mcp-skylos
Skylos is a local, read-mostly code-analysis MCP server that scans a repository for dead code, security flaws, secrets, quality and architecture issues, can generate or apply fixes, and exposes a codebase graph for navigation and change review.
Scan the codebase:
analyze(dead code),security_scan(injection, SSRF, path traversal, unsafe deserialization),secrets_scan(redacted credentials),quality_check(complexity, nesting, duplication),architecture_check(coupling, circular deps), andhealth_score(combined risk/maintainability/dead-code readout).Understand a change:
change_map(per-function diff with callers, signature changes, review plan),validate_code_change(pre-landing diff check for security regressions, new dangerous patterns, secrets, hallucinated dependencies), andverify_change(AI-code defects plus security/secrets for a file or line range).Fix findings:
generate_fix(dead-code removal patch, preview or apply) andremediate(LLM-planned or applied fixes; needs theskylos[llm]extra).Triage:
learn_triagerecords accept/dismiss decisions andget_triage_suggestionsproposes decisions from learned patterns.Verify AI applications:
verify_agentstatically scores agent guardrails with OWASP LLM/Agentic coverage, andget_security_contextsummarizes the project's frameworks, auth and security conventions.Attribute code:
provenance_scanreports agent/bot/human contribution evidence from git signals.Navigate the codebase graph:
graph_find,graph_show,graph_impact(dependents and reaching tests),graph_areas(module groupings),graph_relevant(token-budgeted context for files being edited), plusgraph_pendingandgraph_describeto write and save plain-English summaries locally.Access notes:
analyzeand the local map/graph tools work without a key (analyzelimited to 5 calls/day); all other tools requireSKYLOS_API_KEY. Results include a_run_id/_result_uri, scans are local and upload nothing, and advice is grouped unlessexpand_adviceis set.
Scans Docker Compose and other deployment configs for privileged access, host networking, missing sandboxing, and other edge-device security misconfigurations.
Generates GitHub Actions PR gates with annotations and failure thresholds, and scans workflows for CI/CD misconfigurations.
Scans GitLab CI configurations for dangerous triggers, unpinned actions/includes, broad tokens, and other supply-chain risks.
Docs · Quick start · Website · VS Code · Discord
What is Skylos?
Skylos is a free, open-source (Apache-2.0) checker for the code you and your coding agents write. It runs on your machine, inside your agent's loop and as a pull-request gate. No account, no API key and no LLM needed.
Coding agents such as Claude Code, Codex and Cursor write code faster than anyone can review it, and they repeat the same mistakes. They say "done" after deleting or skipping a failing test. They install packages that don't exist and import functions nobody wrote. They leave injection bugs and hard-coded keys behind. Linters and security scanners each catch a slice of this, after the fact. Skylos checks all of it in one tool, at the points where it can still be stopped.
It is built for:
Developers who let agents write code, and want the agent checked while it works, not after.
Maintainers who want one free check on every pull request.
Existing codebases that need security, secrets, dependency, quality and dead-code findings from one scan, in Python, TypeScript, Java, Go and more.
Related MCP server: loctree-mcp
Quick start
pip install skylos
skylos . -a # scan this repo with every check; nothing leaves your machineKey commands
No account needed. Your code and findings stay on your machine.
To | Run |
Find dead code |
|
Run every check: security, secrets, dependencies, quality, AI-code mistakes |
|
Check only what your branch changed |
|
Fail the build when the gate fails |
|
Check the agent really finished (runs your tests) |
|
Check every pull request in CI |
|
Set up Claude Code and Codex in this repo |
|
Skylos Cloud: see results online and block failing pull requests
Optional. Five steps, in this order, from your repository folder. No token to copy.
Step | Run or do | What happens |
1. Upload your first scan |
| Your browser opens skylos.dev. Sign in, then pick or create the project for this repo. Back in the terminal, Skylos scans and uploads the findings (not your code). |
2. Open your results | Click the | The scan in your dashboard: its gate result and every issue. Find it again later at skylos.dev/dashboard. |
3. Add the pull request check |
| Writes |
4. Install the GitHub App, then merge | Open the GitHub App link it printed | Install the Skylos GitHub App on the repo before you merge that pull request. CI then uploads with its GitHub identity, so there is no token or secret to add. |
5. Make the check required |
| Run it after the merge (it uses the GitHub CLI, |
Done: every pull request gets a Skylos check, and every push to your default branch shows up in your dashboard.
