This record as markdown: /tools/io-github-dave-london-http/log-graph.md
What log-graph does on Http
AI agents call log-graph to retrieve information from Http without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why log-graph is rated Low
This tool retrieves and formats branch topology information (likely from a version control system like Git) for display purposes. It has no side effects—it queries existing data and transforms it into a visual representation without creating, modifying, deleting, or executing external operations. The tool fits the 'Read' category as it performs retrieval with no destructive or state-changing consequences.
From the tool's definition Tool name 'log-graph' and description 'Returns visual branch topology as structured data' indicate retrieval and formatting of existing data without modification. The verb 'Returns' confirms a read operation.
Attacks that exploit this kind of access
The rule that runs log-graph safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Http, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For log-graph, this is the rule to start with:
log-graph is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Http, apply this rule, and every log-graph call is checked against it from then on.
Questions about log-graph
Returns visual branch topology as structured data. Wraps. It is categorised as a Read tool in the Http MCP Server, which means it retrieves data without modifying state.
Register the Http MCP server in PolicyLayer and add a rule for log-graph: 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 Http. Nothing to install.
log-graph 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 log-graph 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 log-graph. 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.
log-graph is provided by the Http MCP server (@paretools/http). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Http, and thousands of servers like it.
This server
Across the catalogue