OPA MCP Server

A Model Context Protocol (MCP) server that turns any MCP-compatible client (Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and others) into a first-class Open Policy Agent and Rego authoring environment.

+--------------------+ MCP/stdio  +-----------------+ spawn/HTTP +---------------------+
|  Claude · Cursor · |----------> | @orygn/opa-mcp  |----------> | opa · regal         |
|   VS Code · ...    |<---------- |                 |<---------- | conftest · REST API  |
+--------------------+  52 tools  +-----------------+            +---------------------+

Status: v0.2.0. Tool surface, error codes, and environment variables follow SemVer from v0.1.0 forward.

Table of contents

• What you can do with it
• Why this MCP
• Install
• Configuration
• Tool reference
• Prompts
• Resources
• Cookbook
• Architecture
• Security
• Troubleshooting
• Development
• Versioning & support
• License

What you can do with it

Once an MCP client is connected, an agent can:

• Author Rego. Generate, format, and refactor policies. The server

runs the real opa fmt and opa parse so output is byte-identical to what you'd get on the command line, and regal (optional) surfaces idiomatic suggestions.

• Evaluate against data. Run a query against a policy and an input

document. Optional --explain, --profile, and --coverage flags surface execution traces, hot rules, and per-line coverage.

• Debug a deny. rego_explain_decision walks the agent through every

rule that fired (and every one that didn't), so it can answer "why was this rejected" without you reading the trace by hand.

• Manage policies on a running OPA. List, get, put, delete policies on

an OPA server through its REST API. Works against a local opa run --server or a production deployment with bearer-token auth.

• Build & sign bundles. Package a directory of policies into a

deployable bundle, optionally signing it. Output is a regular .tar.gz the agent can hand to your delivery system.

• Lint. rego_lint runs Regal across a directory or a single file

and returns categorized findings (style, bugs, performance, idioms).

A walk-through of a typical session lives in Cookbook.

Why this MCP

OPA already has a perfectly good CLI and REST API. So why an MCP wrapper?

• Schema-shaped tool surface. An agent calling rego_eval gets a

validated input schema, a structured output envelope, and stable error codes, instead of parsing free-form CLI text and inventing its own failure taxonomy. That alone makes Rego usable to an agent the way a language server makes a language usable to an IDE.

• Higher-level helpers. rego_explain_decision,

rego_generate_test_skeleton, rego_describe_policy, and rego_suggest_fix compose the lower-level primitives into the tasks agents are actually asked to do. They don't exist in the OPA CLI.

• Curated knowledge. The bundled MCP resources expose the OPA

built-in function catalog, the official Rego style guide (formatted for LLMs), and a curated pattern library covering RBAC, ABAC, Kubernetes admission, IaC gates, API authz, and rate limiting, so the agent has authoritative context without needing to scrape it.

• Safety boundaries the agent can rely on. Path allow-list,

subprocess timeouts, and response-size caps. Defaults are conservative; running the server doesn't quietly grant the agent more reach than the operator intended.

If you've ever watched an agent fight opa eval's argument order, you'll recognize the gap this fills.

Install

The server runs locally over stdio. Pick the install path that matches your client.

Claude Desktop

Edit claude_desktop_config.json directly (or copy from examples/claude-desktop.json):

{
  "mcpServers": {
    "opa": {
      "command": "npx",
      "args": ["-y", "@orygn/opa-mcp"],
      "env": {
        "OPA_BINARY": "/usr/local/bin/opa",
        "REGAL_BINARY": "/usr/local/bin/regal",
        "OPA_URL": "http://localhost:8181",
        "OPA_MCP_ALLOWED_PATHS": "/path/to/your/policies"
      }
    }
  }
}

Replace the /usr/local/bin/... paths with your real ones. See the first-time install gotcha below. Windows users substitute C:\\path\\to\\opa.exe.

Or download opa-mcp.mcpb from the latest release and double-click it.

Alternatively, use the Smithery one-liner:

npx -y @smithery/cli install @orygn/opa-mcp --client claude

Claude Code (CLI)

Register the server for the current project with claude mcp add:

claude mcp add \
  --env OPA_BINARY=/usr/local/bin/opa \
  --env REGAL_BINARY=/usr/local/bin/regal \
  --env OPA_MCP_ALLOWED_PATHS=/path/to/your/policies \
  opa -- npx -y @orygn/opa-mcp

This writes the config into .mcp.json at your project root and is picked up automatically on every claude session in that directory. Add --scope user to register it globally instead.

Replace the paths with your real absolute paths (same caveat as Claude Desktop above). On Windows use C:\path\to\opa.exe syntax.

