MCP ZAP Server
Give AI agents a safe, self-hosted ZAP operator for guided web security scans, findings, reports, and production guardrails.
Note This project is not affiliated with or endorsed by the ZAP project. It is an independent implementation.
mcp-zap-server exposes ZAP through MCP over streamable HTTP so agentic tools can run operator-controlled security workflows without brittle glue scripts or unsafe scanner access.
Use it when you want:
- safe agentic scanning with guided defaults for spider, active scan, passive scan, API imports, findings, and reports
- operator control through API-key or JWT auth, tool scopes, runtime policy bundles, rate limits, and audit events
- self-hosted deployment with Docker Compose for local adoption and Helm for Kubernetes
- expert ZAP access when you intentionally need lower-level ZAP context, user, scan, and report controls
Full documentation: danieltse.org/mcp-zap-server
Watch the demo: browser demo or YouTube
Quick Start
Prerequisites:
- Docker 20.10+
- Docker Compose v2 (
docker compose)
- your own MCP client with Streamable HTTP and custom-header support
git clone https://github.com/dtkmn/mcp-zap-server.git
cd mcp-zap-server
./bin/bootstrap-local.sh
./dev.sh
./bin/self-serve-doctor.sh
Those scripts are the supported local happy path, not hidden magic:
bootstrap-local.sh creates .env, generates local API keys, and prepares the ZAP workspace.dev.sh starts the Docker Compose stack with the faster JVM image.self-serve-doctor.sh checks Docker, auth, MCP initialize, tools/list, guided tools, and a harmless tool call.
The JVM image remains Java 25 end to end: source compilation, bytecode, and
runtime all target Java 25. Its final runtime is distroless, so it intentionally
contains no shell, package manager, or curl. A small built-in HTTP probe keeps
the normal Docker Compose health status; docker compose ps still reports the
MCP service as (healthy) after startup.
Connect your MCP client:
The stack runs the MCP server, ZAP, and demo targets. Install and configure
your preferred MCP client separately.
When scanning the bundled demo targets, use the container URLs that ZAP can
reach from inside Compose:
- Juice Shop scan target:
http://juice-shop:3000
- Petstore scan target:
http://petstore:8080
After connecting, try this first prompt:
Use the guided ZAP tools to crawl http://juice-shop:3000. Wait for the crawl
and passive analysis to finish, show a findings summary, generate an HTML
report, and read it back through MCP. Do not run an active scan.
Expect a completed crawl, a findings summary, and a report the client can
read. Finding counts vary; a connection or scan error is not a clean result.
The default Compose stack publishes host ports on 127.0.0.1 only. Set MCP_ZAP_BIND_ADDRESS=0.0.0.0 only when you intentionally expose the stack behind trusted network controls.
Client setup:
There are two independent authentication layers. The API key or JWT lets
Cursor call MCP ZAP Server. An optional target-auth profile lets ZAP log in to
an application you are authorized to scan. Most first runs need only the MCP
API key; never put a target website password in Cursor or an MCP prompt.
This repository includes MCP Registry metadata in .mcp/server.json.
Use metadata from the same version as the image you deploy. The image includes
the MCP server name expected by registry and catalog tooling. Check
GitHub Releases and the
release workflow before installing a versioned image or publishing its package
metadata; repository metadata alone is not proof of image availability.
Docker Compose remains the easiest installation path because the MCP server is designed to operate with a ZAP sidecar and explicit auth keys. The OCI package metadata is for advanced standalone installs where ZAP is already running and reachable from the MCP container.
What You Get
- Guided scans: intent-first tools for spider, active scan, passive scan, API imports, findings, reports, and scan history.
- Expert ZAP control: optional lower-level tools for advanced ZAP context, user, scan, and report workflows.
- Authentication: API key mode by default, optional JWT mode with refresh and revocation support.
- Runtime policy bundles: dry-run and enforcement support through
zap_policy_dry_run and policy-mode configuration.
- Scan queue and history: queued active, spider, and AJAX Spider jobs with claim-based recovery, durable Postgres state, and evidence export.
- Extension contracts: experimental policy, protection, evidence metadata, and extension metadata APIs with sample extension packaging.
- Operational guardrails: request body limits, rate limits, workspace quotas, tool-scope authorization, structured logs, metrics, and audit events.
- Deployment paths: local Docker Compose, published JVM container images, and Helm charts for Kubernetes.
Latest Release
See GitHub Releases
for the latest published version and its publication date. Version-specific
documentation describes that version's behavior; it does not announce image
availability. Deploy only after the corresponding release workflow succeeds
and the versioned image is available in your registry.
Version v0.12.0 improves scan queue waiting, cancellation, and cleanup, and
uses ZAP node identity for findings. Before upgrading, review the PostgreSQL
V7/V8 migrations, snapshot v2 compatibility, and timeout changes in the release
notes.
Security Defaults
The default posture is intentionally conservative:
api-key mode is the base runtime default.none mode is for explicit local dev/test only.- Docker Compose binds published ports to loopback by default.
- The Java 25 JVM image uses a digest-pinned distroless runtime with no shell or
package manager; debug it through logs, metrics, and external diagnostic
containers rather than installing tools into the application container.
- URL validation blocks localhost, private networks, and link-local targets by default.
- Target authentication is optional and profiles default to an empty list. When enabled, guided auth binds an exact server-side credential reference and login settings to one approved origin; callers provide only
profileId and targetUrl.
- Public auth exchange endpoints are rate-limited.
- MCP request bodies have a hard early size cap.
Production and shared deployments should review:
Architecture
flowchart LR
Client["Your MCP Client"] -->|"MCP over Streamable HTTP"| MCP["MCP ZAP Server"]
MCP -->|"ZAP API"| ZAP["ZAP"]
ZAP -->|"scan"| Target["Authorized target app"]
MCP -->|"reports / findings / history"| Evidence["Evidence + reports"]
For multi-replica queueing, durable Postgres state, claim recovery, and ingress affinity, use the operations docs instead of this README:
Extension Model
ZAP is the first scanner engine, not the whole product boundary. The current
public extension work is intentionally small:
This is not runtime multi-engine support yet. Additional scanner engines need
an adapter design and explicit fail-closed capability boundaries before they
become product claims.
Documentation Map
Start here:
Scanning:
Operations:
Open Source Core And Extension Model
mcp-zap-server is the Apache-2.0-licensed open-source core. It is intended to be useful on its own for self-hosted MCP and ZAP workflows.
Private or enterprise capabilities may be built as separate extensions around this core. Those extensions are not required to run the OSS project, and enterprise implementation code is not shipped in this repository.
The boundary is intentional:
- this repository remains the public OSS distribution
- extension points should be documented and kept stable where practical
- private extensions must not weaken the security, licensing, or usability of the OSS core
- security scanning and open-source program entitlements for this repository apply only to this public project
Contributing And Support
If this project saves you time or becomes part of your security workflow, you can sponsor the maintainer to support ongoing maintenance.
Agentic Lab offers optional paid support for teams adopting the public core in production. Commercial support is separate from the Apache-2.0-licensed OSS distribution, and the public core should remain usable without private extensions or paid services.
Contact Agentic Lab
License
Apache License 2.0. Copyright 2025-2026 Daniel Tse. See LICENSE.