The end of step 1 looks like this:
✓ Scan saved · gate (not blocking): fail
Open: https://skylos.dev/dashboard/projects/<project>/scans/<scan>
Saved for review. Only verified CI scans block merges and update the project verdict.
Next: to block pull requests, run skylos cicd init and merge the workflow it writes.A scan from your machine is saved for review but never blocks a merge; only CI
scans do. Upload again any time with skylos cloud. Details:
Skylos Cloud.
Working with a coding agent? skylos setup once per repo, then skylos open
every day for a diagram of your code, what changed, and every check run. The
tutorial walks through a real session.
How it works
Skylos steps in at four points:
When | Command | What it stops |
While the agent works |
| Made-up package installs, reads of files holding secrets, git-hook bypasses; checks every edit |
When the agent says "done" |
| Deleted or skipped tests, loosened CI steps, silenced lint or type checks, test-only special cases; runs your tests |
On every pull request |
| Critical security issues, secrets and critical AI-code mistakes, plus anything over your limits |
Any time, on the whole repo |
| Security flaws, secrets, vulnerable dependencies, quality regressions, AI-code mistakes, dead code |
See it work
A 20-line Flask app, scanned with every check (excerpt):
$ skylos . -a --format concise
app.py:15 SKY-D211 Possible SQL injection: tainted or string-built query.
app.py:5 SKY-L012 Import from local module 'billing' requests 'issue_refund', but that name is not defined or re-exported there.
app.py:8 SKY-S101 Potential stripe secret detected
requirements.txt:1 SKY-SCA-GHSA-68rp-wp8r-4726 flask@3.1.2: Flask session does not add `Vary: Cookie` header when accessed in some ways
billing.py:1 SKY-U001 unused function: charge_cardEvery finding names the file, line and rule. Security findings show the
source-to-sink path when one was recorded; --format json keeps the full
evidence.
Check every agent edit
Install hooks so the agent is checked while it works:
skylos agent install-hooks # Claude Code
skylos agent install-hooks --codex # Codex
skylos agent install-hooks --cursor # CursorAfter each edit: checks the changed lines for security issues, secrets and AI-code mistakes, and tells the agent what to fix.
Before a file read: blocks files that contain hard-coded secrets.
Before a package install (
pip,uv,npm,pnpm,bun,go, ...): blocks made-up or typosquatted packages, and asks before installs it cannot verify.Before a git command: blocks
--no-verifyand other ways around your git hooks.At stop: blocks "done" while issues the agent added are still open.
If Skylos itself errors, the action is allowed and both you and the agent are told it went unchecked. See agent hooks.
Is the agent really done?
skylos done --base mainskylos done compares the branch with main and runs your tests. It flags:
deleted, skipped or weakened tests
loosened test settings and CI test steps
silenced lint or type checks
code that special-cases the tests
code the branch left with no callers (advice, not a block)
When a test fails, it reruns it on main and labels the failure "introduced"
or "already failing". It writes a receipt to .skylos/receipts/. pytest runs
automatically; other runners need one line:
[tool.skylos.done]
test_command = "npm test"It reads its settings from main, so a branch cannot loosen its own check.
Exit codes: 0 pass, 1 blocked, 2 could not run. See the
done gate and what it misses.
Gate pull requests
No account or token needed:
git checkout -b add-skylos-gate
skylos cicd init --no-upload
git add .github/workflows/skylos.yml
git commit -m "Add Skylos pull request gate"
git push -u origin add-skylos-gateThe workflow reviews the changed lines of each pull request and runs
skylos done when it finds your tests. skylos cicd init also sets up GitLab
CI, Jenkins, Bitbucket Pipelines, Azure Pipelines and CircleCI
(any CI).
The gate always fails on a critical security issue, a secret, or a critical AI-code issue such as an import of a package that doesn't exist. Everything else fails only above your limits:
[tool.skylos.gate]
max_high = 5 # high-severity security issues allowed
max_quality = 10 # quality issues allowed
max_ai_defects = 10 # AI-code issues allowedThe policy is read from the base branch, so a pull request cannot loosen its
own gate. Each run ends with Quality Gate: PASSED, FAILED (exit 1) or
INCOMPLETE (exit 2) and the reasons. Walkthrough:
your first gated pull request.
Need a person to sign off on risky changes? skylos cicd init --risk-review
adds a check that waits for a human approval when a pull request deletes
tests, removes auth checks, changes dependencies or weakens CI. See
risk review.
