SafeWeave

dev.safeweavePublished by safeweave.devOfficial publisherv0.7.5Updated Oct 27, 2026

Security scanner for AI-written code: SAST, secrets, dependencies, IaC, containers and DAST.

VerifiedStreamable HTTPWeb executableDeveloper ToolsSecurity & Monitoring

Overview

AI-generated overview

SafeWeave is a security scanner for AI-written code that lets an assistant scan a project for vulnerabilities, leaked secrets, risky dependencies, IaC and…

What you can do
  • Scan source code for vulnerabilities such as SQL injection, XSS, SSRF and insecure crypto
  • Detect hardcoded secrets, API keys, tokens and private keys in source
  • Check npm, pip, Go and Cargo dependencies for known CVEs and risky licenses
  • Scan Terraform, Dockerfile and Kubernetes configs, container images and API posture
  • Apply compliance profiles such as standard, hardened, owasp, soc2, pci-dss or hipaa
  • Run runtime DAST scans against a running app on paid cloud plans
When to use it
Useful when you want an assistant to check code it or you just wrote before committing, pushing or opening a pull request, and to fix the findings in the same turn. Also suited to routine dependency, secret and infrastructure-configuration checks inside an MCP-capable editor.
Requirements
Runs as a remote endpoint or as a local npm package (safeweave-mcp) via npx, or via Docker with SSE. OAuth is declared as required; a SAFEWEAVE_LICENSE_KEY is optional (10-scan trial without one, free account for 7 local scanners, paid plans for DAST and hosted scans). Scanner binaries are downloaded on first use, so internet access is needed; macOS, Linux and Windows x64 are supported.
Before you install
The server downloads and runs third-party scanner binaries (gitleaks, trivy, opengrep) into a local cache, so review that behavior before use. Scans read your project directory, and cloud plans send scan data to hosted services. The optional Claude Code skill can run scans automatically before git commit, push or PR creation and may block pushes on critical or high findings. Paid plans cost $29 or $59 per month.

Installation

In SourceWeft

  1. Open SafeWeave in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/dev.safeweave%2Fsafeweave/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "safeweave": {
      "type": "http",
      "url": "https://mcp.safeweave.dev/mcp"
    }
  }
}

README

SafeWeave

Security scanner for AI-written code. SafeWeave runs inside your AI editor over MCP (Claude Code, Cursor, VS Code, Windsurf) and checks your code for vulnerabilities, leaked secrets, risky dependencies, IaC and container issues, so your assistant can fix findings in the same turn.

This repository is the open-core part of SafeWeave: the scanner engines (packages/scanners), the scan gateway (packages/gateway), shared types (packages/common), Docker files and the Claude Code skill. The MCP server itself ships on npm.

Quick Start

Run one command. It downloads the scanners and configures every editor it finds:

bash
npx -y safeweave-mcp

Or add it to your editor's MCP config yourself:

json
{  "mcpServers": {    "safeweave": {      "command": "npx",      "args": ["-y", "safeweave-mcp"],      "env": {        "SAFEWEAVE_LICENSE_KEY": "your-license-key-here"      }    }  }}

The key is optional. Without one you get a 10-scan trial (SAST, secrets and dependencies). A free account at safeweave.dev/signup unlocks unlimited local scans with 7 scanners.

Plans

PlanPriceWhere scans runScanners
No keyFreeLocal, 10-scan trial3 (SAST, secrets, dependencies)
Free accountFreeLocal7 (everything except DAST)
Cloud$29/moLocal + hostedAll 8, plus PR checks, website scans and AI-builder rules
Cloud Plus$59/moLocal + hostedAll of Cloud, plus teammates

See safeweave.dev/pricing for details.

Alternative: Docker

If you prefer running via Docker:

bash
git clone https://github.com/nickfluxk/safeweave.gitcd safeweavecp .env.example .env   # Edit with your license key and SCAN_DIRdocker compose up

How Scanner Binaries Work

SafeWeave automatically downloads and manages the scanner binaries it needs on first use.

