# AI Agent Tool Permission Worksheet for ERP Access

> Source: https://netray.co/tools/ai-agent-tool-permission-worksheet
> Publisher: Netray (netray.co), AI and integration engineering for ERP and manufacturing systems.
> Section: Free Tools

## Short answer

Inventory each agent tool, score its blast radius and decide who approves it before an AI agent touches ERP data.

## Category

ai-automation

## Audience

- IT security
- ERP administrator
- AI engineer
- Internal audit

## Tool

**Kind:** worksheet

**Mode:** editable

**Columns:**

#### Tool name

**Key:** tool

**Type:** text

#### ERP or system

**Key:** system

**Type:** text

#### Access level

**Key:** access

**Type:** select

**Options:**

- Read
- Write draft
- Write post
- Delete

#### Data class

**Key:** data

**Type:** select

**Options:**

- Public
- Internal
- Confidential
- Export controlled

#### Impact (1-5)

**Key:** impact

**Type:** number

**Help:** Harm if the tool is misused or wrong.

#### Likelihood (1-5)

**Key:** likelihood

**Type:** number

**Help:** Chance of a wrong or unintended call.

#### Risk score

**Key:** risk

**Type:** number

**Expr:** impact * likelihood

**Format:** integer

#### Approval rule

**Key:** approval

**Type:** select

**Options:**

- None
- Log only
- User confirms
- Manager approves
- Blocked

#### Owner

**Key:** owner

**Type:** text

**Rows:**

**Tool:** get_sales_order_status

**System:** ERP

**Access:** Read

**Data:** Internal

**Impact:** 2

**Likelihood:** 2

**Approval:** Log only

**Owner:** Sales ops

**Tool:** search_inventory_by_part

**System:** ERP

**Access:** Read

**Data:** Internal

**Impact:** 2

**Likelihood:** 3

**Approval:** Log only

**Owner:** Planning

**Tool:** get_supplier_bank_details

**System:** ERP

**Access:** Read

**Data:** Confidential

**Impact:** 5

**Likelihood:** 2

**Approval:** Blocked

**Owner:** Finance

**Tool:** create_purchase_requisition_draft

**System:** ERP

**Access:** Write draft

**Data:** Internal

**Impact:** 3

**Likelihood:** 3

**Approval:** User confirms

**Owner:** Purchasing

**Tool:** post_goods_receipt

**System:** ERP

**Access:** Write post

**Data:** Internal

**Impact:** 4

**Likelihood:** 3

**Approval:** Manager approves

**Owner:** Warehouse

**Tool:** read_itar_drawing_index

**System:** PLM

**Access:** Read

**Data:** Export controlled

**Impact:** 5

**Likelihood:** 2

**Approval:** Manager approves

**Owner:** Compliance

**Totals:**

#### Total risk score

**Key:** risk

**Agg:** sum

**Format:** integer

#### Highest single risk

**Key:** risk

**Agg:** max

**Format:** integer

#### Tools listed

**Key:** tool

**Agg:** count

**Format:** integer

**Summary:**

#### Average risk per tool

**Key:** avg_risk

**Expr:** sum_risk / count

**Format:** decimal

**Primary:** true

**Description:** Rows scoring 15 or more deserve a human approval step or removal.

**Notes:** Suggested rule: any tool scoring 12 or more needs user confirmation, 15 or more needs manager approval, and anything touching export controlled or banking data should be reviewed by compliance before it is exposed. Review the sheet whenever a tool is added.

## Content

**Intro:** Before an AI agent gets tools for your ERP, someone should be able to say exactly which actions it can take, on what data, and who signs off. This worksheet is that inventory, with a simple risk score per tool.

**Sections:**

#### How to use the worksheet

**Body:** List one row per tool, not per agent, because the same agent will gain and lose tools over time. Set the access level, classify the data the tool can return, and score impact and likelihood from 1 to 5. The sheet multiplies them into a risk score. Then choose an approval rule: none for harmless lookups, user confirmation for drafts, manager approval for postings, and blocked where the data should never reach a model. Export to Excel for the audit file.

**Bullets:**

- Assign a named owner to every tool
- Separate draft writes from posting writes
- Re-score after incidents or schema changes

#### The method behind the score

**Body:** Impact times likelihood is the standard qualitative risk matrix, kept deliberately simple so a plant IT team can run it in a workshop. The value is less in the number than in the conversation: why is the likelihood a 3, what would reduce it, and who is accountable. Least privilege means the ERP account used by the agent carries only the roles needed for the tools listed here, nothing broader.

#### Reading the example

**Body:** The sample rows show a spread. Order status is low risk and only logged. Supplier bank details score high because of fraud exposure, so they are blocked. A purchase requisition draft needs the user to confirm, while a goods receipt posting needs a manager because it moves inventory and accounting. An export controlled drawing index is readable only after compliance review, which matters for ITAR or EAR obligations your company carries.

#### Common mistakes

**Body:** Common faults are scoring by how impressive the demo is rather than by worst case, forgetting that a read tool can leak confidential data, sharing one powerful service account across all tools, and approving tools once without a review date. Keep the sheet current and tie it to change control so a new tool cannot ship without a row.

**Cta:** If you want help turning this inventory into enforced roles, approvals and audit logging in your ERP, Netray can build that layer on your infrastructure.

**Faq:**

#### Why score tools instead of agents?

**Answer:** Agents change prompts and capabilities often, but each tool is a concrete action with a defined data scope. Permissions and approvals attach naturally to tools, so the inventory stays accurate longer.

#### Is a read-only tool always low risk?

**Answer:** No. A read tool can expose pricing, bank details, personal data or export controlled technical data. Classify the data it returns and score impact on that basis, not on whether it can change records.

#### What approval rule should writes get?

**Answer:** Start with drafts that a person confirms, then posting actions that a role holder approves. Avoid autonomous posting until you have audit logs, limits and a track record from the draft stage.

#### How often should I review it?

**Answer:** Review when a tool is added or changed, after any incident, and at least quarterly. Tie it to your normal change control so it stays part of the process instead of a one-time document.

## Search terms

ai agent permissions template, agent tool access matrix, least privilege ai agent erp, ai agent risk register excel, mcp tool permission matrix, human approval ai write back, agent authorization worksheet, ai tool access review

---
Talk to an engineer: https://netray.co/contact?intent=erp_ai | Machine catalog: https://netray.co/agent/catalog.json
