# @orygn/opa-mcp

Author, validate, debug, and explain OPA Rego policies through any MCP-compatible client.

- **Type:** MCP server
- **Trust:** 85/100 (A), scored on the package rubric
- **Verification:** verified (build provenance)
- **Version:** 0.8.0
- **Author:** io.github.OrygnsCode
- **License:** MIT
- **npm:** @orygn/opa-mcp
- **Source:** https://github.com/OrygnsCode/opa-mcp-server
- **Compatible clients:** claude-code, cursor, copilot, gemini (basis: transport)

## Trust

85/100 (A), scored on the package rubric
- Publisher verified: no
- Build provenance: verified attestation
- npm trusted publishing (OIDC): yes
- Install scripts: nothing suspicious found
- Prompt-injection scan: not run
- Obfuscation scan: not run
- Evidence age: 113 days — stale; the grade is a claim about the present made from dated evidence

## Security scan

- **Status:** clean
- **Scanned:** 2026-06-14T11:10:58.534Z
- **Version scanned:** 0.2.0
- **CVEs:** none found by OSV at scan time

## Tools

40 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `rego_bench`
- `opa_bundle_build`
- `rego_capabilities`
- `rego_check_schema`
- `rego_check`
- `rego_compile_query`
- `rego_coverage_gaps`
- `opa_get_data`
- `opa_put_data`
- `opa_patch_data`
- `opa_delete_data`
- `opa_query_decision`
- `opa_compile_query`
- `rego_deps`
- `rego_describe_policy`
- `rego_eval`
- `rego_eval_with_explain`
- `rego_eval_with_profile`
- `rego_eval_with_coverage`
- `opa_exec`
- `rego_explain_decision`
- `rego_explain_undefined`
- `rego_fix`
- `rego_format_write`
- `rego_format`
- `rego_generate_test_skeleton`
- `rego_infer_input_schema`
- `rego_inspect`
- `rego_lint`
- `rego_migrate_v1`
- `rego_parse_ast`
- `rego_playground_share`
- `opa_list_policies`
- `opa_get_policy`
- `opa_put_policy`
- `opa_delete_policy`
- `rego_policy_diff`
- `conftest_pull`
- `conftest_push`
- `rego_security_audit`

## Install

**Verdict: review** — Installable, but 1 thing to check first: The last scan is 113 days old — the evidence behind this verdict is dated.
**Cautions** (coverage gaps and advisories — never blocking)
- The last scan is 113 days old — the evidence behind this verdict is dated.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"opa\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@orygn/opa-mcp\"\n      ],\n      \"env\": {\n        \"OPA_TOKEN\": \"<YOUR_OPA_TOKEN>\",\n        \"GITHUB_TOKEN\": \"<YOUR_GITHUB_TOKEN>\"\n      }\n    }\n  }\n}"
```
**Credentials it will ask for** (names only — Forge never holds a value):
- `OPA_TOKEN` — Opa Token (optional)
- `GITHUB_TOKEN` — GitHub Token (optional)
Placeholders only. Forge never holds, brokers, or transmits a credential value — replace each <YOUR_NAME> in your own config file. Do not send a value back to Forge; no Forge endpoint accepts one.
- This entry needs 2 credentials (0 required). The generated config carries placeholders, so it will fail in the editor rather than at runtime if they are left unset.

## Blast radius

Critical blast radius — runs commands; holds an api key.
- Floor 72, ceiling 72 (tier: critical)
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/%40orygn%2Fopa-mcp
- Install plan: https://forgeregistry.com/api/v1/packages/%40orygn%2Fopa-mcp/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/%40orygn%2Fopa-mcp
- HTML page: https://forgeregistry.com/registry/%40orygn%2Fopa-mcp
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.