The real workflow
Where Cursor enters the work
An agency coding agent can cross client boundaries when repositories, terminals, credentials, caches, or sessions are reused between engagements.
Cursor combines an AI editor with codebase context, indexing, agent features, model providers, extensions, web search, and optional background or connected tools.
MCP servers, extensions, model providers, and web search widen the systems and data Cursor can interact with.
Privacy Mode affects data use and retention, but it is not the same as a repository access boundary. Users still need to control workspaces, indexing, ignored paths, extensions, tools, and commands.
The presence of this path does not prove an incident. It identifies the boundary that should be checked before more sensitive context or authority is added.
Tool-specific boundary
Inspect the real access points.
What may carry context
open files and editor context
codebase indexing and embeddings
agent commands, extensions, web search, and MCP tools
Settings to verify
Privacy Mode and codebase indexing
.cursorignore and workspace scope
Agent, extension, web, network, and MCP permissions
Why this context matters
The consequence for agencies
Agency risk compounds when staff, contractors, shared tools, and reused credentials create paths between otherwise separate client environments. In this case, a business connector can turn an over-privileged account into a broad retrieval or action surface spanning customers, employees, projects, and internal operations.
A connector does not create data, but it can make existing account permissions available through a new interface. The safe question is not only whether the connector is trusted; it is whether the connected account is broader than the task requires.
Every client remains isolated, access is attributable to a named operator, and the agency can deliver consistent evidence without revealing another client.
Context decision
Three questions before adding access
Can this operator or tool reach any repository, mailbox, drive, cache, token, or transcript belonging to another client?
Are credentials and AI sessions issued per client and person rather than shared across the agency?
Can the agency deliver useful proof to this client without including another client's names, paths, findings, or configuration?
Evidence goal: Create a separate client evidence record covering operator identity, workspace isolation, credentials, approved systems, review history, and delivery status.
A repeatable review
Four steps, no sensitive data required
- 1
Write down the exact Cursor account, workspace, project, device, and connected service used in this workflow.
- 2
Inventory active MCP servers, extensions, search access, API keys, and their filesystem or network permissions.
- 3
Assign the decision and next review to the client service owner or agency security lead; do not leave the access boundary as an unwritten assumption.
- 4
Remove unused integrations and restrict each server to the smallest paths, scopes, and hosts. Record the result without copying private content or raw credentials into the report.
Controls to apply
Reduce access before adding trust
Remove unused integrations and restrict each server to the smallest paths, scopes, and hosts.
Use a least-privilege account or service identity created for the specific workflow.
Separate read-only retrieval from write, send, share, delete, and financial actions.
Set a recurring owner and expiry date for every connector rather than leaving access permanent.
Decision rule
Know when a formal baseline is justified
If the assistant has no connectors, document that and keep it true. If it can retrieve or change business data across services, create an access map before adding another integration.
CapitalGuard is relevant when the workflow includes repositories, recurring private work, credentials, connected systems, commands, or evidence that must be shared with another person. It does not inspect this account from the page or guarantee that an incident cannot occur.
Primary references