LeashIndex Get the report

Index / calendar

rstream CLI MCP

io-github-rstreamlabs-rstream declares 65 capabilities across 65 tools, with 2 critical issues. One of them, no-revocation, is recorded for every server in the index because MCP has no field in which to declare a way to switch a tool off; a missing declaration is not evidence that the control is missing.

99/100 exposureHigh exposure

Manifest recorded 2026-11-04 from tools/list answered by the container image docker.io/rstream/rstream version 1.36.4 (published as the image docker.io/rstream/rstream:1.36.4, listed in the official MCP registry as io.github.rstreamlabs/rstream 1.36.4), 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 65 tools

65 of 65 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 · destructive-uncapped · 18 of 65 tools

18 tools are annotated by the server as destructive (destructiveHint) and declare no limit. In MCP that annotation marks a tool that may make destructive changes rather than only additive ones; it does not say the change cannot be undone.

high · no-expiry · All 65 tools

65 of 65 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 65 tools

65 of 65 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 · 11 of 65 tools

11 tools can modify data and declare no limit.

low · uncapped-read · 36 of 65 tools

36 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
rstream_auth_startwrite assumed
rstream_auth_polldestructive declared
rstream_context_listread declared
rstream_context_getread declared
rstream_project_creation_optionsread declared
rstream_project_createwrite inferred
rstream_project_updatedestructive declared
rstream_project_deletedestructive declared
rstream_project_listread declared
rstream_project_logsread declared
rstream_project_events_listread declared
rstream_project_webhooks_listread declared
rstream_project_webhook_deliveries_listread declared
rstream_project_webhook_delivery_getread declared
rstream_project_usageread declared
rstream_project_plan_getread declared
rstream_project_turn_usageread declared
rstream_project_turn_credentials_createwrite inferred
rstream_project_domains_listread declared
rstream_project_domain_createwrite inferred
rstream_project_domain_getread declared
rstream_project_domain_deletedestructive declared
rstream_project_domain_verifyread inferred
rstream_project_domain_connectread declared
rstream_project_tcp_addresses_listread declared
rstream_project_tcp_address_reservewrite assumed
rstream_project_tcp_address_releasedestructive declared
rstream_project_settings_getread declared
rstream_project_settings_patchdestructive declared
rstream_project_settings_resetdestructive declared
rstream_local_tunnel_exposewrite assumed
rstream_local_tunnel_listread declared
rstream_local_tunnel_stopdestructive declared
rstream_remote_exposewrite assumed
rstream_remote_expose_stopdestructive declared
rstream_remote_mcp_discoverread declared
rstream_remote_mcp_toolsread declared
rstream_remote_mcp_calldestructive declared
rstream_runtime_preparedestructive declared
rstream_runtime_statusread declared
rstream_token_createwrite inferred
rstream_workspace_listread declared
rstream_workspace_members_listread declared
rstream_webtty_listread declared
rstream_webtty_servers_listread declared
rstream_webtty_server_getread declared
rstream_webtty_server_createwrite inferred
rstream_webtty_server_updatedestructive declared
rstream_webtty_server_deletedestructive declared
rstream_webtty_server_enrollment_getread declared
rstream_webtty_execdestructive declared
rstream_webtty_sessions_listread declared
rstream_webtty_session_getread declared
rstream_webtty_session_eventsread declared
rstream_webtty_session_exportread declared
rstream_webtty_session_participantsread declared
rstream_webtty_control_requests_listread declared
rstream_webtty_control_request_createwrite inferred
rstream_webtty_control_request_resolvedestructive declared
rstream_webtty_fs_downloaddestructive declared
rstream_webtty_fs_listread declared
rstream_webtty_fs_readread declared
rstream_webtty_fs_writedestructive declared
rstream_webtty_fs_mkdirwrite inferred
rstream_webtty_fs_deletedestructive declared
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.