Hyperengage
Pricing
Agent API (Beta)About
Book a Demo
Hyperengage Logo

The customer memory graph for post-sales agents.

Stay in the loop

Product

  • Memory Graph
  • Agent API (Beta)
  • Pricing
  • Security

Resources

  • Blog
  • Podcast
  • Glossary
  • Newsletter

Company

  • About
  • Contact

Legal

  • Privacy Policy
  • Terms of Service
  • Cookie Policy
  • Subprocessors

© 2026 Hyperengage Inc. All rights reserved.

PrivacyTermsCookies
Private beta·MCP

Plug any agent into the Customer Memory Graph.

Hyperengage ships an MCP server that exposes live customer state as typed tools. Claude, Codex, ChatGPT, or your own agent can read events, emails, meetings, decisions, actions, and threads. And write back. No stale CRM exports. No glue code.

Request beta accessSee how it works
~/.claude/mcp.jsonconnected
{
  "mcpServers": {
    "hyperengage-memory": {
      "command": "npx",
      "args": ["@hyperengage/mcp"],
      "env": {
        "HYPERENGAGE_API_KEY": "hp_live_••••••••"
      }
    }
  }
}

Why MCP

Most agents work off stale decisions.

A CRM export is a snapshot. By the time your agent reads it, the customer has shipped a feature, opened a ticket, sent a renewal email, and changed champion. Your agent acts on a world that no longer exists.

The Customer Memory Graph reconciles every signal as it happens. MCP gives your agent a tool to read it the moment it's true. Live state. Reasoned. Tenant-scoped. Always current.

CRM export

  • · Snapshot
  • · Hours stale
  • · Forms only
  • · No sentiment
  • · One-way

Memory Graph

  • · Live
  • · Reconciled now
  • · All channels
  • · Reasoned signals
  • · Bidirectional

How it works

Three steps. No glue code.

STEP 01

Drop in the MCP config

Add the Hyperengage MCP server to your agent's mcp.json. Two lines for Claude, Codex, Cursor, or Continue. Done in 60 seconds.

STEP 02

Your agent discovers tools

memory.read, memory.search, memory.subscribe, graph.traverse, memory.write — auto-discovered, fully typed, with example usage.

STEP 03

Read & write live state

The agent calls tools as needed. Reads return reasoned, reconciled state. Writes update the graph. Sidekick, Copilot, and Signals Engine see the changes instantly.

What your agent reads

Every memory type. Reasoned, not raw.

The graph stores six entity types per customer. Your agent reads them as structured, typed objects with relationships, sentiment, and derived signals.

Events

Product usage, feature adoption, milestone hits.

Emails

Inbound and outbound across every CSM and customer contact.

Meetings

Recordings, transcripts, and reasoned briefs — not raw notes.

Decisions

Renewal calls, pricing concessions, exec asks. Captured and timestamped.

Actions

Playbook steps, follow-ups, CRM updates. What was done, by whom, when.

Threads

Slack and internal conversations about the account, threaded to it.

Tools your agent gets

Six MCP tools. All typed.

memory.read

Pull a customer's full memory or filter by entity type, time window, or signal.

memory.search

Semantic search across every customer interaction — emails, meeting transcripts, threads.

memory.subscribe

Stream changes as they reconcile. Your agent reacts in seconds, not on a polling loop.

memory.write

Write back decisions, actions, and notes. The graph is bidirectional.

graph.traverse

Walk relationships — account → contacts → meetings → decisions → next actions.

graph.diff

Ask what changed between two points in time. Reasoned diffs, not raw deltas.

Built right

What makes this different.

Live state, not stale exports

Your agent sees the graph as it is right now — not a CSV exported six hours ago.

Bring any agent

Claude, Codex, ChatGPT, or your own custom agent. MCP is the universal protocol.

Reasoned, not raw

Tools return interpreted state — sentiment, trajectory, signals — not just rows.

Tenant-scoped & audited

Every call is workspace-scoped, logged, and rate-limited. Read scopes are explicit.

Bidirectional

Agents read state and write decisions/actions back. The graph stays in sync with what your agents do.

Drop-in MCP

Stand up an MCP server in two lines of config. Works with any MCP-compatible host.

Works with

Any MCP-compatible agent. No exceptions.

If it speaks MCP, it can read the graph. We ship example configs for the runtimes our customers actually use.

C

Claude

C

Claude Code

C

Codex

C

ChatGPT

C

Cursor

+

Custom

FAQ

Common questions.

What is MCP?+

Model Context Protocol — an open standard for letting AI agents call typed tools across servers. Hyperengage exposes the Customer Memory Graph as an MCP server, so any MCP-compatible agent (Claude, Codex, ChatGPT desktop, your own runtime) can read live customer state.

How is this different from a CRM API?+

A CRM API returns whatever someone typed into a form. The Customer Memory Graph returns reconciled, reasoned state — sentiment, trajectory, risk signals, expansion moments — fused across CRM, product, support, and comms. Your agent doesn't have to stitch context together itself.

Can my agent write back?+

Yes. memory.write lets agents persist decisions, actions, follow-ups, and notes. The graph stays consistent with what your agents do, and Sidekick / Copilot / Signals Engine see the same writes immediately.

Which agents work today?+

Anything that speaks MCP. Confirmed: Claude (claude.ai, Claude Code), Codex, ChatGPT (desktop), Cursor, Continue, and custom runtimes built on the Anthropic / OpenAI / Vercel AI SDKs. We ship example configs for each.

What does pricing look like?+

MCP access is included with every Hyperengage workspace. Per-call rate limits scale with your plan. Beta participants get unlimited calls during the program.

Is the protocol open?+

MCP is an open standard. Our implementation follows the spec; tool schemas, scopes, and webhooks are documented. You're never locked into Hyperengage's stack to talk to the graph.

Request beta access

We onboard a small batch each month. Tell us what you're building and we'll fit you in.