Skip to content
Integrations

MCP servers, AI backends,
and deep integrations.

MCP servers, skill snippets, and AI backends. Plug in the tools your team already uses with one-click installs.

AI Models

Opus.Sonnet.Haiku.

  • Built for Claude Code. CLI and API backends with full model selection.
  • Assign Opus for complex reasoning, Sonnet for general tasks, Haiku for speed.
  • More providers coming: ChatGPT, Llama, Grok, and others on the roadmap.
MCP Servers

The tools your team already uses.

One-click install from GitHub, Slack, Linear, Sentry, PostgreSQL, and dozens more. Category filtering, instant search, and per-preset recommendations.

  • One-click install from the official MCP registry
  • Per-preset recommendations surface the right servers
  • Category filtering and instant search across 100+ servers
  • Each server exposes typed tools agents can call directly
MCP Servers12 servers
Search servers...
AllDevDataCommsCloud
GitHub23Developer
Repos, PRs, issues, actions
Active
Filesystem15
Read, write, search, watch files
Active
PostgreSQL15
Queries, schemas, migrations
Active
Slack12PM
Channels, threads, notifications
Active
Brave Search8
Web search, news, images
Active
Playwright19
Browser automation, testing, scraping
Install
Linear14PM
Issues, projects, cycles, teams
Install
Notion16
Pages, databases, search
Install
Sentry18
Errors, performance, alerts
Install
Docker11
Containers, images, compose
Install
Supabase20
Database, auth, storage, edge functions
Install
Stripe17
Payments, subscriptions, invoices
Install
GitHub tools
create_pull_request()list_issues()get_repo()
Customisation

Fully customisable, every layer.

Presets, project rules, hooks, skills, cost gates, and approval flows. Every aspect of agent behaviour is configurable to suit your team's workflow.

  • Agent presets with curated tool sets, models, and system prompts
  • Project-level CLAUDE.md rules injected into every session
  • Lifecycle hooks for pre-commit checks, test runs, and deploys
  • Custom slash commands, skills, cost alerts, and approval gates
  • All fully customisable per agent, per project, or globally
Customisation7 configs
Developerpreset
preset
Project Rulesinstructions
CLAUDE.md
Pre-commithook
hook
Code Reviewskill
skill
Deploy Gateautomation
gate
Test Runnerskill
skill
Cost Alertsautomation
gate
Developerpreset
Full-stack agent with 6 MCP servers and project-aware tooling.
1---
2name: Developer
3model: claude-sonnet-4-5
4permission: full_access
5autonomy: semi_auto
6colour: #a78bfa
7max_turns: 200
8cost_limit: $5.00
9---
10 
11## MCP Servers
12GitHub, Filesystem, Playwright,
13Brave Search, PostgreSQL, Sentry
14 
15## System Prompt
16You are a senior full-stack developer
17working on an Electron + React app.
18Always run vitest before committing.
19Use the project lint config. Never push
20directly to main without a PR. Check
21for regressions in adjacent modules.
22 
23## Hooks
24pre_commit: lint + typecheck + test
25on_error: pause and notify operator
26on_idle: check pending relay messages
27on_cost_limit: warn then pause at 120%
28 
29## Allowed Paths
30src/**, tests/**, package.json
31# Deny: .env*, secrets/*, *.pem
AI Backends

CLI or API. Switch in seconds.

Toggle between the Claude CLI and direct API access with a single click. All agents switch seamlessly, conversations preserved.

  • CLI backend: local sessions via Claude Code with CLI-managed permissions
  • API backend: direct Anthropic API with streaming and exact cost tracking
  • Per-agent model overrides: assign Opus, Sonnet, or Haiku individually
Backend Activity3 agents
DevCLIOpus 4.6
PMAPISonnet 4.5
QACLIHaiku 4.5
Live Activity
CLI~120ms|API~85ms|3 models|$0.054