Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Orca MCP Server

NPM · @ORCALANG/ORCA-MCP-SERVER · SCANNED SEP 20

Go from natural language to verified finite state machines — topology bugs caught before code runs.

0 this week 85 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 31 of 100 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability87
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 1597 tokens (~106/item across 15 items; 12 tools + 3 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management90
  • Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the Orca MCP Server server?

Orca MCP Server runs locally as an npm package, launched with npx -y @orcalang/orca-mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @orcalang/orca-mcp-server

# add to Claude Code
claude mcp add jascal-orca-mcp-server -- npx -y @orcalang/orca-mcp-server
// .cursor/mcp.json
{
  "mcpServers": {
    "jascal-orca-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@orcalang/orca-mcp-server"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "jascal-orca-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@orcalang/orca-mcp-server"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add jascal-orca-mcp-server -- npx -y @orcalang/orca-mcp-server
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "jascal-orca-mcp-server": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@orcalang/orca-mcp-server"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add jascal-orca-mcp-server --command npx --arg -y --arg @orcalang/orca-mcp-server
# ~/.hermes/config.yaml
mcp_servers:
  jascal-orca-mcp-server:
    command: "npx"
    args: ["-y", "@orcalang/orca-mcp-server"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "jascal-orca-mcp-server": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@orcalang/orca-mcp-server"
      ]
    }
  }
}
# add to Vellum
assistant mcp add jascal-orca-mcp-server -t stdio -c npx -a -y @orcalang/orca-mcp-server
// mcp.json
{
  "mcpServers": {
    "jascal-orca-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@orcalang/orca-mcp-server"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 16 Sept 26 0
    • Stability: 0.97 → pass security
  • 15 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Sept 26 −3
    • Stability: pass → 0.80 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed npm/@orcalang/orca-mcp-server@0.1.30

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 100 packages
Packages resolved 100
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 12 exposed · ~988 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
compile_decision_table ~70

Compile verified decision table to TypeScript, Python, Go, or Rust evaluator function, or portable JSON. Run verify_decision_table first.

NameTypeReqDescription
sourcestringyesRaw .orca.md content containing a # decision_table heading.
targetstringCompilation target (default: typescript)

No output schema declared.

No examples provided.

compile_machine ~108

Compile verified machine to XState v5 TypeScript or Mermaid stateDiagram-v2. Run verify_machine first. target: "xstate" (default) or "mermaid".

NameTypeReqDescription
sourcestringyesRaw .orca.md content. Must start with "# machine Name". States use "## state Name [initial|final]". Transitions use a markdown table with columns: Source, Event, Guard, Target, Action.
targetstringCompilation target (default: xstate)

No output schema declared.

No examples provided.

generate_actions ~148

Generate action scaffold code from verified machine. lang: typescript (default), python, go, or rust. Pass verified .orca.md source. use_llm: true for implementations vs templates. generate_tests: true for test scaffolds.

NameTypeReqDescription
generate_testsbooleanInclude test scaffolds in the output (default: false)
langstringTarget language (default: typescript)
sourcestringyesRaw .orca.md content of a valid machine. Actions in the "## actions" table (| Name | Signature |) will have stubs generated.
use_llmbooleanUse LLM to generate implementations instead of templates (default: false)

No output schema declared.

No examples provided.

generate_decision_table ~52

Generate a decision table in .orca.md format from a natural language spec. Always verify_decision_table next. Requires LLM API key.

NameTypeReqDescription
specstringyesNatural language description of the decision logic

No output schema declared.

No examples provided.

generate_machine ~66

Generate draft .orca.md from natural language spec. Returns source + is_multi flag. Always verify_machine next, then refine_machine if errors. Requires LLM API key (ANTHROPIC_API_KEY, etc.).

NameTypeReqDescription
specstringyesNatural language description of the desired state machine

No output schema declared.

No examples provided.

generate_multi_machine ~65

Generate coordinated multi-machine .orca.md from spec (machines separated by ---). Use invoke: ChildMachine in states. Always verify_machine next, then refine_machine if errors. Requires LLM API key.

NameTypeReqDescription
specstringyesNatural language description of the desired multi-machine system

No output schema declared.

No examples provided.

parse_decision_table ~76

Parse decision table from .orca.md source → JSON (conditions, actions, rules). Syntax: # decision_table Name, ## conditions table, ## actions table, ## rules table. Can be standalone or combined with machines in the same file.

NameTypeReqDescription
sourcestringyesRaw .orca.md content containing a # decision_table heading.

No output schema declared.

No examples provided.

parse_machine ~108

Parse .orca.md source → JSON (states, events, transitions, guards, actions, context). Syntax: # machine Name, ## state Name [initial|final], ## transitions table (| Source | Event | Guard | Target | Action |).

NameTypeReqDescription
sourcestringyesRaw .orca.md content. Must start with "# machine Name". States use "## state Name [initial|final]". Transitions use a markdown table with columns: Source, Event, Guard, Target, Action.

No output schema declared.

No examples provided.

refine_machine ~108

Fix verify_machine errors using LLM. Loops until valid or max_iterations (default: 3). Pass errors array from verify_machine output, or omit to auto-verify first.

NameTypeReqDescription
errorsarrayVerification errors from verify_machine. If omitted, verification runs automatically.
max_iterationsnumberMaximum refinement iterations (default: 3)
sourcestringyesRaw .orca.md content with errors. Must use "# machine Name" heading and proper Orca markdown syntax.

No output schema declared.

No examples provided.

server_status ~35

Return MCP server version, active LLM provider/model, and configuration. API keys are never exposed — only whether a key is configured.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

verify_decision_table ~56

Verify decision table: checks completeness (all condition combinations covered), consistency (no contradictory rules), redundancy. Returns structured errors with codes and suggestions.

NameTypeReqDescription
sourcestringyesRaw .orca.md content containing a # decision_table heading.

No output schema declared.

No examples provided.

verify_machine ~96

Verify machine structure: checks [initial] presence (exactly one), reachability, no deadlocks, guard determinism. Returns structured errors with codes and suggestions. Run before compile_machine.

NameTypeReqDescription
sourcestringyesRaw .orca.md content. Must start with "# machine Name". States use "## state Name [initial|final]". Transitions use a markdown table with columns: Source, Event, Guard, Target, Action.

No output schema declared.

No examples provided.

Common questions

What is the Orca MCP Server server?

Orca MCP Server is listed in the public MCP registry as io.github.jascal/orca-mcp-server. Go from natural language to verified finite state machines, topology bugs caught before code runs. This page covers its npm package (@orcalang/orca-mcp-server).

Is the Orca MCP Server server safe to use?

Orca MCP Server scores 85 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Orca MCP Server server expose?

Orca MCP Server exposes 12 tools: parse_machine, verify_machine, compile_machine, generate_machine, generate_actions, and 7 more. Their descriptions and schemas cost roughly 988 tokens of context every time the server is loaded.

Is the Orca MCP Server server still maintained?

Orca MCP Server is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Orca MCP Server server under?

Orca MCP Server declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.