Inspect extracted contracts and confidence-ranked cross-repo links from the last group sync. Supports filtering by kind, repo, and minimum confidence.
AI agents call group_contracts 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.
This tool retrieves and queries pre-computed contract data and cross-repository relationships from a prior sync operation. It supports filtering by kind, repo, and confidence threshold but does not create, modify, delete, or execute any operations. The blast radius of misuse is limited to information disclosure, making it a Read-category tool with low severity.
From the tool's definition Tool performs 'Inspect extracted contracts' and 'cross-repo links' with filtering capabilities. The verb 'inspect' and the read-only operations (filtering, viewing results from 'last group sync') indicate data retrieval with no modification.
Attacks that exploit this kind of access
Inspect extracted contracts and confidence-ranked cross-repo links from the last group sync. Supports filtering by kind, repo, and minimum confidence. 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_contracts: 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_contracts 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_contracts 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_contracts. 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_contracts 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 →