io.github.kanywst/mcp-opa-authz
OCI · GHCR.IO/KANYWST/MCP-OPA-AUTHZ
Authorization answers from real policy code: evaluate Rego locally, or ask an AuthZEN 1.0 PDP.
Available components
Last scanned (21 hours ago)
Scores higher than 89% of OCI servers
Category Security
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 Security0
- No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
- Known CVEs could not be checked: this image's dependency list comes from an SBOM its publisher attached, which nothing verifies, so we will not report it as a clean result.Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: this image's dependency list comes from an SBOM its publisher attached. It names packages and versions but not whether each is deprecated, still maintained or linked to its source, so there is nothing we can fairly grade.Unverified
Provenance & Transparency48
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 9 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability65
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1715 tokens (~343/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
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
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
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.
- 28 Oct 26 0
- Stability: 0.97 → pass security
- 27 Oct 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.
- 25 Oct 26 +1
- Stability: 0.87 → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Package version: 0.6.1 → 0.6.2 functional
- 22 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.
- 21 Oct 26 0
- Provenance: unverified → fail ▼ security
- 20 Oct 26 +1
- Provenance: fail → unverified ▼ security
- 18 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.
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 4 Nov 2026 · Analysed oci/ghcr.io/kanywst/mcp-opa-authz@0.6.2
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | oci |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
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 →
authzen_discover ~118
Fetch a PDP's AuthZEN metadata document from /.well-known/authzen-configuration to find out which endpoints and capabilities it offers. Use this when a PDP URL is known but its evaluation endpoint is not, or to check whether a PDP supports batch evaluation before calling authzen_evaluate_batch.
| Name | Type | Req | Description |
|---|---|---|---|
| pdp_url | string | – | The PDP root, e.g. `https://pdp.example.com`. An evaluation endpoint URL is also accepted — the known AuthZEN path suffix is stripped. Defaults to the configured AUTHZEN_PDP_URL. |
| Name | Type | Req | Description |
|---|---|---|---|
| metadata | object | yes | – |
| metadata_url | string | yes | – |
No examples provided.
authzen_evaluate ~279
Ask an OpenID AuthZEN 1.0 Policy Decision Point whether a subject may perform an action on a resource. Use this when the answer has to come from the PDP that actually governs the system, rather than from a policy pasted into the conversation. Returns the PDP's decision and any context it attached.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | JSON object naming the action. AuthZEN requires "name"; "properties" is optional. Example: {"name":"read"} |
| context | string | – | Optional JSON object of runtime context the policy may read — IP address, time of day, MFA strength. Example: {"ip":"10.0.0.7","mfa":"webauthn"} |
| pdp_url | string | – | Override the configured AUTHZEN_PDP_URL for this call. Must be an absolute http(s) URL to an Access Evaluation endpoint. |
| resource | string | yes | JSON object identifying the target. AuthZEN requires "type" and "id"; "properties" is optional. Example: {"type":"document","id":"doc-1","properties":{"classification":"secret"}} |
| subject | string | yes | JSON object identifying the principal. AuthZEN requires "type" and "id"; "properties" is optional. Example: {"type":"user","id":"alice","properties":{"department":"sales"}} |
Structured output declared, but exposes no named fields.
No examples provided.
authzen_evaluate_batch ~355
Ask an OpenID AuthZEN 1.0 PDP for several decisions in one round trip (the Access Evaluations API). Use this to answer "which of these may the subject do" — filtering a list of resources, or checking every action on one resource — instead of calling authzen_evaluate in a loop. Top-level subject/action/resource/context act as defaults that each entry may override.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | Default JSON action for entries that omit one. Requires "name". |
| context | string | – | Default JSON context object for entries that omit one. |
| evaluations | string | yes | JSON array of evaluation objects. Each may carry its own "subject", "action", "resource" and "context"; anything omitted falls back to the top-level argument of the same name. Example: [{"resource":{… |
| evaluations_semantic | string | – | How the PDP should process the list. `execute_all` (default) evaluates every entry; `deny_on_first_deny` and `permit_on_first_permit` let the PDP stop early and return fewer decisions than there were… |
| pdp_url | string | – | Override the endpoint for this call. Must point at an Access Evaluations (plural) endpoint. Defaults to the one the configured PDP advertises in its metadata, or the default path under the root of AU… |
| resource | string | – | Default JSON resource for entries that omit one. Requires "type" and "id". |
| subject | string | – | Default JSON subject for entries that omit one. Requires "type" and "id". |
| Name | Type | Req | Description |
|---|---|---|---|
| decisions | null|array | yes | – |
| endpoint_source | string | yes | – |
| evaluations_semantic | string | yes | – |
| pdp_url | string | yes | – |
| request_id | string | yes | – |
| truncated | boolean | yes | – |
No examples provided.
