Find a project by working directory path or name. Pass cwd for auto-detection from your current directory, or query to search by name.
AI agents call resolve_project to retrieve information from Open Context without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves/looks up a project record based on a path or name. It performs no writes, executions, or deletions — it is a pure lookup/search operation with no side effects.
From the tool's definition "Find a project by working directory path or name" and "auto-detection from your current directory, or query to search by name"
Attacks that exploit this kind of access
Find a project by working directory path or name. Pass cwd for auto-detection from your current directory, or query to search by name. It is categorised as a Read tool in the Open Context MCP Server, which means it retrieves data without modifying state.
Register the Open Context MCP server in PolicyLayer and add a rule for resolve_project: 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 Open Context. Nothing to install.
resolve_project 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 resolve_project 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 resolve_project. 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.
resolve_project is provided by the Open Context MCP server (niawjunior/opencontext). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →