結合テスト用。キーに JSON 値を保存する。
AI agents use dev-store-set to create or update resources in Local Context — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Local Context environment.
This tool stores or modifies data in a key-value store. It performs a reversible write operation (data can be overwritten or deleted by other means), making it a Write category tool. Severity is low because the blast radius is limited to local test data storage with no destructive, financial, or execute-level consequences. Confidence is high because the function is clearly described as a write/save operation.
From the tool's definition Tool description states: 'キーに JSON 値を保存する' (save JSON value to key), which is a create/modify operation. The 'dev-store-' prefix and sibling 'dev-store-get' indicate this is a key-value storage tool.
Attacks that exploit this kind of access
結合テスト用。キーに JSON 値を保存する。. It is categorised as a Write tool in the Local Context MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Local Context MCP server in PolicyLayer and add a rule for dev-store-set: 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-set is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the dev-store-set 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-set. 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-set 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 →