alm_search
AI agents call alm_search to retrieve information from HP ALM MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'search' operation in the context of HP ALM/Quality Center typically retrieves test cases, defects, requirements, or other QA artifacts. No side effects or modifications are implied. Confidence is slightly reduced due to the empty description, which prevents direct confirmation of scope and behavior, but the naming convention and server context strongly indicate a read-only query tool.
From the tool's definition Tool name 'alm_search' indicates a search/query operation. The description is empty, but the name and context of a QA management system suggest data retrieval without modification.
Attacks that exploit this kind of access
alm_search. It is categorised as a Read tool in the HP ALM MCP Server MCP Server, which means it retrieves data without modifying state.
Register the HP ALM MCP Server MCP server in PolicyLayer and add a rule for alm_search: 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 HP ALM MCP Server. Nothing to install.
alm_search 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 alm_search 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 alm_search. 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.
alm_search is provided by the HP ALM MCP Server MCP server (uditmahaldar/opentext-alm-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 →