Dead code, security, secrets detection and code quality for Python, TypeScript, Go.
Skylos MCP server is a hosted integration for AI assistants that speak the Model Context Protocol. Dead code, security, secrets detection and code quality for Python, TypeScript, Go.
Skylos is an open-source static analysis CLI for Python, TypeScript, JavaScript, Java, Go, Kotlin, PHP, Rust, Dart, C#, Shell, and deployment config. It runs locally by default and can also be used as a CI/CD PR gate.
Once Skylos is connected, these are the calls the assistant has available:
Attestation — ** JSON/md/SARIF reports carry a reproducible SHA-256 digestCI-native — ** skylos cicd init --defend generates the workflow step, theAgent-native — ** the verify_agent MCP tool lets coding agents verify theFramework — aware dead code detection:** FastAPI, Django, Flask, pytest,Local — first operation:** core static analysis does not require cloud uploadAgent — loop verification:** skylos verify and MCP verify_change returnEvidence — backed AI defects:** --ai-defects and full scans put strictVerification — backed remediation:** security fixes are checked by re-runningProject — specific rules:** add local YAML rules and extend prompt, credential,events.jsonl — chronological run, phase, and tool-call eventsstate.json — full observable state, including phases, tool calls, decisions,summary.json — compact status, counts, budget, and artifact pathsYou will need 2 environment variables: RULE_ID, MY_AGENT_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Skylos's toolset — Attestation, CI-native, Agent-native and 11 more — is a fair guide to whether it matches your workflow. It is maintained by duriantaco; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Skylos's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Attestation | ** JSON/md/SARIF reports carry a reproducible SHA-256 digest |
| CI-native | ** skylos cicd init --defend generates the workflow step, the |
| Agent-native | ** the verify_agent MCP tool lets coding agents verify the |
| Framework | aware dead code detection:** FastAPI, Django, Flask, pytest, |
| Local | first operation:** core static analysis does not require cloud upload |
| Agent | loop verification:** skylos verify and MCP verify_change return |
| Evidence | backed AI defects:** --ai-defects and full scans put strict |
| Verification | backed remediation:** security fixes are checked by re-running |
| Project | specific rules:** add local YAML rules and extend prompt, credential, |
| events.jsonl | chronological run, phase, and tool-call events. |
| state.json | full observable state, including phases, tool calls, decisions, |
| summary.json | compact status, counts, budget, and artifact paths. |
| behavior-results.json | normalized runtime assertions, provenance, coverage, |
| Goal | Command |
{
"mcpServers": {
"skylos": {
"command": "uvx",
"args": ["skylos"],
"env": {
"RULE_ID": "your-value",
"MY_AGENT_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| RULE_ID | Configuration value read at startup. | Optional |
| MY_AGENT_API_KEY | Credential the server authenticates with. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.