Update project context and learning patterns
AI agents use cursor_project_context to create or update resources in SAM — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SAM environment.
The tool modifies stored project context and learning patterns, which falls under Write category (creates or modifies data reversibly). Severity is medium because while the tool can alter AI behavioral patterns and project configuration, updates are generally reversible and don't execute external code or delete data.
From the tool's definition Tool description states 'Update project context and learning patterns' - the verb 'Update' indicates modification of data. This is reversible data modification rather than irreversible deletion or code execution.
Documented attack patterns abuse exactly the kind of access cursor_project_context gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SAM, and nothing reaches the server without passing your rules. This is the rule we recommend for cursor_project_context:
{
"version": "1",
"default": "deny",
"tools": {
"cursor_project_context": {
"limits": [
{
"counter": "cursor_project_context_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}cursor_project_context 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.
Free to start. No card required.
Update project context and learning patterns. It is categorised as a Write tool in the SAM MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the SAM MCP server in PolicyLayer and add a rule for cursor_project_context: 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 SAM. Nothing to install.
cursor_project_context is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the cursor_project_context 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 cursor_project_context. 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.
cursor_project_context is provided by the SAM MCP server (pigrieco/mcp-memory-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SAM, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
37 SAM tools catalogued and risk-classified — across an index of 43,000+ MCP servers.