# Spedy

> Agency software for agencies that build software themselves. One board per client with its own budget, your own AI agents connected via MCP, and every hour — human or agent — on the right client.

Spedy is a multi-tenant delivery platform for software agencies and consultancies in the DACH region: client boards with monthly budgets and carryover, tickets, wiki, time tracking on the ticket, linked GitHub, GitLab and Bitbucket pull requests, free client logins, and an MCP server plus one-click ticket handoff so the AI agents a team already runs (Claude Code, Codex, Cursor, …) work with full project context. Spedy does not run agents itself. Its reference frame is agency software (MOCO, awork, Teamleader, ZEP, Productive), not developer issue trackers — it replaces the delivery side and leaves invoicing where your accounting already has it.

Deliberately out of scope: Spedy has no hourly rates, does not invoice your clients, and reports no margin or utilisation. It counts hours; the valuation stays in your invoicing software.

## Features

- [Dashboard](https://spedy.ai/features/dashboard): Focus your team on what matters now — triage, idle tickets, waiting states and unbooked work in one clear operational dashboard.
- [Kanban Boards](https://spedy.ai/features/boards): Visualize your workflow with flexible, customizable Kanban boards. Drag & drop, real-time updates, and full transparency for your team.
- [Ticket Management](https://spedy.ai/features/tickets): Everything in one place — your tickets, perfectly organized. From idea to implementation with detailed tickets, comments, time tracking and Git integration.
- [Personal Todos](https://spedy.ai/features/todos): A private todo list next to the tickets — only you see your entries; delegate to a team member with a reminder at the right time (delegation from Starter).
- [Wiki & Docs](https://spedy.ai/features/wiki): Share knowledge, maintain documentation. Central knowledge base with hierarchies, versioning and granular permissions; readable and writable over MCP.
- [Teams & Roles](https://spedy.ai/features/teams): Effectively organize and authorize teams. Invite team members, organize them in teams and grant exactly the permissions they need.
- [Integrations](https://spedy.ai/features/integrations): Connect your tools seamlessly. GitHub, GitLab, Bitbucket, Jira, YouTrack, MOCO and more — native integrations and an open API.
- [Time Tracking](https://spedy.ai/features/time-tracking): Precise time tracking right in the ticket. Start the timer with one click, track work time and export for billing. Time an agent books over MCP lands as a draft for human approval.
- [Releases & Milestones](https://spedy.ai/features/releases): From idea to release — structured planning. Organize your backlog, set milestones and plan releases with full progress tracking.
- [Ticket Transparency (Explainability)](https://spedy.ai/features/explainability): Understand why, not just what. Deterministic explainability: Spedy shows why a ticket is blocked, what it waits on and why a status is suggested — from recorded events and dependencies, not from an AI assistant.
- [Project Pulse](https://spedy.ai/features/pulse): Real-time insights into project health, team velocity and potential risks.
- [Real-time Workload](https://spedy.ai/features/workload): See who is working on what, in real time. Live view of your entire team workload — active timers, assigned tickets, and blocked work at a glance.
- [AI Knowledge Base](https://spedy.ai/features/ai-knowledge): Persistent memory for the agents you run — solutions, preferences and patterns are stored and recalled over MCP.
- [Agent loops (your own agents)](https://spedy.ai/features/agents): Spedy runs no agents. Your own — Claude Code, Codex, Cursor, any MCP client — pull tickets over MCP: seat-free agent users with an owner, scoped tokens (allowedBoardIds, readOnly, denyDelete, clientLabel), exclusive expiring ticket claims, one tickets_report call to finish (comment, PR link, status, timer, release), a delivery trace per ticket, agent policies (status moves that need human approval, PRs flagged for human review), an agents overview and wiki writes over MCP. Webhook `ticket.assigned` wakes a loop. Agent users are a Pro feature.
- [MCP Server](https://spedy.ai/features/mcp): Spedy's own MCP server — 52 tools in 14 namespaces for tickets, boards, wiki, knowledge, pull requests, pipelines, time tracking and work context. For the agent you already use (Claude Code, Codex, Cursor, Claude Desktop). On every plan including Free with your personal token; seat-free agent users from Pro.
- [Handoff to AI tools](https://spedy.ai/features/ai-handoff): Open a ticket in your own coding tool with one click — full ticket context as the prompt, the agent reports back to the ticket via MCP.
- [Pull Requests](https://spedy.ai/features/pull-requests): GitHub, GitLab and Bitbucket pull requests linked to tickets, status moves with the PR.
- [Pipelines](https://spedy.ai/features/pipelines): CI runs from GitHub Actions, GitLab CI and Bitbucket in one dashboard across repositories.
- [GitLab](https://spedy.ai/features/gitlab): gitlab.com or your own self-hosted instance: merge requests and pipelines on the ticket, subgroup paths supported.
- [Automations](https://spedy.ai/features/automations): Rule-based workflows on ticket events (Pro).
- [Public Forms](https://spedy.ai/features/public-forms): Branded public intake forms that create tickets on a board, embeddable on your own site (Pro).

