browser_session_replay
Load a recorded session trajectory and return its steps so the caller can dispatch them through the 23 browser_* tools. Does NOT itself drive the browser — replay execution is caller-orchestrated to keep this tool a primitive (ADR-0001 §7). Use when native WebFetch is wrong because you need real ...
This record as markdown: /tools/io-github-ruvnet-claude-flow/browser-session-replay.md
What browser_session_replay does on Claude Flow
AI agents call browser_session_replay to retrieve information from Claude Flow without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why browser_session_replay is rated Low
This tool is a data retrieval primitive that loads and returns recorded browser session trajectories. While it facilitates browser automation workflows (which could be execute-level when combined with browser_* tools), the tool itself performs no side effects—it only reads and returns stored session data. The architectural design (ADR-0001 §7) deliberately keeps this as a 'primitive' that does not execute.
From the tool's definition Tool description states it 'Load[s] a recorded session trajectory and return[s] its steps' and explicitly 'Does NOT itself drive the browser — replay execution is caller-orchestrated.' It retrieves and returns recorded session data without modifying,…
Attacks that exploit this kind of access
The rule that runs browser_session_replay safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Claude Flow, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For browser_session_replay, this is the rule to start with:
browser_session_replay is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Claude Flow, apply this rule, and every browser_session_replay call is checked against it from then on.
Questions about browser_session_replay
Load a recorded session trajectory and return its steps so the caller can dispatch them through the 23 browser_* tools. Does NOT itself drive the browser — replay execution is caller-orchestrated to keep this tool a primitive (ADR-0001 §7). Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions, AIDefence PII gating before content reaches Claude. For static HTML pages, native WebFetch is faster and free. It is categorised as a Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.
Register the Claude Flow MCP server in PolicyLayer and add a rule for browser_session_replay: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Claude Flow. Nothing to install.
browser_session_replay is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the browser_session_replay rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for browser_session_replay. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
browser_session_replay is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Claude Flow, and thousands of servers like it.
This server
Across the catalogue