Persistent context and auto-checks for policy repos. If you work in an OPA policy repo regularly, two extra files remove repetitive setup from every session:

• examples/CLAUDE.md -- copy to your repo

root or .claude/CLAUDE.md. Claude Code loads it every session, so the agent always knows which tools to use and what conventions apply.

• examples/claude-code-hook.json --

merge the hooks block into .claude/settings.json. Runs opa check automatically after any .rego file is written, so syntax errors surface immediately without a manual tool call.

Cursor

Drop examples/cursor.json into either .cursor/mcp.json (project-scoped) or ~/.cursor/mcp.json (user-scoped).

VS Code (GitHub Copilot Chat)

Drop examples/vscode.json into .vscode/mcp.json, or paste the servers block into your user settings.json under mcp.servers.

Windsurf, Zed, and others

See examples/ for a full set of drop-in configs.

Manual install (any MCP client)

npm install -g @orygn/opa-mcp
opa-mcp --version

then point your client at the opa-mcp binary.

Docker

docker pull orygn/opa-mcp:latest
docker run --rm -i \
  -v /path/to/your/policies:/policies:ro \
  -e OPA_MCP_ALLOWED_PATHS=/policies \
  orygn/opa-mcp

The image is multi-arch (linux/amd64, linux/arm64), bundles pinned versions of opa and regal, and runs as a non-root user. No host install of OPA or Regal is required.

⚠ First-time install gotcha (read this if you used npx or the global install)

If your client's PATH doesn't include the directory where opa lives (this happens with Claude Desktop on Windows and macOS by default), the server boots fine but every tool call returns OPA_BINARY_NOT_FOUND.

Fix: add OPA_BINARY and REGAL_BINARY env entries to your client config with the absolute path to each binary. The example configs under examples/ ship with placeholder paths you replace. Find the real paths with:

which opa && which regal                                    # macOS / Linux

Get-Command opa, regal | Select-Object Source              # Windows

This does not affect the Docker or MCPB install paths; those ship opa and regal inside the bundle and bypass PATH entirely. See Troubleshooting for full detail.

Configuration

The server reads its configuration from environment variables. Every variable is optional; defaults are sensible for a local OPA on http://localhost:8181.

Paths in OPA_MCP_ALLOWED_PATHS and the *_BINARY variables must be absolute. Relative paths and missing binaries are rejected with structured errors.

Tool reference

Every tool returns a JSON envelope:

{ "ok": true, "data": { ... }, "warnings": [ ... ] }
{ "ok": false, "error": { "code": "INVALID_REGO", "message": "...", "hint": "...", "details": { ... } } }

Stable error codes: INVALID_INPUT, INVALID_REGO, INVALID_BUNDLE, EVAL_ERROR, OPA_BINARY_NOT_FOUND, REGAL_NOT_FOUND, REGAL_VERSION_TOO_OLD, CONFTEST_NOT_FOUND, OPA_UNREACHABLE, OPA_AUTH_FAILED, POLICY_NOT_FOUND, DATA_NOT_FOUND, PATH_NOT_ALLOWED, PATH_NOT_FOUND, DEPENDENCY_CONFLICT, NO_TESTS_FOUND, COVERAGE_BELOW_THRESHOLD, OPA_VERSION_UNSUPPORTED, VERIFY_INCONCLUSIVE, Z3_INIT_ERROR, GITHUB_TOKEN_MISSING, GIST_CREATE_FAILED, TIMEOUT, CANCELLED, UNKNOWN_ERROR.

Category A: Authoring & static analysis

Operate on Rego source code without needing a running OPA server. Wrap opa fmt, opa parse, opa check, opa inspect, opa capabilities, opa deps, and regal.

#### Featured: rego_format

// Input
{
  "source": "package x\nallow{input.user==\"admin\"}"
}

// Output (ok)
{
  "ok": true,
  "data": {
    "formatted": "package x\n\nallow if input.user == \"admin\"\n",
    "changed": true
  }
}

#### Featured: rego_check

// Input
{
  "source": "package x\nallow if y",
  "strict": true
}

// Output (error path; the JSON diagnostics arrive on stderr from opa)
{
  "ok": true,
  "data": {
    "valid": false,
    "errors": [
      {
        "code": "rego_unsafe_var_error",
        "message": "var y is unsafe",
        "location": { "row": 2, "col": 11 }
      }
    ]
  }
}

Category B: Evaluation & testing

Run a query against a policy and input. Wrap opa eval, opa test, and opa bench.

#### Featured: rego_eval

// Input
{
  "query": "data.rbac.allow",
  "source": "package rbac\nimport rego.v1\nallow if input.role == \"admin\"",
  "input": { "role": "admin" }
}

// Output
{
  "ok": true,
  "data": {
    "result": [{ "expressions": [{ "value": true, "text": "data.rbac.allow", "location": { "row": 1, "col": 1 } }] }]
  }
}

Category C: Bundle operations

Package and sign deployable bundles. Wrap opa build and opa sign.

