task_history
Query your recent task history and messages from the local database.
This record as markdown: /tools/cowork-os/task-history.md
What task_history does on CoWork OS
AI agents call task_history to retrieve information from CoWork OS without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why task_history is rated Low
This tool retrieves historical data with no side effects or reversible modifications. It is a straightforward read operation that queries existing data from a local database. The limited scope (personal task history and messages) and local-first nature further minimize risk.
From the tool's definition The tool performs a query operation on a local database to retrieve 'recent task history and messages' without any modification, deletion, or execution capability.
Attacks that exploit this kind of access
The rule that runs task_history safely
PolicyLayer is an MCP gateway: it sits between your AI agents and CoWork OS, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For task_history, this is the rule to start with:
task_history 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 CoWork OS, apply this rule, and every task_history call is checked against it from then on.
Questions about task_history
Query your recent task history and messages from the local database. It is categorised as a Read tool in the CoWork OS MCP Server, which means it retrieves data without modifying state.
Register the CoWork OS MCP server in PolicyLayer and add a rule for task_history: 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 CoWork OS. Nothing to install.
task_history 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 task_history 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 task_history. 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.
task_history is provided by the CoWork OS MCP server (CoWork-OS/CoWork-OS). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on CoWork OS, and thousands of servers like it.
This server
Across the catalogue