This record as markdown: /tools/7836246-claude-team-mcp/history-get.md
What history_get does on Claude Team MCP
AI agents call history_get to retrieve information from Claude Team MCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why history_get is rated Low
This tool retrieves and reads historical collaboration records. It performs a query operation to fetch existing data about past interactions between AI models. There is no indication of data modification, deletion, execution of code, or financial impact. The action is read-only and informational, making it a Read category tool with low severity.
From the tool's definition Tool name 'history_get' and description '获取某次协作的详细记录' (Get detailed records of a collaboration session) indicate retrieval of historical data without modification or side effects.
Attacks that exploit this kind of access
The rule that runs history_get safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Claude Team MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For history_get, this is the rule to start with:
history_get 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 Team MCP, apply this rule, and every history_get call is checked against it from then on.
Questions about history_get
获取某次协作的详细记录. It is categorised as a Read tool in the Claude Team MCP MCP Server, which means it retrieves data without modifying state.
Register the Claude Team MCP server in PolicyLayer and add a rule for history_get: 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 Team MCP. Nothing to install.
history_get 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 history_get 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 history_get. 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.
history_get is provided by the Claude Team MCP server (7836246/claude-team-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Claude Team, and thousands of servers like it.
This server
Across the catalogue