resolve_keyword_call
AI agents call resolve_keyword_call to retrieve information from RobotWS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The description is empty, so classification is based on the name alone. 'Resolve' implies a lookup or query operation to find or determine what a keyword call maps to in the indexed Robot Framework files. This is consistent with the sibling tools (find_keyword_callers, find_taf_library_usage) which appear to be read/search operations. No evidence of write, execute, or destructive behavior.
From the tool's definition Tool name 'resolve_keyword_call' suggests resolving/looking up a keyword call, likely a read/query operation against the SQLite index.
Attacks that exploit this kind of access
resolve_keyword_call. It is categorised as a Read tool in the RobotWS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the RobotWS MCP Server MCP server in PolicyLayer and add a rule for resolve_keyword_call: 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 RobotWS MCP Server. Nothing to install.
resolve_keyword_call 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 resolve_keyword_call 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 resolve_keyword_call. 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.
resolve_keyword_call is provided by the RobotWS MCP Server MCP server (stella555359/robotws_mcp_server). 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 →