graph_connect · Claude Session Continuity MCP: Risk & Policy

WHAT IT DOES

What graph_connect does on Claude Session Continuity

AI agents use graph_connect to create or update resources in Claude Session Continuity — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Session Continuity environment.

WHY IT NEEDS A POLICY

Why graph_connect needs a policy

The graph_connect tool creates or modifies relationships in a knowledge graph by inserting/upserting edges between memories. This is a Write operation because it creates/modifies data (graph edges) reversibly—the relations can be updated or removed later. While it has side effects (modifying the graph structure), it does not execute arbitrary code, delete data irreversibly, or move money.

From the tool's definition Tool description states 'inserts or replaces a row in memory_relations (upsert on sourceId+targetId+relation)' which indicates it creates or modifies data reversibly.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

graph_connect Rate-limited

graph_connect stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "graph_connect": {
      "limits": [
        {
          "counter": "graph_connect_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Claude Session Continuity, so you can run agents against it safely.

FAQ

Questions about graph_connect

What does the graph_connect tool do? +

Create a directed edge between two memories in the knowledge graph. Supports 7 relation types for structured knowledge organization. Side effects: inserts or replaces a row in memory_relations (upsert on sourceId+targetId+relation). Use memory_related to discover existing connections; use graph_explore to traverse the graph from a starting node. It is categorised as a Write tool in the Claude Session Continuity MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on graph_connect? +

Register the Claude Session Continuity MCP server in PolicyLayer and add a rule for graph_connect: 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 Claude Session Continuity. Nothing to install.

What risk level is graph_connect? +

graph_connect is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit graph_connect? +

Yes. Add a rate_limit block to the graph_connect 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.

How do I block graph_connect completely? +

Set action: deny in the PolicyLayer policy for graph_connect. 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.

What MCP server provides graph_connect? +

graph_connect is provided by the Claude Session Continuity MCP server (leesgit/claude-session-continuity-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.