## MCP tools (52 tools, 14 namespaces)

- **Tickets** (21): `tickets_list`, `tickets_search`, `tickets_get`, `tickets_create`, `tickets_update`, `tickets_move_status`, `tickets_resolve`, `tickets_add_comment`, `tickets_set_custom_fields`, `tickets_claim`, `tickets_heartbeat`, `tickets_release`, `tickets_report`, `tickets_delivery_trace`, `tickets_list_links`, `tickets_create_link`, `tickets_delete_link`, `tickets_list_subtickets`, `tickets_create_subticket`, `tickets_convert_to_subticket`, `tickets_promote_to_standalone`
- **Boards** (2): `boards_list`, `boards_get`
- **Statuses** (1): `statuses_list`
- **Labels** (1): `labels_list`
- **Milestones** (1): `milestones_list`
- **Custom fields** (1): `custom_fields_list`
- **Time tracking** (4): `timers_start`, `timers_stop`, `timers_stopAll`, `timers_list`
- **Knowledge base** (6): `knowledge_recall`, `knowledge_search`, `knowledge_store`, `knowledge_update`, `knowledge_list`, `knowledge_delete`
- **Wiki** (7): `wiki_spaces_list`, `wiki_spaces_get`, `wiki_pages_list`, `wiki_pages_get`, `wiki_search`, `wiki_pages_create`, `wiki_pages_update`
- **Pull requests** (2): `pull_requests_list`, `pull_requests_get`
- **Pipelines** (1): `pipelines_list`
- **Users** (1): `users_me`
- **Work context** (3): `work-context_get`, `work-context_board-health`, `work-context_ticket-explanation`
- **Context search** (1): `context_search`

Endpoint: `https://<org>.spedy.ai/api/v1/mcp` (streamable HTTP). Auth: OAuth 2.0 with PKCE and Dynamic Client Registration, or a personal access token. Server card: https://spedy.ai/.well-known/mcp/server-card.json

## Pricing

- **Free**: 0 €/forever — 1 user, 2 GB storage, boards, tickets, wiki, personal todos, Git integration, MCP access for your own agents with your personal token. A single seat: enough to look around, not enough to run an agency on.
- **Starter**: 5 €/user/month (net, excl. VAT) — up to 5 users, 10 GB storage, everything in Free plus multiple users, teams and todo delegation.
- **Pro**: 9 €/user/month (net, excl. VAT) — unlimited users, 50 GB storage, everything in Starter plus unlimited users, automations, webhooks, API access, public forms, AI knowledge base and seat-free agent users (machine users with scoped tokens, ticket claims, run reports, delivery trace, agent policies). Ten people cost 90 €/month.
- **Business**: 19 €/user/month (net, excl. VAT) — unlimited users, 250 GB storage, everything in Pro plus custom permission groups, OAuth apps and priority support.

Client logins (external stakeholders) are unlimited and free on every plan. Storage is per organisation on the local filesystem of the hosting server; plan limits above are hard caps.

Spedy does not run AI agents. Teams bring their own agent (Claude Code, Codex, Cursor, any MCP client) with their own key and connect it via MCP — on every plan including Free, with a human's own personal access token or OAuth. Seat-free **agent users** (machine users with an owner and scoped tokens, ticket claims, run reports, delivery trace, agent policies, agents overview, wiki write over MCP) are a Pro feature. LLM costs are paid to the agent's provider directly, not to Spedy.

## Who it is for

- **Software agencies and consultancies** (primary): 10–50 people, own developers and own repos, 5–15 client projects in parallel, delivery bottlenecked on two or three seniors
- **Product teams**: building their own product rather than client work
- **In-house dev teams**: with compliance requirements — SSO, audit log export, on-premise

## Links

- [Homepage](https://spedy.ai)
- [Agent loops](https://spedy.ai/features/agents)
- [Developer portal](https://spedy.ai/developers)
- [For software agencies](https://spedy.ai/fuer/software-agenturen)
- [For product teams](https://spedy.ai/fuer/produktteams)
- [For in-house dev teams](https://spedy.ai/fuer/in-house-dev-teams)
- [Pricing](https://spedy.ai/pricing)
- [ROI calculator](https://spedy.ai/en/roi-calculator)
- [Comparisons](https://spedy.ai/en/compare)
- [Docs: agent loops](https://docs.spedy.ai/docs/features/agent-loops)
- [Docs: reference loop](https://docs.spedy.ai/docs/features/agent-loop-example)
- [Terms & Conditions](https://spedy.ai/terms)
- [Privacy Policy](https://spedy.ai/privacy)
- [Imprint](https://spedy.ai/imprint)
- [Full llms.txt](https://spedy.ai/llms-full.txt)