Turns a Frappe site into a remote MCP server that AI clients such as Claude can sign in to with OAuth and use curated, task-level tools registered by installed apps. Every call runs as the signed-in user with that user's permissions, with schema-checked arguments and rollback on failure.

Enables querying a Chatwoot support inbox in plain language—finding conversations, contacts, and conversations needing attention—and, after explicit confirmation, adding private notes or updating assignments, labels, and status without sending customer messages.

Enables plain-language queries about a support desk, ticket and customer investigation, and safe, confirmation-gated ticket assignment and internal notes.

Enables natural-language querying of GLPI IT helpdesk and asset data—tickets, ownership, deadlines, and person-held assets—plus safe follow-up additions and ticket updates that require one-time confirmation before changes are applied.

Enables coding agents to index repositories, retrieve task-relevant code within a token budget, and record facts that are flagged stale when their anchored code changes.

Enables MCP-compatible AI clients to search and view CRM customers, deals, contracts, tasks, calendars, and outbound jobs, and to propose opt-in write actions that require human approval in the CRM.

Enables AI coding agents to automatically compress context at agent-judged task boundaries, write incremental structured session snapshots, and maintain per-fact long-term memory for priority restoration across sessions.

Enables Claude to answer business questions against a company's retail database — sales summaries, top customers, inventory alerts, customer profiles, and plain-English queries — through read-only SQL tools plus a schema resource and reporting prompt. Access is governed by OAuth 2.1 roles and scopes, column-level PII masking, a SQL guard, rate limits, and audit logging.

Self-hosted daemon connecting Claude Code, Codex, and other coding agents across machines via MCP + A2A: delegate tasks, ask questions, share results, and wake sessions.

Publishes a weather MCP server that layers governance onto a working baseline: JWT scope checks on tools, logging with redaction, background tasks with progress and elicitation, and search/code-mode views of the same server. It also supports an in-process proxy provider and a packaged skill for agent-side discovery.

Task tracker for product teams: projects, features, tasks, bugs, team chats and code context.

Your LeapSteps to-do list, goals and focus timer: plan the day, add tasks and move goals forward.

Expense ledger for AI assistants: record receipts line by line, ask what you spent, export anytime.

Run AI agent tasks in isolated sandboxes with a cost cap, saved workflows and scoped connections.

The CRM your AI agent works in: companies, people, deals, tasks and buying signals, signed.

Fortnox MCP server: ask ChatGPT, Claude, Grok or Gemini about your books. You approve every change.

B2B leads at a buying moment, with the why and the outreach. Ask your AI about your leads.

Shared memory for your AI tools: tasks, notes and context every tool can read and write over MCP.

Ask your AI about your Brazilian bank spending. Requires a paid Mofi plan. Read-only bank link.

Find and live-check the paid x402 API for an agent task, ranked by real 30-day payers and price.

A shared message board and task list for coding agents that cannot talk to each other.

Connect AI agents to your own Chrome with scoped access, approvals, and verified task results.

Connect your AI to your own devices, 3D printers, factory tools and a shared agent task pool.

Cloud Android phones for AI agents: tap, type, screenshot, install APKs, run plain-English tasks.