get_patterns
AI agents call get_patterns to retrieve information from TempoGraph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The pattern name strongly suggests inspection or analysis of code patterns without modification. However, confidence is moderately reduced due to empty description. Could hypothetically have side effects if 'patterns' implies generating synthetic data or triggering analysis pipelines, but most likely read-only given the server's stated purpose as a 'context engine' and sibling tools that are predominantly…
From the tool's definition Tool name 'get_patterns' suggests retrieval/querying of code patterns. No description provided, but naming convention aligns with Read category tools on this server (e.g., 'architecture', 'dependencies', 'hotspots').
Attacks that exploit this kind of access
get_patterns. It is categorised as a Read tool in the TempoGraph MCP Server, which means it retrieves data without modifying state.
Register the TempoGraph MCP server in PolicyLayer and add a rule for get_patterns: 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 TempoGraph. Nothing to install.
get_patterns 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_patterns 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_patterns. 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_patterns is provided by the TempoGraph MCP server (tempograph). 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 →