LeashIndex Get the report

Index / storage

Agent360 Browser MCP

io-github-agent360dk-browser-mcp declares 40 capabilities across 40 tools, with 2 critical issues.

89/100 exposureHigh exposure

Manifest recorded 2026-10-15 from tools/list answered by the npm package @agent360/browser-mcp@1.30.3 (published to npm as @agent360/browser-mcp, listed in the official MCP registry as io.github.Agent360dk/browser-mcp 1.30.3), run in an isolated container with no network access and no credentials. The date changes only when the manifest does. Not verified by a maintainer.

Issues

These describe what this server's manifest declares. A product can provide controls that MCP has no way to express — token revocation, an admin console, audit logs — and this page cannot see them. The absence of a declaration is not evidence that a control is absent.

critical · no-revocation · All 40 tools

40 of 40 tools declare no way for the customer to switch them off once granted. This applies to every tool because MCP has no field in which to declare a revocation mechanism; the product may provide one outside MCP that a manifest cannot show.

critical · irreversible-uncapped · 2 of 40 tools

2 tools are classified as irreversible and declare no limit.

high · no-expiry · All 40 tools

40 of 40 tools declare no expiry. This applies to every tool because MCP has no field in which to declare an expiry; the product may provide one outside MCP that a manifest cannot show.

high · no-audit-trail · All 40 tools

40 of 40 tools declare no record of their actions that the customer can read. This applies to every tool because MCP has no field in which to declare an audit requirement; the product may provide one outside MCP that a manifest cannot show.

high · uncapped-write · 26 of 40 tools

26 tools can modify data and declare no limit.

low · uncapped-read · 12 of 40 tools

12 tools can read data and declare no limit.

Declared capabilities

How each tool was read. declared means the server's own annotation said so — self-reported and unverified. inferred is from the tool's name. assumed means nothing indicated either way.

ToolRead asBasis
browser_navigatewrite assumed
browser_get_page_contentread inferred
browser_extract_listread inferred
browser_screenshotwrite assumed
browser_execute_scriptwrite assumed
browser_double_clickread inferred
browser_right_clickwrite assumed
browser_click_xywrite assumed
browser_reattach_debuggerwrite assumed
browser_clickwrite assumed
browser_fillwrite assumed
browser_press_keywrite assumed
browser_scrollwrite assumed
browser_waitwrite assumed
browser_hoverwrite assumed
browser_select_optionwrite assumed
browser_dismiss_overlayswrite inferred
browser_set_comboboxwrite inferred
browser_drop_filedelete inferred
browser_set_datewrite inferred
browser_handle_dialogwrite assumed
browser_wait_for_networkwrite inferred
browser_fetchread inferred
browser_list_tabsread inferred
browser_get_cookiesread inferred
browser_get_local_storageread inferred
browser_set_cookieswrite inferred
browser_set_local_storagewrite inferred
browser_console_logsread inferred
browser_ask_userwrite assumed
browser_list_framesread inferred
browser_select_framewrite assumed
browser_get_new_tabread inferred
browser_switch_tabwrite assumed
browser_close_tabdelete inferred
browser_upload_filewrite inferred
browser_extract_tokenwrite assumed
browser_solve_captcharead inferred
browser_aboutread inferred
browser_provide_feedbackwrite assumed

Record history

Earlier records for this server. A correction is added here, never written over the record it corrects.

RecordedExposureSource
2026-10-1489 tools/list answered by the npm package @agent360/browser-mcp@1.30.2 (published to npm as @agent360/browser-mcp, listed in the official MCP registry as io.github.Agent360dk/browser-mcp 1.30.2), run in an isolated container with no network access and no credentials
2026-10-1188 tools/list answered by the npm package @agent360/browser-mcp@1.30.1 (published to npm as @agent360/browser-mcp, listed in the official MCP registry as io.github.Agent360dk/browser-mcp 1.30.1), run in an isolated container with no network access and no credentials
Answering this question about your own agent? The self-serve stack report applies the same reading to your own stack or server and gives you a dated document you can hand to a customer's security review. It is generated in your browser, with nobody to wait for. Buying one does not change this page, its score or its place in the index — see Independence.
Maintain this server? If this page misreads your manifest, or your server has changed, submit its current tools/list response and it will be re-scored and dated. Corrections are published alongside the original, not in place of it.