Extract cross-repo contracts (exports, routes, schemas, events) from every member repo in a group and detect provider→consumer links via name matching and RRF scoring.
AI agents call group_sync to retrieve information from code-intel MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
group_sync retrieves and analyzes metadata (exports, routes, schemas, events) from repository members to understand relationships. It extracts and detects information but does not create, modify, delete, or execute code. This is a read-only intelligence operation consistent with other tools in the code-intel server (explain_relationship, blast_radius, etc.). No side effects or data modification occurs.
From the tool's definition Tool performs extraction and detection of existing cross-repo contracts and links: 'Extract cross-repo contracts...and detect provider→consumer links via name matching and RRF scoring.' These are analysis and query operations with no modification, deletion,…
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Extract cross-repo contracts (exports, routes, schemas, events) from every member repo in a group and detect provider→consumer links via name matching and RRF scoring. It is categorised as a Read tool in the code-intel MCP Server MCP Server, which means it retrieves data without modifying state.
Register the code-intel MCP Server MCP server in PolicyLayer and add a rule for group_sync: 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 code-intel MCP Server. Nothing to install.
group_sync 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 group_sync 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 group_sync. 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.
group_sync is provided by the code-intel MCP Server MCP server (vohongtho/code-intel-platform). 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 →