Scan a repository
skylos . # dead code (fast, default)
skylos . -a # every check
skylos . -a --diff origin/main # only findings on changed lines
skylos . --format pretty # grouped report with code snippets
skylos . --tui # keyboard-driven triage
skylos . -a --format json # full evidence for scripts and agents
skylos . --format sarif # GitHub code scanning
skylos cleanup . --top 5 # a prioritized fix listPython dead code can be removed for you: skylos clean . --dry-run shows the
plan, --apply edits files. Output modes and exit codes:
CLI output.
What Skylos catches
Category | Examples |
AI-code mistakes | imports of functions that don't exist, invented package APIs, packages that don't exist, impossible versions, unfinished stubs, disabled controls |
Security flaws | SQL injection, XSS, SSRF, path traversal, command injection, unsafe deserialization, ReDoS |
Secrets | API keys, tokens, private credentials, high-entropy strings |
Dependencies | known CVEs, malicious packages, license policy, offline SBOM (CycloneDX, SPDX) |
Quality | complexity, deep nesting, duplicate branches, long functions, inconsistent returns |
Dead code | unused functions, classes, imports, files and dependencies, framework-aware (FastAPI, Django, Flask, Next.js, React, Laravel, ...) |
CI/CD and deployment | risky GitHub Actions and GitLab CI, Dockerfiles, Docker Compose, systemd, Kubernetes |
LLM apps | unsafe tool use, prompt-injection exposure, missing output validation |
Every rule: Rules Reference and rule dictionary.
Verify the AI apps you build
If your code calls an LLM, Skylos checks the guardrails around it, with no model in the loop:
skylos discover . # list LLM calls, agent tools and prompt sites
skylos defend . # score the guardrails around them
skylos defend . --fail-on critical # CI gate
skylos defend . --format md -o evidence.md # evidence report with OWASP LLM Top 10 coverageIt covers Python and TypeScript/JavaScript; --owasp-framework agentic reports
against the OWASP Agentic Top 10. To test a running agent against
expected answers and tool calls, use skylos agent test. See
agent verification and
agent behavior testing.
Language Support
Language | Dead code | Security | Quality |
Python | Yes | Yes | Yes |
TypeScript / JavaScript | Yes | Yes | Yes |
Java | Yes | Yes | Yes |
Go | Yes | Partial | Partial |
PHP | Yes | Yes | No |
Rust | Experimental | Partial | Partial |
Ruby | Partial | Partial | No |
Dart | Yes | Partial | No |
C# | Partial | Partial | Partial |
C++ | Partial | No | No |
Kotlin | Partial | Partial | No |
Swift | Partial | No | No |
Shell | No | Partial | No |
Python has the deepest coverage.
Go needs the native
skylos-goengine. It ships in the PyPI wheels for Linux, macOS and Windows; elsewhereskylos doctorprints the build command.Dart needs
pip install "skylos[dart]".Rust dead code is hidden by default;
--confidence 40shows it.
Full matrix and per-language limits: language support.
Configuration
skylos init adds a starter config to pyproject.toml. Projects without one
can use skylos.toml with the same keys at the top level:
# skylos.toml
exclude = ["generated", "dist"]
[gate]
max_high = 5
[done]
test_command = "npm test"In a monorepo, each package can have its own file; the nearest one wins per
key. skylos doctor shows which files are in use.
Silence one finding with a reason:
query = build_query(user_id) # skylos: ignore[SKY-D211] user_id is an int from the routerTo accept existing findings and gate only new ones, run skylos baseline .
and scan with --baseline. More: configuration.
Integrations
Integration | What it does |
Pull-request gate, optional container-image gate | |
Pull-request gate for that CI | |
Claude Code, Codex and Cursor checked on every edit | |
Skylos scans as tools for AI assistants | |
Findings in the editor | |
Optional: findings and the gate per branch, over time |
Install options
pip install skylos # core checks
pip install "skylos[llm]" # agent commands that use an LLM
pip install "skylos[all]" # every optional extraOr run the container image:
docker run --rm -v "$PWD":/work -w /work ghcr.io/duriantaco/skylos:latest . -aOther extras (lint, verdict, dart), Python-specific image tags and
source installs: installation.
What leaves your machine
Your code and findings reach Skylos Cloud only when you run a command that
says it uploads, such as skylos cloud or --upload. A saved login alone
never uploads anything. There are no analytics.
Dependency and package checks send package names and versions to OSV and the public registries, never source. LLM commands share code only with the model provider you configure. Every request, its trigger and how to turn it off: privacy and network.
