get_strategy
AI agents call get_strategy to retrieve information from Oblique Strategies MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves creative strategy prompts from the Oblique Strategies deck. It has no side effects, does not modify data, execute code, delete content, or commit financial obligations. It is a pure read operation that queries the strategy card collection. The lack of tool description reduces confidence slightly, but sibling tools and server purpose confirm the retrieval-only nature.
From the tool's definition Tool name 'get_strategy' with sibling tool 'search_strategies' and 'list_editions' indicates this retrieves strategy cards from a deck. Server purpose is to 'retrieving random prompts from various editions'.
Attacks that exploit this kind of access
get_strategy. It is categorised as a Read tool in the Oblique Strategies MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Oblique Strategies MCP Server MCP server in PolicyLayer and add a rule for get_strategy: 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 Oblique Strategies MCP Server. Nothing to install.
get_strategy 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 get_strategy 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 get_strategy. 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.
get_strategy is provided by the Oblique Strategies MCP Server MCP server (lmorchard/oblique-strategies-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →