PluginBench
MCP Server
Active
MIT

io.github.kanywst/mcp-opa-authz MCP Server

io.github.kanywst/mcp-opa-authz

RepositoryRegistry
How to choose

What this kind of tool is for

  • Scan a repository or dependency tree for known vulnerabilities.
  • Audit secrets, permissions, or headers during a pre-release review.
  • Have your agent explain a suspicious script or config before you run it.

How to compare servers like this

Failure mode:
Vulnerability reports are probabilistic; read findings as leads to verify, not verdicts.
Data leaving the box:
Check whether files or code are uploaded anywhere before scanning anything private.
Maintenance signal:
Security rulesets age fast; stale tools miss new classes of issue.
Report clarity:
The best tools say what is wrong, how sure they are, and how to fix it — verify findings yourself.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

What is the io.github.kanywst/mcp-opa-authz MCP server?

Authorization answers from real policy code: evaluate Rego locally, or ask an AuthZEN 1.0 PDP.

How to install io.github.kanywst/mcp-opa-authz

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • AUTHZEN_PDP_URL

    Default AuthZEN Access Evaluation endpoint, e.g. https://pdp.example.com/access/v1/evaluation. Only evaluate_policy works without it.

  • AUTHZEN_PDP_TOKEN
    secret

    Authorization header value for the PDP. A value with no scheme is sent as "Bearer <token>".

  • AUTHZEN_PDP_TIMEOUT

    Per-request timeout for PDP calls, as a Go duration. Default 10s.

  • MCP_OPA_EVAL_TIMEOUT

    Wall-clock limit on a single Rego evaluation, as a Go duration. Default 5s.

  • MCP_OPA_ALLOW_NETWORK_BUILTINS

    Re-enable http.send, net.lookup_ip_addr and opa.runtime inside evaluated policies. Off by default: policy source evaluated here comes from a model and runs inside the server process.

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "mcp-opa-authz": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/kanywst/mcp-opa-authz:0.3.1"
      ],
      "env": {
        "AUTHZEN_PDP_URL": "<YOUR_AUTHZEN_PDP_URL>",
        "AUTHZEN_PDP_TOKEN": "<YOUR_AUTHZEN_PDP_TOKEN>",
        "AUTHZEN_PDP_TIMEOUT": "<YOUR_AUTHZEN_PDP_TIMEOUT>",
        "MCP_OPA_EVAL_TIMEOUT": "<YOUR_MCP_OPA_EVAL_TIMEOUT>",
        "MCP_OPA_ALLOW_NETWORK_BUILTINS": "<YOUR_MCP_OPA_ALLOW_NETWORK_BUILTINS>"
      }
    }
  }
}

Related MCP servers

Personal MCP server for humans who create. Proof of authorship, license control.

0
Go
View repository →

Score any AI for trust across 10 dimensions; evaluate, monitor & govern LLMs and agents.

1
TypeScript
View repository →

AI-native server security audit, hardening, and fleet management across 4 cloud providers with 449 checks.

57
TypeScript
Apache-2.0
View repository →
APAPEX PSI logo

APEX PSI

Active

Cryptographic truth infrastructure for AI agents: seal, verify, anchor, cite, audit.

1
JavaScript
View repository →
FIFirekeep logo

Firekeep

Active

Self-hosted operating layer for AI agents: knowledge, continuity, coordination, and governance.

1
Python
View repository →

Local semantic code search with Git history—no API key, runs offline, saves 50% tokens.

47
Python
MIT
View repository →