Results
10 Skylos-assisted dead-code cleanup PRs have been merged in 9 open-source projects, including Black, NetworkX, Optuna, mitmproxy and pypdf. Real-World Results lists all 26 PRs we recorded, including the ones that were closed or reverted. These are accepted cleanups, not endorsements.
Methods, dated results and competitor comparisons: BENCHMARK.md.
FAQ
Does Skylos replace Semgrep, CodeQL, Bandit or Vulture? No. It runs alongside them. It adds agent checks, framework-aware dead code and one gate across security, secrets, dependencies and quality.
Does it need an LLM?
No. The core checks run locally with no model. LLM features are optional
(skylos[llm]).
Is it free? The CLI is free and open source. Skylos Cloud is optional and has a free plan; see pricing.
Can I check only my changes?
Yes: skylos . -a --diff origin/main. A removed security check, such as a
deleted auth decorator, is still reported.
What about code that is only called dynamically?
Use inline ignores, a baseline, or --trace to record what actually runs. See
smart tracing.
More: FAQ.
Documentation
Need | Read |
Every command and flag | |
Install, extras, Docker | |
Config files, ignores, baselines | |
Output formats and exit codes | |
Agent hooks | |
| |
Pull-request gates | |
Security and taint analysis | |
Dependencies, SBOM, licenses | |
AI-code checks | |
Network requests | |
Rule IDs |
Contributing
Read CONTRIBUTING.md before sending a pull request.
Report a bug with
skylos feedback(no account needed), or open an issue with a minimal repro.Report security issues through SECURITY.md.
Analyzer changes are tested on real projects with liveness_primer, built by Matthew Digman. See the guide.
Ideas to work on: ROADMAP.md. Chat: Discord.
License
Apache License 2.0. See LICENSE.
Available Tools
24 toolsanalyzeFind dead codeARead-only
Find dead code: unused functions, classes, imports, variables, parameters and files.
Use this to list cleanup candidates in a project. Returns JSON with a
summary and per-category findings (file, line, name, confidence) plus
_run_id; the full result is stored locally and can be read from the
skylos://results/{run_id} resource. Read-only: it never edits code.
Findings are candidates: before deleting one, check for dynamic use
(getattr, string dispatch, entry points, framework decorators, tests).
A non-empty analysis_errors means analysis or verification was
incomplete; do not treat the findings as a complete scan.
Defect and Review records remain complete. Advice is grouped by default; expand_advice=True includes every Advice record. Read _result_uri for the complete saved result without rescanning.
Works without SKYLOS_API_KEY (5 calls/day); higher limits with a key.
Inputs: path (required), confidence, expand_advice, exclude_folders. Returns: result
architecture_checkCheck architectureARead-only
Report architecture findings for a project: module coupling, cohesion and circular dependencies.
Returns JSON with the architecture findings and _run_id. Read-only
and local. Use quality_check for function-level issues.
Defect and Review records remain complete. Advice is grouped by default; expand_advice=True includes every Advice record. Read _result_uri for the complete saved result without rescanning.
Requires SKYLOS_API_KEY: this tool returns an authentication error unless the MCP server is started with SKYLOS_API_KEY set. Without a key, analyze works (5 calls/day) and the local map tools (change_map and the graph_* tools) work with no limit. The local CLI needs no key: skylos verify <file> and skylos agent install-hooks.
Inputs: path (required), confidence, expand_advice, exclude_folders. Returns: result
change_mapMap what a change touchesARead-only
Map what a code change touches, to review it: every changed Python or TypeScript/JavaScript function, method or class with its old and new code, calls added and removed, calls that only moved into a helper, its callers (with call lines, and whether each caller was updated), removed security checks and access checks, breaking or compatible signature changes, changed module values and the functions using them, and a review plan: read first, read, skim, or skip (skip only when the logic is proven the same: docstring only or local names only; moved code is skim because its import path changed), with changed-line counts and tests whose expected answers changed. Flags list what a person must look at.
Computed from the code, not by a model: the same commit gives the same map. Returns JSON. Read-only and local.
Works without SKYLOS_API_KEY and has no daily limit: it reads the repository on this machine and sends nothing to Skylos Cloud.
Inputs: base, path. Returns: result
generate_fixGenerate a dead-code removal patchADestructive
Build a unified-diff patch that removes (or comments out) dead code found by static analysis, after grep verification drops findings that are still referenced.
Returns the diff, patch summary, validation errors and applied status. With apply=False (default) it previews changes; with apply=True it edits files if patch validation succeeds. Refuses to run when the analysis or grep verification was incomplete. Review the diff and run trusted tests before keeping it.
