IntruderSAFE
An MCP server to let AI agents control Intruder
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Let MCP clients like Claude and Cursor control Intruder. For more information and sample use cases, please see our blog post.
Installation
There are two ways to use the MCP server:
- Locally on your machine with Python
- In a Docker container
All of these methods require you to provide an Intruder API key. To generate a key, see the documentation.
Running Locally
Install uv if it isn't already present, and then clone this repository and run the following from the root directory:
uv venv uv pip install -e .
Then, add the following to your MCP client configuration, making sure to fill in your API key, and update the path to where you have cloned this repository:
{
"mcpServers": {
"intruder": {
"command": "uv",
"args": [
"--directory",
"path/to/intruder-mcp/intruder_mcp",
"run",
"server.py"
],
"env": {
"INTRUDER_API_KEY": "your-api-key"
}
}
}
}Running in a Container
Add the following to your MCP client configuration, making sure to fill in your API key:
{
"mcpServers": {
"intruder": {
"command": "docker",
"args": [
"container",
"run",
"--interactive",
"--rm",
"--init",
"--env",
"INTRUDER_API_KEY=",
"ghcr.io/intruder-io/intruder-mcp"
]
}
}
}de005f8bad5eOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add intruder-mcp --env INTRUDER_API_KEY=${INTRUDER_API_KEY} -- uvx intruder-mcp{
"mcpServers": {
"intruder-mcp": {
"command": "uvx",
"args": [
"intruder-mcp"
],
"env": {
"INTRUDER_API_KEY": "${INTRUDER_API_KEY}"
}
}
}
}Exposed tools (22)
14 read · 5 write · 3 destructive. Blast radius: 3 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
cancel_scan | read | |
create_scan | write | |
create_scan_schedule | write | |
create_target_tag | write | |
create_targets | write | |
delete_scan_schedule | destructive | |
delete_target | destructive | |
delete_target_tag | destructive | |
get_scan | read | |
get_scanner_output | read | |
get_status | read | Get the status of the Intruder API |
get_user | read | Get the current user of the Intruder API that we are authenticated as |
list_issues | read | |
list_licenses | read | |
list_occurrences | read | |
list_scan_schedules | read | |
list_scans | read | |
list_tags | read | |
list_targets | read | |
snooze_issue | read | |
snooze_occurrence | read | |
update_scan_schedule | write |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
delete_scan_schedule, delete_target, delete_target_tag
Gates applied: no_behavioural_pass.
de005f8bad5efull audit observations/trust-audit/mcp-server/intruder-io__intruder.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | de005f8bad5e | SAFE | B | 89 | first audit |
Questions
What is the Intruder MCP server?
An MCP server to let AI agents control Intruder
What tools does Intruder expose?
22 in total: 14 read-only, 5 that write, and 3 that can delete or overwrite (delete_scan_schedule, delete_target, delete_target_tag). Every one is listed on this page with its risk.
Is Intruder safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 3 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Intruder need?
It reads INTRUDER_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Intruder run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as intruder-mcp.
How current is this page?
The grade is for one exact copy of the source (de005f8bad5e), read on 2026-10-08. The repository is watched and re-audited when it changes.