Category D: OPA server management

Talk to a running OPA server over its REST API. Require OPA_URL to point at a reachable server.

Category E: Higher-level helpers

The differentiation surface. These compose lower-level primitives into the tasks agents are actually asked to do.

Category F: Conftest (configuration policy testing)

Test Kubernetes manifests, Terraform plans, Dockerfiles, Helm charts, and any YAML/JSON/HCL/TOML/INI against Rego policies using conftest. Requires conftest on PATH or CONFTEST_BINARY set; all four tools return CONFTEST_NOT_FOUND otherwise.

#### Featured: conftest_test with inline config

// Input
{
  "inlineConfig": "apiVersion: v1\nkind: Pod\nspec:\n  containers:\n  - name: app\n    image: nginx:latest",
  "inlinePolicy": "package main\ndeny[msg] { input.spec.containers[_].image == \"nginx:latest\"; msg := \"pin your image tag\" }"
}

// Output
{
  "ok": true,
  "data": {
    "passed": false,
    "results": [
      {
        "filename": "<inline>",
        "namespace": "main",
        "successes": 0,
        "failures": [{ "msg": "pin your image tag" }],
        "warnings": [],
        "skipped": [],
        "exceptions": []
      }
    ],
    "summary": { "passed": 0, "failed": 1, "warnings": 0, "skipped": 0 }
  }
}

Category G: Meta

Prompts

Three MCP prompts ship with the server. Clients surface them as slash commands or workflow templates.

Resources

Three MCP resources expose curated reference data the agent can read at any time.

Cookbook

A few session shapes that the tool set was designed for.

"Help me write a policy"

You: I need an authz policy: editors can read/write, viewers can only read,
     admins can do anything.

Agent: I'll draft it. (calls rego_format on a draft, then rego_check, then
       rego_lint)

Agent: Here's the policy. I've also generated a test file with cases for
       each role. (calls rego_generate_test_skeleton, then rego_test)

Agent: All 9 tests pass. Want me to save it to <path>?

"Why was this denied?"

You: This API call is being denied and I don't know why.
     [pastes input.json]

Agent: (calls rego_explain_decision against your local policy with that input)

Agent: The deny comes from rule `forbid_anonymous_writes` at line 17.
       Specifically, `input.user` is null and the request method is "POST".
       The rule fires, which causes the default deny. To allow this, you'd
       need either an authenticated user or a policy exception for this
       endpoint.

"Push this policy to staging OPA"

You: Push policies/rbac.rego to the staging OPA server, but first lint and
     test it.

Agent: (rego_lint → 2 style warnings, no errors)
       (rego_test on policies/ → all pass)
       (opa_put_policy with id="rbac" against $OPA_URL)
       (opa_get_policy to verify)

Agent: Done. Policy `rbac` is live on staging at $OPA_URL.

Architecture

┌──────────────────────────────────── @orygn/opa-mcp ───────────────────────────────────┐
│                                                                                       │
│   src/server.ts ──── McpServer (stdio) ─── tool / prompt / resource registries        │
│                          │                                                            │
│                          ├── tools/authoring/         ─┐                              │
│                          ├── tools/evaluation/        ─┤                              │
│                          ├── tools/bundles/           ─┼─── lib/opa-cli.ts ──┐        │
│                          ├── tools/server-management/ ─┤                     │        │
│                          ├── tools/helpers/           ─┤                     │        │
│                          ├── tools/meta/              ─┘                     │        │
│                          │                                                   ▼        │
│                          │                              lib/subprocess.ts ──┴── opa   │
│                          │                              lib/regal-cli.ts   ───── regal│
│                          │                              lib/opa-client.ts  ───── HTTP │
│                          │                                                            │
│                          └── lib/output.ts (envelope + truncation)                    │
│                              lib/security.ts (path allow-list)                        │
│                              lib/errors.ts (structured failures)                      │
│                              lib/logger.ts (file-only, never stdout)                  │
└───────────────────────────────────────────────────────────────────────────────────────┘

Three things worth knowing if you're going to operate this:

1. stdout is the protocol channel. The server logs to a file via

lib/logger.ts and never writes to stdout. If you see stray stdout bytes, the client disconnects; the MCP transport layer is strict.

1. No tool throws. Every tool catches its own exceptions and returns

a structured { ok: false, error: ... } envelope. The agent sees a stable error vocabulary, not a stack trace.

1. Subprocesses are tightly bounded. lib/subprocess.ts runs opa

and regal with shell: false, a hard timeout, and SIGTERM-then- SIGKILL escalation. There is no path through the server where an agent can construct a shell command.