Requires SKYLOS_API_KEY: this tool returns an authentication error unless the MCP server is started with SKYLOS_API_KEY set. Without a key, analyze works (5 calls/day) and the local map tools (change_map and the graph_* tools) work with no limit. The local CLI needs no key: skylos verify <file> and skylos agent install-hooks.
Inputs: path (required), mode, apply, min_safety. Returns: result
get_security_contextSummarize security contextARead-only
Summarize a project's security setup: detected web frameworks, auth decorators and middleware, security headers, rate limiting, input validation and a supported Skylos YAML policy file.
Use it before reviewing or writing security-sensitive code to learn the project's conventions. Returns JSON. Read-only and local.
Requires SKYLOS_API_KEY: this tool returns an authentication error unless the MCP server is started with SKYLOS_API_KEY set. Without a key, analyze works (5 calls/day) and the local map tools (change_map and the graph_* tools) work with no limit. The local CLI needs no key: skylos verify <file> and skylos agent install-hooks.
Inputs: path (required). Returns: result
get_triage_suggestionsSuggest triage decisionsARead-only
Suggest accept or dismiss for current findings, based on decisions recorded with learn_triage in this project.
Returns JSON suggestions with finding fingerprints, suggested actions and confidence, plus the number of learned patterns. Read-only and local.
Requires SKYLOS_API_KEY: this tool returns an authentication error unless the MCP server is started with SKYLOS_API_KEY set. Without a key, analyze works (5 calls/day) and the local map tools (change_map and the graph_* tools) work with no limit. The local CLI needs no key: skylos verify <file> and skylos agent install-hooks.
Inputs: path (required). Returns: result
graph_areasThe areas of the codebaseARead-only
The codebase split into areas: groups of functions and classes that work together, grouped folder by folder and named after the folder and the member the rest of the code depends on most, with its size, folders and links to other areas. Pass an area id to get its members, most important first, and the areas it links to. Use it to get oriented in an unfamiliar repository. Returns JSON. Read-only and local.
Works without SKYLOS_API_KEY and has no daily limit: it reads the repository on this machine and sends nothing to Skylos Cloud.
Inputs: area, path. Returns: result
graph_describeSave plain-English descriptions to the codebase graphA
Save descriptions you wrote for items from graph_pending into .skylos/graph/notes.json, where the graph viewer and graph_show read them. A replaced description is kept as the previous one, so readers can see what the code did before. Unknown ids are ignored, and so are impact entries for callers graph_pending did not list with that change. Summaries are capped at 400 characters and impact effects at 300. Writes one local file.
Works without SKYLOS_API_KEY and has no daily limit: it reads the repository on this machine and sends nothing to Skylos Cloud.
Inputs: items (required), path. Returns: result
graph_findFind code in the codebase graphARead-only
Search the codebase graph for functions, methods and classes by name. Each result has its id, file, line and plain-English summary when one exists. Builds the graph first if the repository has none (Python, TypeScript, JavaScript). Returns JSON. Read-only and local.
Works without SKYLOS_API_KEY and has no daily limit: it reads the repository on this machine and sends nothing to Skylos Cloud.
Inputs: query (required), path, include_tests. Returns: result
graph_impactWhat depends on a functionARead-only
Everything in the repository that calls a function or class, directly or through other code, grouped by distance, plus the tests that reach it. Use it before changing a signature or behaviour. Returns JSON. Read-only and local.
Works without SKYLOS_API_KEY and has no daily limit: it reads the repository on this machine and sends nothing to Skylos Cloud.
Inputs: name (required), path, depth. Returns: result
graph_pendingCode that still needs a plain-English descriptionA
Functions and classes that have no plain-English description yet (or whose code changed since it was written), with their source, callers and callees. Write the descriptions yourself and save them with graph_describe; nothing is sent to any model by this tool. With changes=true, lists changed code whose logic changed (not code proven to keep the same logic) to explain instead, each with its old and new code, proven facts, the tests that reach it and its callers (code proven to call it within 2 steps, with what each does today), and writes .skylos/graph/changes.json for the viewer; explain each change and, in impact, how it changes each listed caller that behaves differently. Use change_map first to see what to read. Returns JSON. Local.
Works without SKYLOS_API_KEY and has no daily limit: it reads the repository on this machine and sends nothing to Skylos Cloud.
