Multi-keyword mentions. Params: keywords (array|string), start, end, chain, limit, cursor, sources.
AI agents call elfa_keyword_mentions to retrieve information from CG Alpha MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool fetches social/market mention data for given keywords over a time range. It has no side effects, does not modify data, and is purely a read/search operation. Severity is low as misuse only exposes market sentiment data.
From the tool's definition 'Multi-keyword mentions' with params for keywords, start, end, chain, limit, cursor, sources — this is a query/search operation retrieving mention data
Attacks that exploit this kind of access
Multi-keyword mentions. Params: keywords (array|string), start, end, chain, limit, cursor, sources. It is categorised as a Read tool in the CG Alpha MCP MCP Server, which means it retrieves data without modifying state.
Register the CG Alpha MCP server in PolicyLayer and add a rule for elfa_keyword_mentions: 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 CG Alpha MCP. Nothing to install.
elfa_keyword_mentions 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 elfa_keyword_mentions 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 elfa_keyword_mentions. 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.
elfa_keyword_mentions is provided by the CG Alpha MCP server (jcf0/cg-alpha-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 →