authzen_search ~400
Ask an OpenID AuthZEN 1.0 PDP which entities are permitted, rather than whether one is (the Search APIs). `search` picks the question: "subject" — who may perform the action on the resource; "resource" — which resources of a type the subject may act on; "action" — what the subject may do to the resource. The entity being searched for carries only its `type`; the action search takes no `action` at all. Use authzen_evaluate_batch instead when the candidates are already known.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | JSON action with "name", e.g. {"name":"read"}. Required for subject and resource searches; must be omitted for an action search. |
| context | string | – | Optional JSON object of runtime context the policy may read. |
| page_limit | number | – | Maximum number of results the PDP should return in one page. A PDP without pagination support may ignore it. |
| page_token | string | – | next_page_token from a previous authzen_search result, to fetch the next page. Every other argument must be unchanged from that call; AuthZEN lets the PDP reject a changed query. |
| pdp_url | string | – | Override the endpoint for this call. Must point at the Search endpoint for the chosen kind. Defaults to the endpoint the configured PDP advertises in its metadata, or the specification's default path… |
| resource | string | yes | JSON resource. For a resource search, only "type" (e.g. {"type":"document"}); otherwise "type" and "id" are required. |
| search | string | yes | Which entity to search for: subject, resource or action. |
| subject | string | yes | JSON subject. For a subject search, only "type" (e.g. {"type":"user"}); otherwise "type" and "id" are required. |
Structured output declared, but exposes no named fields.
No examples provided.
evaluate_policy ~292
Evaluate a Rego policy module against an input document and optional data namespace. Runs in-process via OPA; no external service is contacted, and the built-ins that could contact one are disabled. Use this to author or debug a policy whose source you have. Returns the decision, whether the query was defined at all, the raw OPA result set, and any print() output.
| Name | Type | Req | Description |
|---|---|---|---|
| data_json | string | – | JSON-encoded base document seeding the `data` namespace, for policies that read reference data. |
| input_json | string | – | JSON-encoded input document — the `input` variable inside the policy. |
| query | string | yes | Rego query to evaluate, e.g. `data.example.allow` or `data.example.violations[_]`. |
| rego | string | yes | Rego source for the policy module. Must include a `package` declaration. Rego v1 syntax by default: rule bodies need `if`, and multi-value rules need `contains`. |
| rego_version | string | – | Rego syntax version: `v1` (default) or `v0` for pre-OPA-1.0 policies written without `if`/`contains`. |
| trace | boolean | – | Return a pretty-printed evaluation trace. Use this to find out why a rule did not fire; it is verbose, so leave it off until a result is surprising. |
Structured output declared, but exposes no named fields.
No examples provided.
How do I install the io.github.kanywst/mcp-opa-authz server?
io.github.kanywst/mcp-opa-authz runs locally as a container image, launched with docker run --rm -i -e AUTHZEN_PDP_URL -e AUTHZEN_PDP_TOKEN -e AUTHZEN_PDP_TIMEOUT -e MCP_OPA_EVAL_TIMEOUT -e MCP_OPA_ALLOW_NETWORK_BUILTINS ghcr.io/kanywst/mcp-opa-authz:0.6.2. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
oci · ghcr.io/kanywst/mcp-opa-authz
claude mcp add kanywst-mcp-opa-authz -- docker run --rm -i -e AUTHZEN_PDP_URL -e AUTHZEN_PDP_TOKEN -e AUTHZEN_PDP_TIMEOUT -e MCP_OPA_EVAL_TIMEOUT -e MCP_OPA_ALLOW_NETWORK_BUILTINS ghcr.io/kanywst/mcp-opa-authz:0.6.2
This image reads AUTHZEN_PDP_URL, AUTHZEN_PDP_TOKEN, AUTHZEN_PDP_TIMEOUT, MCP_OPA_EVAL_TIMEOUT and MCP_OPA_ALLOW_NETWORK_BUILTINS. Set them in your client's env block for this server; docker run -e passes each one through to the container.
What is the io.github.kanywst/mcp-opa-authz server?
io.github.kanywst/mcp-opa-authz is listed in the public MCP registry as io.github.kanywst/mcp-opa-authz. Authorization answers from real policy code: evaluate Rego locally, or ask an AuthZEN 1.0 PDP. This page covers its container image (ghcr.io/kanywst/mcp-opa-authz).
Is the io.github.kanywst/mcp-opa-authz server safe to use?
io.github.kanywst/mcp-opa-authz scores 53 out of 100 on VerifyMCP. 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 io.github.kanywst/mcp-opa-authz server expose?
io.github.kanywst/mcp-opa-authz exposes 5 tools: authzen_discover, authzen_evaluate, authzen_evaluate_batch, authzen_search, evaluate_policy. Their descriptions and schemas cost roughly 1,444 tokens of context every time the server is loaded.
Is the io.github.kanywst/mcp-opa-authz server still maintained?
io.github.kanywst/mcp-opa-authz is still listed as active in the MCP registry. We last reached this channel on 4 November 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 io.github.kanywst/mcp-opa-authz server under?
io.github.kanywst/mcp-opa-authz declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.