context_graph
See how stored concepts connect. USE WHEN: the user asks for an overview,
This record as markdown: /tools/100xprompt-chitta/context-graph.md
What context_graph does on Chitta
AI agents call context_graph to retrieve information from Chitta without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why context_graph is rated Low
This tool retrieves and visualizes the structure of a knowledge graph - a read-only operation that provides an overview of how concepts relate to each other. There are no side effects, no data modification, and no external execution.
From the tool's definition Tool name 'context_graph' and description 'See how stored concepts connect' indicates a query/visualization operation that retrieves and displays relationships between stored data without modifying, deleting, or executing external operations.
Attacks that exploit this kind of access
The rule that runs context_graph safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Chitta, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For context_graph, this is the rule to start with:
context_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 Chitta, apply this rule, and every context_graph call is checked against it from then on.
Questions about context_graph
See how stored concepts connect. USE WHEN: the user asks for an overview,. It is categorised as a Read tool in the Chitta MCP Server, which means it retrieves data without modifying state.
Register the Chitta MCP server in PolicyLayer and add a rule for context_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 Chitta. Nothing to install.
context_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 context_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 context_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.
context_graph is provided by the Chitta MCP server (@100xprompt/chitta). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Chitta, and thousands of servers like it.
This server
Across the catalogue