ToolVersionPurpose
gitleaks8.21.2Secret and credential detection
trivy0.58.0Container vulnerability and IaC misconfiguration scanning
opengrep1.16.3SAST analysis (Semgrep-compatible, standalone binary)
  • Binaries are resolved in order: system PATH → ~/.safeweave/bin/ cache → auto-download
  • If you already have gitleaks or trivy installed via Homebrew/apt, those are used (never shadowed)
  • For SAST, system semgrep is preferred; if not found, opengrep (a standalone Semgrep-compatible fork) is downloaded — no Python required
  • Downloads happen in the background at startup — the server is ready immediately
  • Versions are pinned and updated with each SafeWeave release
  • If a download fails (no internet), that scanner is skipped gracefully

Supported platforms: macOS (arm64, x64), Linux (arm64, x64), Windows (x64)

Cache location:

~/.safeweave/  bin/       # Downloaded binaries  meta/      # Version metadata (JSON)

To force a re-download: rm -rf ~/.safeweave/bin ~/.safeweave/meta

What's Included

ScannerWhat it detectsPlan
SASTSQL injection, XSS, SSRF, path traversal, insecure cryptoFree
SecretsAPI keys, tokens, passwords and private keys in sourceFree
DependenciesKnown CVEs in npm, pip, Go and Cargo packagesFree
IaCTerraform, Dockerfile and Kubernetes misconfigurationsFree account
ContainerVulnerabilities in container imagesFree account
LicenseGPL, AGPL and other risky dependency licensesFree account
PostureMissing auth, rate limiting, CORS and security headersFree account
DASTRuntime API security issues in a running appCloud

MCP Integration

Works with any MCP-compatible editor — Cursor, Claude Code, VS Code, Windsurf, and more.

Once configured (see Quick Start above), ask your AI:

  • "Scan this project for security vulnerabilities"
  • "Check my dependencies for CVEs"
  • "Scan for hardcoded secrets"
  • "Run an IaC misconfiguration scan"

If running via Docker, use the SSE transport instead:

json
{  "mcpServers": {    "safeweave": {      "url": "http://localhost:9000/sse"    }  }}

HTTP API

Health Check

bash
curl http://localhost:9000/api/health

Run a Scan

bash
curl -X POST http://localhost:9000/api/scan \  -H 'Content-Type: application/json' \  -d '{"directory": "/path/to/project"}'

Scan Specific Scanners

bash
curl -X POST http://localhost:9000/api/scan \  -H 'Content-Type: application/json' \  -d '{"directory": "/path/to/project", "scanners": ["sast", "secrets"]}'

Compliance Profiles

Built-in profiles: standard, hardened, owasp, soc2, pci-dss, hipaa

Set via MCP set_profile tool or create a custom .safeweave/profile.yaml in your project.

Configuration

Environment Variables

VariableRequiredDescription
SAFEWEAVE_LICENSE_KEYNoYour license key from safeweave.dev. Without it: a 10-scan trial
SCAN_DIRDocker onlyHost directory to mount for scanning
SAFEWEAVE_LICENSE_URLNoLicense server URL (defaults to https://license.safeweave.dev)

Claude Code Skill: Auto-Scan Before Push

SafeWeave includes a Claude Code skill that automatically scans your code before every git commit, git push, or PR creation.

Install the skill

Copy the skill to your Claude Code skills directory:

bash
mkdir -p ~/.claude/skills/secure-before-pushcurl -sL https://raw.githubusercontent.com/nickfluxk/safeweave/main/skills/secure-before-push/SKILL.md \  -o ~/.claude/skills/secure-before-push/SKILL.md

Or clone and copy:

bash
git clone https://github.com/nickfluxk/safeweave.git /tmp/safeweavecp -r /tmp/safeweave/skills/secure-before-push ~/.claude/skills/

What happens after install

Once installed, Claude Code automatically runs a SafeWeave scan whenever you say "commit", "push", "ship it", or "create a PR":

SeverityActionBlocks push?
Critical / HighFix immediately, re-scanYes
MediumWarns, asks confirmationUser decides
Low / InfoNo actionNo

Prerequisites

SafeWeave MCP server must be configured. Run npx safeweave-mcp to set it up automatically.

Verify

Start a new Claude Code session and ask it to commit code. You should see a SafeWeave scan run before the git operation.

License

MIT. See LICENSE.

Source: README.md at commit 8cb96a9

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

2
  1. v0.7.5LatestOct 20, 2026
  2. v0.7.4Oct 19, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts