Explain common Microsoft Graph API error codes and how to fix them — 401, 403, 404, 429, 503, and Graph-specific error codes like InvalidAuthenticationToken, Forbidden, and ItemNotFound.
AI agents call graph_explain_errors to retrieve information from Ms Graph Dev without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a reference/lookup tool that returns explanatory information about error codes and solutions. It performs no operations on data, does not modify state, does not execute code, and has no side effects. The verb 'explain' combined with the description's focus on providing information about error codes and fixes confirms this is a Read category tool (retrieve/query information).
From the tool's definition Tool name 'graph_explain_errors' and description indicate it 'Explain[s] common Microsoft Graph API error codes and how to fix them' — a purely informational/reference function that retrieves and presents error documentation and remediation guidance.
Attacks that exploit this kind of access
Explain common Microsoft Graph API error codes and how to fix them — 401, 403, 404, 429, 503, and Graph-specific error codes like InvalidAuthenticationToken, Forbidden, and ItemNotFound. It is categorised as a Read tool in the Ms Graph Dev MCP Server, which means it retrieves data without modifying state.
Register the Ms Graph Dev MCP server in PolicyLayer and add a rule for graph_explain_errors: 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 Ms Graph Dev. Nothing to install.
graph_explain_errors 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 graph_explain_errors 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 graph_explain_errors. 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.
graph_explain_errors is provided by the Ms Graph Dev MCP server (stubbedev/ms-graph-dev-mcp). 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 →