Site navigation

HIVEBASE MCP

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

One hosted server for Claude, Cursor, Codex, and ChatGPT. Free context reads. Writes stay confirmable, provenanced, and undoable.

claude mcp add --transport http hivebase https://mcp.hivebase.ai

Claude
Cursor
Codex
ChatGPT
Any MCP
FREE READ
mcp.hivebase.ai
Hosted MCP
one endpoint
0
audited tools
0 credits
context reads
OAuth 2.1
scoped consent
INSTALL

Connect your host in one step

Copy the Claude Code, Cursor, or Codex command below. OAuth handles the first connection — no self-hosted server, no version pin.

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

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

AFTER INSTALLAGENTS.md
  • Brief yourself on this company before we workcontext.brief · context.correct01
    Brief yourself on this company before we work. Call context.brief (use lens=handoff). Summarize the cited, current picture: what we do, what is decided, and what is still open. Treat claim_status: never present provisional or speculative claims as fact. Raise material open_questions with me rather than guessing. If a visible citation or statement is wrong, call context.correct with what you actually saw; do not require a hidden memory ID. If the brief is empty or too thin to act on, use the onboard prompt.
  • What changed this weekcontext.sync · context.brief · context.search02
    What changed this week? If we have a persisted context.sync cursor, send it unchanged. Otherwise call context.brief, then context.search for recent evidence. Summarize new facts, superseded decisions, and anything I should re-judge. Cite sources. An empty first sync page is not proof the workspace is empty.
  • Work the shared boardtask.search · task.get · task.status.set · task.post · task.mailbox.read · task.needs_you · receipt.get03
    Get caught up on assigned work with task.search and task.get. Keep the canonical ledger current with task.status.set and append-only task.post updates. Poll task.mailbox.read for human steering. If a real blocker requires judgment, set the task blocked and call task.needs_you; the request is quarantined and must not be described as already visible in Focus. Use caller-stable idempotency keys and confirm receipts with receipt.get.
  • Record this decisiondecision.search · decision.record · receipt.get04
    Record this decision in HiveBase. First call decision.search for precedent. Then call decision.record with rationale, evidence/source references, and a caller-stable idempotency_key. Confirm retryable accepted/processing receipts with receipt.get. If the write is human-held or otherwise terminal and non-retryable, stop polling, report the durable unratified proposal, and do not use it as adopted authority.
  • Correct context and hand it offcontext.search · context.brief · context.correct05
    Correct the wrong company context and verify the handoff. Call context.search or context.brief to obtain the visible citation or exact statement, then call context.correct with a stable idempotency_key and evidence. If applied, call ordinary context.search without dependency plumbing and confirm the replacement is visible. If proposed, ambiguous, or not_found, treat that result as terminal for this attempt. A second authorized agent should call context.brief or context.search and see the same committed correction under its own current authorization.

Empty workspace? Use Onboard from my AI conversations — the cold onboard prompt — then brief again.

HOW IT WORKS

One loop every agent follows

Three moves — load free context, do the work, write back with a trail. Not a different integration per app.

READ
mcp.hivebase.ai
$

Load free company context

Before any spend, the agent pulls a source-backed brief — the same packet Claude, Cursor, or Codex would get.

Always free within scope

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

THE SURFACE

What agents wire first

24 audited tools across 6 domains. Pick a job — see the call and the outcome.

Read context before work

Source-backed company context — evidence, decisions, overlapping tasks — before an agent spends credits.

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

Acme renewal · SSO dependency · board risk this week

3 sources · 1 decision · 0 credits [FREE READ]
same packet →ClaudeCursorCodexChatGPT
MCP VS API

Same product. Two entry paths.

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

Auth
MCP · AI apps
OAuth 2.1 + DCR
Platform API · services
Scoped hb_sk_* keys
Caller
MCP · AI apps
Claude, Cursor, Codex, ChatGPT, MCP hosts
Platform API · services
CI, workers, backends
Writes
MCP · AI apps
Confirmation / hold path
Platform API · services
Inline under programmatic trust
Entry
MCP · AI apps
mcp.hivebase.ai
Platform API · services
REST · @hivebase/sdk · webhooks
FAQ

Questions

What is the HiveBase MCP server?

One hosted endpoint that gives Claude Code, Cursor, Codex, ChatGPT, and other MCP hosts the same company context, scoped auth, and write confirmation — instead of a disconnected integration per app.

How do I add HiveBase to Claude Code, Cursor, or Codex?

Copy the host-specific command on this page (Claude Code: claude mcp add --transport http hivebase https://mcp.hivebase.ai). After connect, use the warm prompts: brief the company, ask what changed, or record a decision. Empty workspace? Start with the onboard-company prompt. Canonical agent instructions: https://hivebase.ai/AGENTS.md.

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 — not symmetrically. Reads are free within scope. Writes are scoped, confirmation-gated for OAuth, and carry provenance so agents can't become silent writers.

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.