Skip to content
Agentmart
Submit a tool

Pentest-tools

MCP server for Pentest-Tools.com: run scans, manage findings and reports via your preffered LLM.

Connector by pentest-tools.comOfficial · Domain verified by the MCP Registry

IndexedGPL-3.0Remote (HTTP)★ 3
Write a review

Install

Works with Claude Code, VS Code, Cursor, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install connector/pentest-tools-com-mcp-server

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Remote endpoint

  • https://mcp.pentest-tools.com/mcp Remote (HTTP)

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

MCP server for Pentest-Tools.com: run scans, manage findings and reports via your preffered LLM.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
4 read · 8 write · 0 delete · 2 not yet classified
Secrets
None asked for
Install scripts
Nothing to install (hosted)
Runs as
Hosted (remote endpoint)

Tools by what they do 14

Read from the source code; the running server may list different tools.

Read 4 · Look things up without changing anything.

  • get_scans
  • get_targets
  • get_vpn_profiles
  • translate_report

Write 8 · Create, change, send or run things.

  • create_report
  • http_logger
  • import_findings
  • report
  • run_network_scanner
  • run_subdomain_finder
  • run_website_scanner
  • target

Not yet classified 2 · We could not tell from the name and description.

  • scan
  • workspace

Secrets and settings it asks for

Other settings (environment variables or headers).

  • Authorization

Network hosts it talks to 1

  • mcp.pentest-tools.com · found in remote endpoint, install command

Files it touches

  • Any path the agent passes to its tools

Tools (14)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • create_report

    Create a pentesting report, based on the findings already present in the platform. Args: format: The format in which to create the report. Possible values: pdf, html, json, csv, xlsx, docx. group_by: What key is used to create the report. Possible values: target, vulnerability. source: This is the source that is used to create the report. Possible values: scans, findings. resources: A list of ids, depeding on which source was chosen. If `scans` was chosed, then it's a list of scan_ids. If `findings` was chosed, then it's a list of finding_ids.

  • get_scans

    Retrieve scans from Pentest-Tools.com with optional filtering. Usage: - To get all scans: call with no extra parameters. - To filter by workspace: set workspace_id=<workspace id>. - To filter by target: set target_id=<target id>. - To filter by scan status: set status to one of the allowed values. - To limit results: set limit=<max number of scans>. - To paginate: set page=<page number>. - To filter by start time: set start_time as a StartTimeInterval dict (e.g. {"start": "...", "end": "..."}). Args: context: The MCP context object. workspace_id: (optional) ID of the workspace to sho…

  • get_targets

    Use this tool to get a list of targets from Pentest-Tools.com. Args: context: The MCP context object. workspace_id: (optional) ID of the workspace to show targets from. target_type: (optional) The type of target. Possible values: "hostname", "ip_address", "url". limit: (optional) The maximum number of targets to return. page: (optional) The page number to return. Returns: JSON string containing the list of targets matching the filters.

  • get_vpn_profiles

    Use this tool to get a list of vpn profiles from Pentest-Tools.com. Returns: JSON string containing the list of targets matching the filters.

  • http_logger

    Manage HTTP request loggers. Usage: - To create a new HTTP logger: call with verb="create", label="logger label", workspace_id=<optional workspace id>. - To delete an HTTP logger: call with verb="delete", logger_id=<logger id>, confirm="yes" (for non-interactive clients). - To clear all data for a logger: call with verb="clear", logger_id=<logger id>. Only set the parameters required for the verb you use. Args: verb: The action to perform. Must be one of: create, delete, clear. label: The label for the logger (required for create). logger_id: The ID of the logger (required for d…

  • import_findings

    Import multiple findings into Pentest-Tools.com. This is the only way to create new findings manually. Use this when you need to add findings that do not come from scans. Args: findings: A list of findings.

  • report

    Manage reports in Pentest-Tools.com. Usage: - To delete a report: verb="delete", report_id=<report id>, confirm="yes" (for non-interactive clients) - To get all reports: verb="get_all" - To get report information: verb="get_report_information_by_id", report_id=<report id> Only set the parameters required for the verb you use. Args: verb: The action to perform. Must be one of: delete, get_all, get_report_information_by_id. context: The MCP context object. report_id: The ID of the report (required for delete and get_report_information_by_id).

