AI agents call get_test_runs to retrieve information from Mcp Jama without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves test run information from JAMA Cloud without modifying any data. The operation is a simple query with pagination, characteristic of Read category tools. Blast radius is minimal—incorrect usage returns stale or filtered data but cannot corrupt or delete records.
From the tool's definition Tool name 'get_test_runs' and description indicate retrieval of test run data (テストランデータを取得). No mutations, deletions, or external operations are described. Parameters suggest pagination ('start_at' to iterate), typical of read-only list operations.
Attacks that exploit this kind of access
テストサイクルのテストラン一覧を取得する（最大50件）。全件取得は start_at を増やして繰り返す。. It is categorised as a Read tool in the Mcp Jama MCP Server, which means it retrieves data without modifying state.
Register the Mcp Jama MCP server in PolicyLayer and add a rule for get_test_runs: 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 Mcp Jama. Nothing to install.
get_test_runs 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_test_runs 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_test_runs. 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_test_runs is provided by the Mcp Jama MCP server (keisukeshima/mcp-jama). 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 →