graph-batch
Combine up to 20 Graph requests into a single HTTP call. Body: { requests: [{ id: '1', method: 'GET'|'POST'|'PATCH'|'DELETE', url: '/me/messages?$top=5', headers?: {...}, body?: {...}, dependsOn?: ['1'] }, ...] }. Returns { responses: [{ id, status, body, headers }] } in arbitrary order — match b...
This record as markdown: /tools/jo3zik-ms-365-mcp-server/graph-batch.md
What graph-batch does on Ms 365
AI agents call graph-batch to permanently remove resources in Ms 365, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
| Parameter | Type | Required | Description |
|---|---|---|---|
body | object | Yes | |
confirm | boolean | — | For destructive operations when the confirm gate is enabled (MS365_MCP_REQUIRE_CONFIRM=true; off by default). Set to true only after the user has explicitly app |
includeHeaders | boolean | — | Include response headers (including ETag) in the response metadata |
excludeResponse | boolean | — | Exclude the full response body and only return success or failure indication |
Parameters from the server's own tool schema.
Why graph-batch is rated Critical
An AI agent that decides to call graph-batch doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Ms 365 is gone. There is no undo for destructive operations.
Risk signalsAccepts raw HTML/template content (body) · Admin/system-level operation
Attacks that exploit this kind of access
The rule that runs graph-batch safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Ms 365, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For graph-batch, this is the rule to start with:
graph-batch is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Ms 365, apply this rule, and every graph-batch call is checked against it from then on.
Questions about graph-batch
Combine up to 20 Graph requests into a single HTTP call. Body: { requests: [{ id: '1', method: 'GET'|'POST'|'PATCH'|'DELETE', url: '/me/messages?$top=5', headers?: {...}, body?: {...}, dependsOn?: ['1'] }, ...] }. Returns { responses: [{ id, status, body, headers }] } in arbitrary order — match by id. Use cases: (1) parallelize many small reads (e.g. fetch 15 mail messages by id in one round-trip); (2) sequence dependent writes via dependsOn; (3) batch many Excel range writes into one call to dramatically reduce latency on large workbook builds. Note: each sub-request URL is relative to the Graph version root (/me/..., /drives/..., NOT https://graph.microsoft.com/v1.0/...). 💡 TIP: Combine up to 20 Graph requests into a single HTTP call. Body: { requests: [{ id: '1', method: 'GET'|'POST'|'PATCH'|'DELETE', url: '/me/messages?$top=5', headers?: {...}, body?: {...}, dependsOn?: ['1'] }, ...] }. Returns { responses: [{ id, status, body, headers }] } in arbitrary order — match by id. Use cases: (1) parallelize many small reads (e.g. fetch 15 mail messages by id in one round-trip); (2) sequence dependent writes via dependsOn; (3) batch many Excel range writes into one call to dramatically reduce latency on large workbook builds. Note: each sub-request URL is relative to the Graph version root (/me/..., /drives/..., NOT https://graph.microsoft.com/v1.0/...). It is categorised as a Destructive tool in the Ms 365 MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
graph-batch accepts 4 parameters: body, confirm, includeHeaders, excludeResponse. Required: body. The full parameter table on this page comes from the server's own tool schema.
Register the Ms 365 MCP server in PolicyLayer and add a rule for graph-batch: 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 365. Nothing to install.
graph-batch is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the graph-batch 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-batch. 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-batch is provided by the Ms 365 MCP server (@jo3zik/ms-365-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Ms 365, and thousands of servers like it.
Across the catalogue