Inputs: base, path, limit, changes. Returns: result
graph_relevantCode that matters most to the files you are changingARead-only
The functions and classes elsewhere in the repository that matter most to the given files, most important first, cut to a token budget: each with its signature, file and line, plain-English summary, how it relates to the files (calls them, called by them) and its area. Use it before editing to know what else to read. Returns JSON. Read-only and local.
Works without SKYLOS_API_KEY and has no daily limit: it reads the repository on this machine and sends nothing to Skylos Cloud.
Inputs: files (required), path, budget. Returns: result
graph_showExplain one function or class from the codebase graphARead-only
One function, method or class from the codebase graph: its plain-English summary, signature, who uses it, what it uses, the tests that reach it within 3 calls, literal input/output pairs its tests expect, and its change verdict when the working tree changed it. Also: description (now, and before when the code changed since the previous one was written), change_note (the saved change explanation, with impact: how the change reaches each caller) and impact_preview (code proven to call it within 3 steps, production first, then tests). Returns JSON. Read-only and local.
Works without SKYLOS_API_KEY and has no daily limit: it reads the repository on this machine and sends nothing to Skylos Cloud.
Inputs: name (required), path, with_code. Returns: result
health_scoreAssess codebase healthARead-only
Assess a project through separate Risk, Maintainability and Dead code readouts.
This tool retains its health_score name for compatibility but no longer creates a blended numeric grade. Gate policy remains independent. Returns assessment, coverage, finding counts and _run_id. Read-only and local. Advice is grouped by default; expand_advice=True includes every Advice record. Read _result_uri for the complete saved result.
Requires SKYLOS_API_KEY: this tool returns an authentication error unless the MCP server is started with SKYLOS_API_KEY set. Without a key, analyze works (5 calls/day) and the local map tools (change_map and the graph_* tools) work with no limit. The local CLI needs no key: skylos verify <file> and skylos agent install-hooks.
Inputs: path (required), confidence, expand_advice, exclude_folders, +3 more. Returns: result
learn_triageRecord a triage decisionA
Record whether a finding was accepted or dismissed so get_triage_suggestions can learn from it.
Writes the decision to the project's local Skylos state.
Requires SKYLOS_API_KEY: this tool returns an authentication error unless the MCP server is started with SKYLOS_API_KEY set. Without a key, analyze works (5 calls/day) and the local map tools (change_map and the graph_* tools) work with no limit. The local CLI needs no key: skylos verify <file> and skylos agent install-hooks.
Inputs: path (required), action (required), action_id (required). Returns: result
provenance_scanAttribute changes to agents or humansARead-only
Report available evidence of AI-agent, bot and human contributions.
Combines git signals since the base (agent bot accounts, Co-authored-by and AI declaration trailers, agent-named commit subjects) with recorded local attribution evidence. Returns JSON with per-file attribution, evidence and coverage status. Commit declarations do not establish line authorship; missing evidence remains unknown. Read-only and local.
Requires SKYLOS_API_KEY: this tool returns an authentication error unless the MCP server is started with SKYLOS_API_KEY set. Without a key, analyze works (5 calls/day) and the local map tools (change_map and the graph_* tools) work with no limit. The local CLI needs no key: skylos verify <file> and skylos agent install-hooks.
Inputs: path (required), diff_base. Returns: result
quality_checkCheck code qualityARead-only
Report code-quality issues: high complexity, deep nesting, long functions, duplicate branches and similar maintainability findings.
Returns JSON with findings (rule ID, file, line, message) and
_run_id. Read-only and local.
Defect and Review records remain complete. Advice is grouped by default; expand_advice=True includes every Advice record. Read _result_uri for the complete saved result without rescanning.
Requires SKYLOS_API_KEY: this tool returns an authentication error unless the MCP server is started with SKYLOS_API_KEY set. Without a key, analyze works (5 calls/day) and the local map tools (change_map and the graph_* tools) work with no limit. The local CLI needs no key: skylos verify <file> and skylos agent install-hooks.
Inputs: path (required), confidence, expand_advice, exclude_folders. Returns: result
remediatePlan or apply LLM fixesADestructive
Plan or apply LLM-generated fixes for Skylos findings in a project.
With dry_run=True (default), static analysis returns a remediation
plan without calling a model or changing files. With dry_run=False,
it generates fixes and can edit files in place: this needs the
skylos[llm] extra and provider configuration (including credentials
when required), and sends affected code to that provider. It does not
run your tests.
Review every change and run trusted tests before keeping it.
Costs no Skylos credits. Scan tools cost no credits either.