Security

This server is designed to run locally, started by an MCP client on the user's own machine, communicating over stdio. It is not designed to be exposed on the network.

• File-based tools refuse to read anything outside OPA_MCP_ALLOWED_PATHS.

When that variable is unset, file tools return PATH_NOT_ALLOWED.

• Subprocesses run with shell: false and a hard timeout.
• OPA_TOKEN is never echoed in tool responses or log entries.
• Releases are published with

npm provenance; the Docker image is built reproducibly from the committed Dockerfile.

To report a vulnerability, follow SECURITY.md. Please do not open a public issue for security problems.

Troubleshooting

Common issues, fast fixes.

`OPA_BINARY_NOT_FOUND` even though `opa` is installed. _(most common first-day issue, read this first)_

MCP clients (notably Claude Desktop on Windows and macOS) launch the server with a deliberately reduced PATH that omits user-local bin directories, even ones that work fine in your interactive shell. The binary is on your machine; the spawned MCP server just can't see it.

Find the absolute path to opa:

# macOS / Linux
which opa
# → /usr/local/bin/opa  (or /opt/homebrew/bin/opa, or ~/.local/bin/opa)

# Windows
Get-Command opa | Select-Object -ExpandProperty Source
# → C:\Users\you\bin\opa.exe  (or wherever)

Then set OPA_BINARY to that absolute path in your client's MCP env block. Same for REGAL_BINARY if you use the rego_lint tool. The examples/ configs already include both env vars; just edit the placeholder paths.

This issue does not affect the Docker or MCPB install paths. Those bundle opa and regal and bypass PATH entirely.

The server starts, then the client says "disconnected."

The most likely cause is something in the process writing to stdout besides MCP frames. If you've added a custom tool, check that no library it calls prints to stdout. The fixed-position safety net is lib/logger.ts. Use it, not console.log.

`PATH_NOT_ALLOWED` on a file under my project.

OPA_MCP_ALLOWED_PATHS is empty by default. Set it to the absolute path(s) you want the server to read from, comma-separated.

*`OPA_UNREACHABLE` when calling `opa_` tools.**

OPA_URL (default http://localhost:8181) must point at a running OPA server (opa run --server ...). Check with curl $OPA_URL/health.

Regal "version too old."

We track the current Regal release. If REGAL_VERSION_TOO_OLD fires, upgrade Regal: brew upgrade regal or download from the Regal releases page.

`directory-package-mismatch` violation when linting inline source.

Since v0.1.1, the server auto-disables this rule for inline-source calls. If you see it, you are running an older version -- upgrade to v0.1.1 or later. To get canonical signal on this rule, lint via paths against the real on-disk file instead of passing source directly.

Where are the logs?

Default location is <OS-tmpdir>/orygn-opa-mcp.log. That's typically /tmp/orygn-opa-mcp.log on Linux/macOS or %TEMP%\orygn-opa-mcp.log on Windows. Set OPA_MCP_LOG_FILE to override, and OPA_MCP_LOG_LEVEL=debug to widen the firehose.

Development

git clone https://github.com/OrygnsCode/opa-mcp-server.git
cd opa-mcp-server
npm install
npm run dev

Common commands:

npm run lint              # ESLint
npm run typecheck         # tsc --noEmit
npm test                  # unit tests (Vitest)
npm run test:coverage     # unit + coverage report
npm run test:integration  # against real opa + regal binaries
npm run build             # compile to dist/

CI runs lint, typecheck, build, and unit tests on every push and PR across Ubuntu, macOS, and Windows on Node 20, 22, and 24. Integration tests run on Linux against pinned opa and regal releases.

For the full contributor workflow (adding tools, naming conventions, logging discipline, release process), see CONTRIBUTING.md.

Versioning & support

This project follows Semantic Versioning. The public surface for SemVer purposes is the set of registered tools, prompts, and resources, their input/output schemas, the recognized environment variables, and the CLI entry point.

Breaking changes will be:

• announced in CHANGELOG.md under a new major version,
• preceded by at least one minor release with a deprecation warning,
• accompanied by a migration note in the release announcement.

Pinned versions of the upstream toolchain (opa and regal) are treated as part of the build, not as a dependency the operator manages. The Dockerfile, MCPB bundle, and CI all use the same pin; bumps go through Dependabot or a manual PR.

License

MIT © Orygn LLC

@orygn/opa-mcp is an independent project. It is not affiliated with, endorsed by, or sponsored by the Open Policy Agent project, the Cloud Native Computing Foundation, Styra, or Anthropic. "Open Policy Agent" and "Rego" are trademarks of their respective owners. "Model Context Protocol" is a trademark of Anthropic, PBC.

Listed in the OPA Ecosystem.