Generate a new shared invite code, invalidating the previous one.
org_billing_contacts role: owner	account	Get or replace billing contact emails for the organization.
org_invoices role: owner/admin	account	List invoices and line items with collection status and hosted links.