Requires SKYLOS_API_KEY: this tool returns an authentication error unless the MCP server is started with SKYLOS_API_KEY set. Without a key, analyze works (5 calls/day) and the local map tools (change_map and the graph_* tools) work with no limit. The local CLI needs no key: skylos verify <file> and skylos agent install-hooks.
Inputs: path (required), model, dry_run, severity, +2 more. Returns: result
secrets_scanFind hard-coded secretsBRead-only
Find hard-coded secrets and credentials (API keys, tokens, private keys, passwords) in source and config files.
Returns JSON with findings (provider, file, line) and _run_id. Secret
values are redacted in the output. Read-only and local.
Defect and Review records remain complete. Advice is grouped by default; expand_advice=True includes every Advice record. Read _result_uri for the complete saved result without rescanning.
Requires SKYLOS_API_KEY: this tool returns an authentication error unless the MCP server is started with SKYLOS_API_KEY set. Without a key, analyze works (5 calls/day) and the local map tools (change_map and the graph_* tools) work with no limit. The local CLI needs no key: skylos verify <file> and skylos agent install-hooks.
Inputs: path (required), confidence, expand_advice, exclude_folders. Returns: result
security_scanScan for security issuesARead-only
Scan source code for security issues such as SQL and command injection, SSRF, path traversal, eval/exec and unsafe deserialization.
Returns JSON with findings (rule ID, severity, file, line, message) and
_run_id. Read-only; the scan runs locally and does not upload code. Use
secrets_scan for hard-coded credentials and validate_code_change
to check a diff before it lands.
Defect and Review records remain complete. Advice is grouped by default; expand_advice=True includes every Advice record. Read _result_uri for the complete saved result without rescanning.
Requires SKYLOS_API_KEY: this tool returns an authentication error unless the MCP server is started with SKYLOS_API_KEY set. Without a key, analyze works (5 calls/day) and the local map tools (change_map and the graph_* tools) work with no limit. The local CLI needs no key: skylos verify <file> and skylos agent install-hooks.
Inputs: path (required), confidence, expand_advice, exclude_folders. Returns: result
validate_code_changeCheck a diff before it landsARead-only
Validate a code diff for security regressions and issues before it lands.
Takes a unified diff and checks for:
Security control regressions (auth, CSRF, TLS, rate limiting removal)
New dangerous patterns (eval, exec, SQL injection, etc.)
Secrets in added code
Hallucinated or undeclared dependencies in added imports and manifest entries (requirements*.txt, pyproject.toml, package.json, go.mod), verified against the package registries. The "registry" field reports "ok", "unreachable" or "error" (lookups incomplete — do not treat pass as clean), or "skipped".
Returns pass/fail with findings.
Requires SKYLOS_API_KEY: this tool returns an authentication error unless the MCP server is started with SKYLOS_API_KEY set. Without a key, analyze works (5 calls/day) and the local map tools (change_map and the graph_* tools) work with no limit. The local CLI needs no key: skylos verify <file> and skylos agent install-hooks.
Inputs: diff (required), path, policy, check_dependencies. Returns: result
verify_agentVerify an AI agent's guardrailsARead-only
Statically verify an AI agent's guardrails before deployment.
Deterministic, local pre-deployment agent verification: inventories LLM integrations, runs the defense checks (prompt-injection exposure, dangerous sinks, tool scope, output validation, PII filtering, cost controls), and returns scores, failed checks with remediation, OWASP LLM/Agentic coverage, and a reproducible attestation digest. No model is involved in the verdict and the analysis runs locally; source code is not sent to Skylos Cloud. Optional gate: set fail_on (severity) and/or min_score (0-100).
Requires SKYLOS_API_KEY: this tool returns an authentication error unless the MCP server is started with SKYLOS_API_KEY set. Without a key, analyze works (5 calls/day) and the local map tools (change_map and the graph_* tools) work with no limit. The local CLI needs no key: skylos verify <file> and skylos agent install-hooks.
Inputs: path, fail_on, min_score, owasp_version, +2 more. Returns: result
verify_changeVerify an edited file or rangeARead-only
Verify a changed file/range for AI-code defects and security bugs.
Returns a narrow, versioned JSON verdict containing AI-code trust findings such as hallucinated references, unfinished generated code, stale references, disabled controls, and dependency hallucinations (checked by default; pass include_dependency_hallucinations=False to skip the registry lookups), plus high/critical security findings (category "security") and hard-coded secrets (category "secret", values redacted) in the selected file/range. Pass include_security_findings=False to skip the security and secret checks.
