結合テスト用。キーに保存された JSON 値を取得する。
AI agents call dev-store-get to retrieve information from Local Context without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool's core function is to fetch stored data by key, analogous to a cache or key-value store lookup. There is no modification, deletion, or execution involved. The Japanese description 'キーに保存された JSON 値を取得する' translates to 'retrieves the JSON value stored at the key', confirming read-only semantics. Severity is low because retrieving test data poses minimal risk to system integrity.
From the tool's definition Tool description states it 'retrieves' (取得する) a JSON value stored at a key. This is a read-only retrieval operation with no side effects.
Attacks that exploit this kind of access
結合テスト用。キーに保存された JSON 値を取得する。. It is categorised as a Read tool in the Local Context MCP Server, which means it retrieves data without modifying state.
Register the Local Context MCP server in PolicyLayer and add a rule for dev-store-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 Local Context. Nothing to install.
dev-store-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 dev-store-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 dev-store-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.
dev-store-get is provided by the Local Context MCP server (obaratch/local-context-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 →