HOME/INTEGRATIONS/MCP SERVER
INTEGRATION · MCP SERVER

Your AI assistant, your growth agent.

An OAuth 2.1 + PKCE-secured Model Context Protocol server. Claude Desktop, ChatGPT, Gemini, Cursor, Zed — any MCP-compatible agent can run experiments, check live rankings, crawl competitors, and analyze analytics in natural language.

Watch 2-min demo ▸
27 TOOLS · 17 READ · 10 WRITEOAUTH 2.1 + PKCEATTESTATION-SIGNED
THE DIFFERENTIATOR

No other optimization platform lets an AI agent operate on your data.

Optimizely has a dashboard. Crayon has a dashboard. Every CI / CRO / SEO tool has a dashboard. Optimize Pilot has dashboards too — and an MCP server. Your AI assistant can now be the one asking "where do we rank vs Notion this week?" and getting back a real answer from real data, then drafting the experiment to respond.

◆ HOW IT WORKS

From "install" to "run experiments from your editor" in three moves.

TOTAL TIME · ~3 MIN
STEP 01

Install the MCP server

Add the Optimize Pilot MCP endpoint to your agent's config. Works with Claude Desktop, Cursor, Zed, Continue, Cline, or any MCP-compatible client.

ONE CONFIG LINE
STEP 02

Authorize with OAuth

First call triggers OAuth 2.1 + PKCE. Scoped tokens — read-only, write, or full — per agent per environment. Revokable per-token from the dashboard.

PKCE · SCOPED
STEP 03

Your agent operates

Ask in natural language. The agent picks tools, calls them, brings back grounded answers. Destructive ops require confirm=true. Every write action is attestation-signed.

27 TOOLS
◆ CAPABILITIES

Your growth stack, exposed as tools.

READ TOOLS · 17

Every signal your agent might need.

Site analytics, geographic and referrer breakdowns, page performance, engagement, real-time visitors, visit timing, goal details, browser/OS, experiments and their results, rank checks, keyword research, rank history, web search, action status. No gap between "what's in the dashboard" and "what the agent sees."

  • site_analytics · geographic · referrers · page_performance · engagement
  • real_time_visitors · search · visit_timing · goal_details · browser_os
  • experiments · experiment_results · rank_check · rank_history
  • keyword_research · web_search · action_status
PRODUCT VISUAL — PLACEHOLDER
WRITE TOOLS · 10

Your agent can actually ship.

Write tools are gated behind the mcp.write scope and require a paid tier. Destructive operations (stop_experiment, deploy_winner) additionally require confirm=true in the tool call — no surprise rollouts.

  • suggest_experiment · create_experiment · start_experiment
  • pause_experiment · stop_experiment (confirm=true)
  • deploy_winner (confirm=true) · crawl_website
  • update_business_profile · update_recommendation_status
  • trigger_seo_audit
PRODUCT VISUAL — PLACEHOLDER
ATTESTATION

Proof the AI read it. Verification it shipped.

When your agent implements a recommendation, a signed attestation token captures what the agent read and the proof URL of the change. The server then verifies server-side that the change is actually live. This is how you trust an AI to touch production.

  • Per-action signed attestation tokens
  • Server-side verification of proof URLs
  • Full audit log of every tool call
  • Revocable per-agent, per-site tokens
PRODUCT VISUAL — PLACEHOLDER
CHAINABLE PROMPTS

Three prompts to start with.

Ships with three built-in chainable prompts that compose the read and write tools into full workflows: design_and_launch_experiment, weekly_performance_review, competitor_gap_brief. Drop them into a Claude project or Cursor rule and your agent has a running start.

  • design_and_launch_experiment — end-to-end with approval gates
  • weekly_performance_review — data pull + summary + next actions
  • competitor_gap_brief — Radar + SEO + Navigator composition
  • Fully customizable per workspace
PRODUCT VISUAL — PLACEHOLDER
ASYNC JOBS

Long-running crawls and audits stream back.

Competitor crawls and SEO audits take more than a single tool-call timeout. The MCP server returns a job ID and streams progress back to the client, so your agent sees the scan complete in real time and can follow up the moment data is ready.

  • Job IDs for long-running operations
  • Progress streaming to MCP clients
  • Multi-site tokens — one token, many sites, agent picks which
  • Rate limits + quotas exposed in the dashboard
PRODUCT VISUAL — PLACEHOLDER
◆ TECHNICAL SPECIFICATIONS

Under the hood.

PROTOCOL
MCP v1 (Model Context Protocol) — full tool, prompt, and resource support
AUTH
OAuth 2.1 with PKCE; scoped tokens per agent + environment
SCOPES
mcp.read · mcp.write — write gated to paid tiers
TOOLS
27 total — 17 read, 10 write
CONFIRM-GATED
stop_experiment, deploy_winner require confirm=true
ATTESTATION
Per-action signed tokens; server-verified proof URLs
CHAINABLE PROMPTS
3 built-in: design_and_launch_experiment · weekly_performance_review · competitor_gap_brief
ASYNC
Long jobs return a job ID; progress streams to client via SSE
MULTI-SITE
One token can operate across every site the user has access to; agent specifies target per call
RATE LIMITS
Per-tier quotas + burst allowance; visible in dashboard
COMPATIBLE CLIENTS
Claude Desktop, Cursor, Zed, Continue, Cline, ChatGPT (MCP beta), Gemini, custom agents
AUDIT LOG
Every tool call logged with agent, user, scope, token, outcome. Exportable.
◉ MCP READY

Wire your agent in this afternoon.

OAuth install in under three minutes. Read-only tokens free-tier. Write tools unlock on paid plans.

Book a demo