Connect Claude (Claude Code) to betool through the MCP server to read your configuration and propose changes in natural language — governed, with human validation.

Drive betool from Claude (MCP server)

betool exposes an MCP server (Model Context Protocol): an external MCP client — typically Claude Code — can read your organisation's configuration and propose changes in natural language (create/edit a pipeline, a role, a mission, an evaluation…). It is like an assistant configuring betool with you, fully governed.

Propose, never apply directly. Every change goes through a proposal that you approve with an Accept button inside betool. Claude can apply nothing on its own. Safer than a tool that writes directly.

What Claude can do

Read: model inventory, a pipeline's graph and nodes, node configuration contracts, roles/missions, available tools, knowledge base.
Propose: via the proposals.create tool, a pending change proposal — you accept or reject it in the UI.

Claude discovers each node's exact contract (fields, allowed values) before proposing: no guessing, no invalid configuration.

Create an MCP key

In betool, open Settings → MCP.
Name the key and pick its scope:
- Read only — Claude reads configuration, proposes nothing;
- Read + proposals (recommended) — Claude reads and can submit proposals;
- Full — the full rights of the key.
The raw key is shown only once — copy it immediately (it can never be read again). You can revoke a key at any time.

Connect Claude Code

Add the betool MCP server to Claude Code (the key goes in the Authorization header):

claude mcp add betool \
  --transport http \
  --header "Authorization: Bearer <your-mcp-key>" \
  https://platform.betool.ai/mcp

Then ask Claude, in natural language: "inspect my pipeline X and propose a step that summarises the ticket before sending". Claude reads the configuration, composes a proposal, and you validate it in betool.

Never paste secrets in clear text in the chat. Claude's reach is bounded by the key scope, and every tool call is logged under Settings → MCP → log (GDPR art. 15).

Scope & isolation

By default a key operates only on your own organisation — the target org is forced server-side; you never pass an organisation id as an argument.
Vendor keys (backoffice organisation) may target another organisation, under that org's explicit consent and with full audit — useful for a multi-tenant vendor use case.

Audit log

Every tool call (external via MCP and internal) writes an audit line: who, which tool, which channel, which scope, outcome, latency. Available under Settings → MCP, strictly scoped to your organisation.

Coming soon

Claude Desktop via OAuth 2.1 (consumer-grade connection without handling a header key).
Fine-grained, per-tool control of the MCP-exposed surface.

Drive betool from Claude (MCP)