  • run_network_scanner

    Run a network scanner on the target hostname. `just_scan_ports` will only scan the selected ports to see which are open, nothing heavy. If someone requests `port_scanner`, this is the option to use. You can set port top only in custom mode. The scanning engines field is required when preset is custom.

  • run_subdomain_finder

    Discover all subdomains for the target domain. Use to enumerate subdomains for further scanning. Args: scan_type: The type of scan to perform. Possible values: "light", "deep", "custom". Default is "light". web_details: Whether to add web details or not. whois: Whether to perform whois or not unresolved_results: Whether to include results that do not DNS resolve or not search_methods: Methods to be used for discovery. All are used by default for a deep scan. For a custom scan, you need to specify at least one. max_scan_time: The maximum duration in minutes for the scan…

  • run_website_scanner

    Run a website scanner on the target URL, reporting progress/status updates. Args: target: The target URL to scan. scan_type: The type of scan to perform. Possible values: "light", "deep", "custom". Default is "light". attack_active: List of active attack modules to run. attack_passive: List of passive attack modules to run. discovery: List of discovery modules to run. spider: Spidering options as a dict. requests_per_second: Max requests per second (1-10000). Default is 100. workspace_id: The Workspace ID for the workspace the scan is going to be running in. …

  • scan

    Manage scans in Pentest-Tools.com. Usage: - To get the status of a scan: verb="get_status", scan_id=<scan id> - To get the raw output of a scan: verb="get_raw_output", scan_id=<scan id> - To get the parsed output of a scan: verb="get_output", scan_id=<scan id> - To start a scan by target id: verb="start_by_targetid", target_id=<target id>, tool_id=<tool id>, tool_params=<tool params> - To stop a scan: verb="stop", scan_id=<scan id> - To delete a scan: verb="delete", scan_id=<scan id>, confirm="yes" (for non-interactive clients) - To get a scan output of a scan: verb="get_scan_output_by_id", s…

  • target

    Manage targets in Pentest-Tools.com. Usage: - To add a new target: verb="add", name=<target name>, description=<optional>, workspace_id=<optional>. - To delete a target: verb="delete", target_id=<target id>, confirm="yes" (for non-interactive clients). Only set the parameters required for the verb you use. Args: verb: The action to perform. Must be one of: add, delete. context: The MCP context object. name: The name of the target to add (required for add). description: Description for the target (optional for add). workspace_id: Workspace ID to associate with the target …

  • translate_report

    Translate a report from English to the target language. IMPORTANT: This tool can only read and translate reports in JSON format. If you want to translate an existing report by report_id, that report must have been created with format="json". For PDF, HTML, or other formats, use `scans` or `findings` as input instead — the tool will create a new translated JSON report from those directly, without needing a pre-existing report. Args: report_id: The id of a JSON-format report to translate. Only one of `report_id`, `findings`, `scans` should be present. findings: The list of finding IDs …

  • workspace

    Everything you need to manage workspaces. Usage: - To create a workspace: call with verb="create", name="workspace name", description="optional description". - To delete a workspace: call with verb="delete", workspace_id=<id>, confirm="yes" (for non-interactive clients). - To edit a workspace: call with verb="edit", workspace_id=<id>, name="new name" (optional), description="new description" (optional). - To get all workspaces: call with verb="list". - To get a workspace by id: call with verb="get", workspace_id=<id>. Only set the parameters required for the verb you use.

Signals

Stars
3
Forks
0
Open issues
0
Last commit
Aug 3, 2026 (2 months ago)
Last release
Apr 24, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
com.pentest-tools/mcp-server
Version
0.1.13
Auth
Bearer token
License
GPL-3.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Cite this page

Pentest-tools MCP server. Agent Mart. https://agentmart.dev/connectors/pentest-tools-com-mcp-server (last updated 2026-10-24)