Shardflux
Persistent cloud workspaces for AI agents: run commands, edit files, use git and a browser.
The current version, v0.12.2, was published to the official MCP registry on 2026-10-08. It is distributed as @shardflux/mcp on npm and as a hosted remote over streamable-http, filed under Browser Automation by this index, and declares 11 environment variables. Removals and unreachable sources are measured across every server this index tracks, contract drift across the servers that answer in consecutive snapshots; the index's current counts put this record in context.
Using Shardflux in Claude, Cursor, Gemini CLI, Cline, or Zed?
MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).
Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less
uv tool install mcpindex-gate && mcpindex-config-wireSemantic screen found no manipulation pattern in the description. Conformance probe not yet run.
mcpindex.integrity.descriptionpassINFOevidence“Normal capability description”via static_description
- - Semantic screen only - the deterministic conformance probe has not run on this server
- - Confidence is reported but not yet calibrated (v1)
- - Screen reads the tool description, not the live behavior
- - advisory
- - registry description only no input schema
- - screen model 8b
- - The registry listing (version, packages, links) changed after this screen ran - the description we assessed did not
Semantic screen: an LLM judge reads the tool description for hidden instructions (status PARTIAL). A pass means the description is not lying, not that the tool is safe: a high-capability tool with an honest description still warrants caution. The deterministic conformance probe has not been run on this server yet, so the screen here is semantic-only. Posture: advisory. Confidences are reported but not yet calibrated (calibrated=false at v1). Full verdict history is not shown on this page.
Own this server? Test a description on the public screen → It is a separate check from the verdict above, so the two can differ.
That verdict was true at screening time (snapshot 2026-10-19).
Contracts can change after screening, with no version bump. The gate pins Shardflux’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.
See your first HOLD in 2 minutes →
Related: how to trust an MCP server · screen before install · silent contract drift
People vet a server before wiring it in. One line on your project site or docs answers that with an independent record: screening verdict, registry provenance, contract drift history. It stays current as new screens and drift events land.
[Independent trust record for Shardflux](https://mcpindex.ai/server/dev-shardflux-mcp) - screening verdict, registry provenance, and contract drift monitoring.<a href="https://mcpindex.ai/server/dev-shardflux-mcp">Independent trust record for Shardflux</a> - screening verdict, registry provenance, and contract drift monitoring.A live verdict badge for your README or listing. It reflects the current screen, links back here, and updates when the verdict does.
[](https://mcpindex.ai/server/dev-shardflux-mcp)<a href="https://mcpindex.ai/server/dev-shardflux-mcp"><img src="https://mcpindex.ai/api/v1/badge/dev-shardflux-mcp" alt="mcpindex verdict" height="20" /></a>SHARDFLUX_API_KEYScoped Shardflux project API key (sfk_<key id>_<secret>). Its tool permissions decide which workspace tools are listed.
SHARDFLUX_API_URLAPI base URL. Plain http:// is allowed only for loopback hosts.
SHARDFLUX_WORKSPACE_KEYPin one workspace: workspace_key becomes optional on every tool and any other key is refused (workspace_pinned).
SHARDFLUX_TEMPLATEDefault template slug for workspace_open.
SHARDFLUX_MCP_TOOL_TIMEOUT_MSDefault and maximum deadline per tool call in milliseconds (1000-3600000). A call's timeout_ms can only shorten it.
SHARDFLUX_WAKEon: workspace tools resume a suspended workspace and then run. off: they return the workspace_not_running refusal.
SHARDFLUX_WAKE_TIMEOUT_MSLongest wait per tool call for a workspace to wake or finish a transition, in milliseconds (1000-3600000; clamped to SHARDFLUX_MCP_TOOL_TIMEOUT_MS).
SHARDFLUX_AGENT_LABELAttribution label of every tool token this server obtains (shown as an agent session).
SHARDFLUX_MCP_LOG_LEVELLog level of the JSON log lines on stderr (stdout carries the protocol).
SHARDFLUX_HTTP_KEEPALIVEUnset: private HTTP/1.1 pooling on Node 26, native fetch elsewhere. 0: force connection closure for diagnosis. 1: select native pooling.
SHARDFLUX_PREWAKEOffer explicit workspace_hint for tool input streaming (on or off).
Publish, test and share browser games on PlayDrop from your AI agent.
Look up a FindMeTool page URL. Tool input stays in the browser.
Read-only web QA agent: scans a site in a real browser and returns evidence-backed findings