
Gadriel AI Security Harness
io.github.Gadriel-aiPublished by GitHub account Gadriel-aiv1.7.1Updated Oct 29, 2026
AI Security Harness: SAST, secrets, deps, containers, config & OWASP LLM. Scans locally.
Overview
Local security scanner MCP server that lets an assistant run SAST, secrets, dependency, container and config scans on a repository and review findings.
- What you can do
- Run security scans on files or in-memory buffers and get findings back
- Look up findings for a given path and apply fixes to a finding
- Cover static analysis, hardcoded secrets, dependencies (SCA/SBOM), containers, configuration and OWASP LLM risks
- Pair with optional repository instructions, prompts and reviewer agents for guided scan, fix and status workflows
- When to use it
- Useful when you want an assistant to check code it just wrote or an existing repository for security issues without leaving the chat, and to walk through and fix the findings it reports.
- Requirements
- Runs locally over stdio via npx from the gadriel npm package, so Node.js is needed (or a global install). Desktop-only; no account or API key is declared. First run contacts app.gadriel.ai for anonymous device registration unless GADRIEL_NO_ANONYMOUS_AUTH is set to 1.
Installation
In SourceWeft
- Open Gadriel AI Security Harness in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
Gadriel — AI Security Harness for GitHub Copilot
Security scanning for the code Copilot writes: SAST, secrets, dependencies (SCA/SBOM), containers and configuration, including AI-specific risks like prompt injection and the OWASP LLM Top 10 — 3,000+ rules, scanned on your machine. Gadriel plugs into Copilot as an MCP server plus repository instructions, prompts, and reviewer agents.
Product Overview · Documentation · MCP Tools Reference · SAST Benchmarks
Part of the Gadriel AI Security Harness, alongside VS Code, Claude Code, Codex, and Cursor.
Get it
Easiest — the VS Code extension. Install
Gadriel AI Security Harness
from the Marketplace. It registers the gadriel MCP server for Copilot
automatically and adds a Gadriel: Scan Repository command — no config to
edit.
Or add the MCP server yourself. The server is published to the
GitHub MCP Registry as
io.github.Gadriel-ai/gadriel, so it shows up in VS Code's MCP: Browse
Servers and Copilot Chat's @mcp search — add it in a click. To wire it
per-repo instead, drop this .vscode/mcp.json into your project (needs Node for
npx, or npm install -g gadriel):
Add the Copilot guidance (optional). Copy the .github/ directory into your
repo so Copilot knows how to use Gadriel:
Use
In Copilot Chat (agent mode), just ask: "Run a Gadriel security scan on this
repo and summarize the findings," or invoke a prompt like /gadriel-scan. The
gadriel MCP tools — validate_file, findings_for_path, fix_finding,
validate_buffer, and more — are available to Copilot directly.
Good to know
- No automatic edit guardrail here. Copilot/VS Code has no edit-time hook (Cursor and Codex do), so scanning runs on request via the MCP tools and prompts rather than blocking each edit.
- Enterprise: Copilot Business/Enterprise can allowlist the
gadrielMCP server through managed MCP policy. - Privacy: code is scanned locally and never uploaded. First run registers
an anonymous device credential with
app.gadriel.ai(a random device id — no hostname, username, or keys); setGADRIEL_NO_ANONYMOUS_AUTH=1to skip. See the privacy policy.
Maintainers
The registry listing is (re)published by .github/workflows/publish-mcp.yml
(GitHub OIDC — an org namespace can only be published from CI in a Gadriel-ai
repo). After a new gadriel npm release, bump server.json and the
.vscode/mcp.json pin, then re-run that workflow.
License
This repository is Apache-2.0. The gadriel scanner it runs is
proprietary, under the Gadriel terms.
Source: README.md at commit fcdb0f6
Tools
0Version history
4- v1.7.1LatestOct 29, 2026
- v1.7.0Oct 8, 2026
- v1.5.0Oct 1, 2026
- v1.4.1Sep 17, 2026
Score
50% 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 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- 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