HiveBase

Site navigation

HiveBase
Log inGet started free
HIVEBASE MCP

Install one MCP endpoint. Give every AI agent the same company context.

Stop re-explaining your company. Update once, and every connected agent catches up with cited context.

Install MCPDeveloper docs
Claude
Cursor
Codex
ChatGPT
Any MCP
CATCH ME UP
mcp.hivebase.ai
Hosted MCP
one endpoint
0
continuity tools
0 credits
context reads
OAuth 2.1
scoped consent
INSTALL

Connect your host in one step

Point any MCP client at the hosted endpoint. OAuth handles the first connection — no self-hosted server, no version pin.

ENDPOINThttps://mcp.hivebase.ai/
CLAUDE CODE · CLI
claude mcp add hivebase --transport http https://mcp.hivebase.ai/

Backend or CI? Scoped API key + REST / @hivebase/sdk · API keys →

MCP docsAPI settings
HOW IT WORKS

One loop every agent follows

Three moves — load cited context, write back one durable outcome, then continue in another agent.

  1. READ
    mcp.hivebase.ai
    $

    The first agent pulls a visibility-scoped, source-backed company brief.

    Visibility-scoped
  2. REMEMBER
    mcp.hivebase.ai
    $

    With writeback enabled, preserve one outcome or explicit decision for the next session.

    Explicit writeback toggle
  3. CONTINUE
    mcp.hivebase.ai
    $

    A fresh host asks for changes since its durable cursor and sees the outcome immediately.

    Same context in every host

Same loop over MCP for AI apps and the Platform API for services. Action receipts →

THE SURFACE

What agents wire first

Seven focused continuity tools across context, decisions, and receipts. No task-management catalog to navigate.

Read context before work

A cited company capsule first, then granular source-backed evidence when the answer needs it.

context.briefcontext.search
Docs
$ context.brief({ query: "Acme renewal" })
CONTEXT PACKET

Acme renewal · SSO dependency · board risk this week

3 sources · 1 decision · cited
same packet →ClaudeCursorCodexChatGPT
Full tool reference →Developer docs →
MCP VS API

Same product. Two entry paths.

AI apps use MCP + OAuth. Services and CI use scoped keys.

MCP · AI appsPlatform API · services
AuthOAuth 2.1 + CIMDScoped hb_sk_* keys
CallerClaude, Cursor, Codex, ChatGPT, MCP hostsCI, workers, backends
WritesExplicit writeback capabilitySame scopes and receipts
Entrymcp.hivebase.ai/mcpREST · @hivebase/sdk
Install MCP →Auth docs →
FAQ

Questions

What is the HiveBase MCP server?

One hosted endpoint that gives Claude, Cursor, Codex, ChatGPT, and other MCP hosts the same cited company context and durable writeback.

Do I need to host it myself?

No. mcp.hivebase.ai is hosted. OAuth handles first connection for AI apps. API keys in settings cover CI and backends.

Can agents write, or only read?

Both. Catch me up is read-only by default. Remember what we decide is a separate explicit toggle; writes return durable receipts and source attribution.

MCP vs API keys — when each?

MCP + OAuth for interactive AI apps. Scoped hb_sk_* keys with REST or @hivebase/sdk for CI and non-interactive services.

When is this not needed?

Personal assistant memory is enough for one-person recall. A single-tracker team happy with that product's agent may not need HiveBase. The fit is multi-surface companies running multiple AI apps against one shared company record.

Install MCP first. Use the API where services need it.

OAuth for AI apps. Scoped keys for CI and backends.

Install MCPMCP docsGet started free