Orca MCP Server

Orca MCP server exists for a simple reason — assistants are far more useful when they can act on Orca directly instead of describing what you should do. Go from natural language to verified finite state machines — topology bugs caught before code runs.

What you get

The core insight: LLMs generate flat transition tables reliably, but they struggle to guarantee topology correctness on their own. Orca separates program structure (state machine topology) from computation (action functions), then verifies the structure automatically before any code runs.

• States with [initial] / [final] markers, descriptions, on_entry / on_exit actions
• Transitions as a flat table — the format LLMs generate most reliably
• Guard expressions: comparisons, boolean logic, null checks
• Hierarchical (nested) states
• Parallel regions with all-final / any-final / custom sync strategies
• Timeouts: timeout: 30s -> state_name

Setting it up

Installation goes through your MCP client rather than a global install: point it at tsx on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

What the assistant can call

Once Orca is connected, these are the calls the assistant has available:

• submit_payment — payment_authorized
• payment_declined — retry_requested
• on_entry — send_authorization_request
• Timeouts — timeout: 30s -> state_name
• Multi — machine files: multiple machines in one .orca.md separated by ---
• Reachability — every state is reachable from the initial state
• Completeness — every (state, event) pair is handled or explicitly ignored
• Cross-machine — cycle detection, child reachability to final state, input mapping validation
• on_done — -> completed
• invoke — PaymentProcessor
• on_error — payment_failed
• timeout — 30s -> timed_out

Configuration and credentials

You will need 4 environment variables: ORCA_API_KEY, ORCA_PROVIDER, ORCA_BASE_URL, ORCA_MODEL. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Before you rely on it

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Orca.
• Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
• MCP clients confirm each tool call by default. Leave that on until you have watched what the orca mcp server does with a few real requests.

Choosing this one

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Orca's toolset — submit_payment, payment_declined, on_entry and 11 more — is a fair guide to whether it matches your workflow. It is maintained by jascal; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.