Github ActionsSAFE
GitHub Actions Model Context Protocol Server
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://mseep.ai/app/cad0f49e-1c4d-4ab1-97e4-2312da835454) [](https://mseep.ai/app/ko1ynnky-github-actions-mcp-server)
[](https://smithery.ai/server/@ko1ynnky/github-actions-mcp-server)
⚠️ Archive Notice: This repository will be archived soon as the official GitHub MCP server is adding Actions support. See github/github-mcp-server#491 for details on the official implementation.
MCP Server for the GitHub Actions API, enabling AI assistants to manage and operate GitHub Actions workflows. Compatible with multiple AI coding assistants including Claude Desktop, Codeium, and Windsurf.
Features
- Complete Workflow Management: List, view, trigger, cancel, and rerun workflows
- Workflow Run Analysis: Get detailed information about workflow runs and their jobs
- Comprehensive Error Handling: Clear error messages with enhanced details
- Flexible Type Validation: Robust type checking with graceful handling of API variations
- Security-Focused Design: Timeout handling, rate limiting, and strict URL validation
Tools
list_workflows- List workflows in a GitHub repository
- Inputs:
owner(string): Repository owner (username or organization)repo(string): Repository namepage(optional number): Page number for paginationperPage(optional number): Results per page (max 100)- Returns: List of workflows in the repository
get_workflow- Get details of a specific workflow
- Inputs:
owner(string): Repository owner (username or organization)repo(string): Repository nameworkflowId(string or number): The ID of the workflow or filename- Ret
de61bed7391bOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add github-actions-mcp --env GITHUB_PERSONAL_ACCESS_TOKEN=${GITHUB_PERSONAL_ACCESS_TOKEN} -- npx -y [email protected]{
"mcpServers": {
"github-actions-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "${GITHUB_PERSONAL_ACCESS_TOKEN}"
}
}
}
}Exposed tools (9)
5 read · 4 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
cancel_workflow_run | write | |
get_workflow | read | |
get_workflow_run | write | |
get_workflow_run_jobs | write | |
get_workflow_usage | read | |
list_workflow_runs | read | |
list_workflows | read | |
rerun_workflow | read | |
trigger_workflow | write |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
node-fetch, @octokit/rest, universal-user-agent, zod, zod-to-json-schema, typescript
Gates applied: no_behavioural_pass, no_license.
de61bed7391bfull audit observations/trust-audit/mcp-server/ko1ynnky__github-actions.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | de61bed7391b | SAFE | B | 89 | first audit |
Questions
What is the Github Actions MCP server?
GitHub Actions Model Context Protocol Server
What tools does Github Actions expose?
9 in total: 5 read-only, 4 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Github Actions safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Github Actions need?
It reads GITHUB_PERSONAL_ACCESS_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Github Actions run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as github-actions-mcp at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (de61bed7391b), read on 2026-10-08. The repository is watched and re-audited when it changes.