AI agents call jam_chart to retrieve information from Mcp Phish without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Jam-charts are reference data about musical performances (Phish concert improvisations). This tool retrieves or queries such data without modifying or deleting anything. The sibling tools are all Read-category (get_*, search_*). No evidence of side effects, code execution, financial impact, or data destruction. Confidence is moderate due to empty description, but context strongly suggests informational lookup.
From the tool's definition Tool name 'jam_chart' combined with sibling tools (get_audio, get_reviews, get_show, get_song, get_track, search_*) and server context (phish.net/phish.in APIs for setlists, songs, jam-charts, reviews, audio) indicates a data retrieval function.
Attacks that exploit this kind of access
jam_chart. It is categorised as a Read tool in the Mcp Phish MCP Server, which means it retrieves data without modifying state.
Register the Mcp Phish MCP server in PolicyLayer and add a rule for jam_chart: 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 Phish. Nothing to install.
jam_chart 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 jam_chart 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 jam_chart. 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.
jam_chart is provided by the Mcp Phish MCP server (pete-builds/mcp-phish). 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 →