Requires SKYLOS_API_KEY: this tool returns an authentication error unless the MCP server is started with SKYLOS_API_KEY set. Without a key, analyze works (5 calls/day) and the local map tools (change_map and the graph_* tools) work with no limit. The local CLI needs no key: skylos verify <file> and skylos agent install-hooks.
Inputs: file, path, confidence, line_range, +6 more. Returns: result
verify_dead_codeVerify dead code with an LLMARead-only
Ask an LLM to review selected unused function, class, import and variable candidates, with its reasoning.
Use it after analyze when you need fewer false positives before
deleting code. Sends code snippets and search results to the chosen
model provider, so it needs the skylos[llm] extra and provider
configuration, including credentials when required. Candidates outside
the review limits, or whose use remains uncertain, can remain
unverified. Does not edit files.
Refuses to run when the static analysis was incomplete.
Requires SKYLOS_API_KEY: this tool returns an authentication error unless the MCP server is started with SKYLOS_API_KEY set. Without a key, analyze works (5 calls/day) and the local map tools (change_map and the graph_* tools) work with no limit. The local CLI needs no key: skylos verify <file> and skylos agent install-hooks.
Inputs: path (required), model, confidence, max_verify, +2 more. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 24 tools
The individual descriptions are strong and often cross-reference each other (security_scan points to secrets_scan, architecture_check to quality_check), but several genuine overlaps remain: verify_change and validate_code_change both validate a change for security/secret problems, and analyze / health_score / verify_dead_code / generate_fix / remediate form a dead-code pipeline whose entry points are easy to confuse. The eight graph_*/change_map tools are more clearly delimited, but an agent must read long descriptions carefully to pick the right scan-vs-verify-vs-fix tool.
Mixed conventions: noun_verb (health_score, security_scan, quality_check, secrets_scan, architecture_check, provenance_scan), verb_noun (generate_fix, learn_triage, get_triage_suggestions, validate_code_change, verify_change, verify_agent, get_security_context, verify_dead_code), bare verbs (analyze, remediate), and a noun_verb graph family (graph_find, graph_show...). Everything is snake_case and readable, and the graph_ prefix groups that family well, but the verb-first/noun-first split is not predictable.
At 24 tools this sits at the heavy end; the graph_* family (7 tools) plus change_map is justified as a coherent subsystem, but the top-level scan/fix surface (security_scan, secrets_scan, quality_check, architecture_check, analyze, health_score, provenance_scan...) pushes the surface wider than most agents need at once and increases selection cost.
Coverage is broad and lifecycle-aware: detection (analyze, security_scan, secrets_scan, quality_check, architecture_check, provenance_scan), remediation (generate_fix, remediate), pre-land validation (validate_code_change, verify_change, verify_agent), triage learning, and a full codebase-graph navigation subsystem. Minor gaps exist around run management (results only via _result_uri resources, no listing/comparison tool) and no explicit baseline/suppression or policy-editing tool beyond get_security_context.
Maintenance
Related MCP Connectors
Zero-config MCP security scanner for AI-generated apps. 25K+ vulnerability patterns.
Code intelligence platform for AI agents. 20 tools for architecture, security & impact analysis.
Scan AI agent skills, MCP server packages and MCP configs before you install them. Static analysis.
FixMyPrompt is a remote MCP server for coding agents. It saves the steps your agent worked out as project memories and fetches them in later sessions, scores and rewrites prompts, and checks CLAUDE.md and AGENTS.md files. Works with Claude Code, Codex and Cursor. Free plan available.
Related MCP Servers
- AlicenseNot gradedqualityFmaintenanceA high-performance MCP server providing lightning-fast hybrid code search using TF-IDF and vector embeddings for AI assistants. It enables real-time codebase indexing and semantic retrieval with sub-50ms latency and offline support.12MIT

loctree-mcpofficial
FlicenseNot gradedqualityBmaintenanceStructural code intelligence for AI agents. Scan once, query everything — dead exports, circular imports, dependency graphs, and more. CLI + MCP server.10-- AlicenseAqualityAmaintenanceAI-powered codebase health analysis — detects dead code, circular dependencies, coupling issues, and architectural drift. 6 MCP tools for Claude Desktop, Cursor, Windsurf, and Slack.665 npmMIT
- FlicenseNot gradedqualityDmaintenanceGive your AI coding agents superpowers — a local MCP server for fast, token-efficient code navigation, search & analysis.-