act-mcp
Allows running GitHub Actions workflows locally via act, providing tools to list workflows, run jobs, and retrieve logs.
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., "@act-mcp list workflows in current repo"
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.
act-mcp
MCP stdio server exposing three tools for running GitHub Actions locally via act.
Peer dependency: act
act must be installed and in PATH:
# macOS
brew install act
# Linux
curl https://raw.githubusercontent.com/nektos/act/master/install.sh | sudo bashRelated MCP server: AI Code Review MCP Server
MCP Tools
list_workflows
Globs .github/workflows/*.yml and returns job names from each file.
Field | Type | Description |
|
| Repo root (default: |
Returns: Array<{ file: string, jobs: string[] }>
run_job
Spawns act -j <jobName>, captures stdout+stderr, caches logs.
Field | Type | Description |
|
| Job ID (key under |
|
| Repo root (default: |
Returns: { exitCode: number, logs: string }
get_logs
Returns logs cached by the most recent run_job call.
Returns: { logs: string | null }
Agent loop
list_workflows → pick failing job
run_job → read exitCode + logs
get_logs → inspect failure output
(patch YAML)
run_job → verify fixMCP client config (Claude Desktop)
{
"mcpServers": {
"act-mcp": {
"command": "npx",
"args": ["act-mcp"]
}
}
}Or point cwd at a specific repo:
{
"mcpServers": {
"act-mcp": {
"command": "npx",
"args": ["act-mcp"],
"env": {}
}
}
}Pass cwd as a tool argument at call time:
{ "name": "list_workflows", "arguments": { "cwd": "/path/to/repo" } }Development
npm install
npm run build # tsc → dist/
npm test # vitest (uses mock act binary, no act required)
npm run dev # run via tsx without buildingEnvironment variables
Variable | Default | Description |
|
| Path to the act binary (useful for testing) |
Available Tools
3 toolsget_logsA
Return cached stdout+stderr from the most recent run_job call
Inputs: no named parameters.
list_workflowsA
List .github/workflows/*.yml files and their job names
Inputs: cwd.
run_jobA
Run a specific job via act -j , returns exitCode and captured logs
Inputs: jobName (required), cwd.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool targets a distinct action: listing workflows, running a job, and retrieving logs. There is no functional overlap between them.
All tool names follow a consistent verb_noun pattern using snake_case: list_workflows, run_job, get_logs. No deviations.
Three tools is within the typical well-scoped range (3-15) and each tool serves a necessary and clear purpose in the workflow.
The tool set covers the full lifecycle for the server's domain: listing available workflows, executing a job, and retrieving results. No obvious gaps are present.
Maintenance
Related MCP Connectors
Build, test and publish agentic workflows from your AI client: approve steps, read tables, see runs.
Build, validate, test-run and publish AIOS workflows from Claude Code, Codex, Cursor or VS Code.
Build, run, inspect, and continue AgentScript workflows on connected Super Chrome and Mac clients.
Operate GitHub from your AI assistant: repos, PRs, issues, Actions. Previews and read-only mode.
Related MCP Servers
- AlicenseAqualityNot gradedmaintenanceConnects AI assistants to GitHub Actions workflows to monitor CI/CD pipelines, view run logs, diagnose failures, and optionally trigger or manage workflows with granular permission controls.101-
- AlicenseBqualityDmaintenanceIntegrates GitHub repository management and local file system access to enable AI agents to perform code reviews and manage pull requests. It provides tools for listing repositories, retrieving PR diffs, and searching or reading files within a specified workspace.7MIT
- AlicenseAqualityBmaintenanceEnables managing and debugging Azure Logic Apps through natural language, with tools for listing, debugging, creating, updating, and deleting workflows.40123 npm7MIT
- AlicenseAqualityCmaintenanceProvides tools to analyze and debug GitHub Actions CI failures, including summarizing failures, detecting flaky tests, and suggesting fixes.104 npm1ISC