# subtract

Subtract b from a.

Agent View of the PolicyLayer registry record for `subtract`. HTML page: https://policylayer.com/tools/io-tinyfn-tinyfn/subtract

## Facts

- Tool: `subtract`
- Server: TinyFn (`https://api.tinyfn.io/mcp/all/`) — https://policylayer.com/tools/io-tinyfn-tinyfn.md
- Homepage: https://github.com/tinyfn-io/tinyfn-mcp
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server rate-limited: no
- Parameters: 2 (2 required)
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `a` | number | yes | First number |
| `b` | number | yes | Number to subtract |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "subtract",
    "arguments": {
      "a": 0,
      "b": 0
    }
  }
}
```

## Why subtract is rated Low

This is a stateless arithmetic operation that only retrieves/computes a result. It has no capability to modify, delete, execute code, or affect external systems. The blast radius of misuse is negligible—an agent cannot cause harm through mathematical subtraction alone.

From the tool's own definition: "The tool performs a pure mathematical operation 'Subtract b from a' with no side effects, no data modification, and no external state changes. It matches the deterministic math category described in the server description."

## Use case

AI agents call subtract to retrieve information from TinyFn without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches TinyFn:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "subtract": {}
  }
}
```

## Other tools on TinyFn (571)

- `array_compact` — Destructive — https://policylayer.com/tools/io-tinyfn-tinyfn/array-compact.md
- `array_dedupe` — Destructive — https://policylayer.com/tools/io-tinyfn-tinyfn/array-dedupe.md
- `truncate_2` — Destructive — https://policylayer.com/tools/io-tinyfn-tinyfn/truncate-2.md
- `generate_hmac` — Execute — https://policylayer.com/tools/io-tinyfn-tinyfn/generate-hmac.md
- `random_float_2` — Execute — https://policylayer.com/tools/io-tinyfn-tinyfn/random-float-2.md
- `random_string_2` — Execute — https://policylayer.com/tools/io-tinyfn-tinyfn/random-string-2.md
- `random_weighted_choice` — Execute — https://policylayer.com/tools/io-tinyfn-tinyfn/random-weighted-choice.md
- `roll_dice` — Execute — https://policylayer.com/tools/io-tinyfn-tinyfn/roll-dice.md
- `null` — Other — https://policylayer.com/tools/io-tinyfn-tinyfn/null.md
- `absolute_value` — Read — https://policylayer.com/tools/io-tinyfn-tinyfn/absolute-value.md
- `acres_to_hectares` — Read — https://policylayer.com/tools/io-tinyfn-tinyfn/acres-to-hectares.md
- `add` — Read — https://policylayer.com/tools/io-tinyfn-tinyfn/add.md
- `adler32_checksum` — Read — https://policylayer.com/tools/io-tinyfn-tinyfn/adler32-checksum.md
- `analogous_colors` — Read — https://policylayer.com/tools/io-tinyfn-tinyfn/analogous-colors.md
- `analyze_password` — Read — https://policylayer.com/tools/io-tinyfn-tinyfn/analyze-password.md
- `array_difference` — Read — https://policylayer.com/tools/io-tinyfn-tinyfn/array-difference.md
- `array_first` — Read — https://policylayer.com/tools/io-tinyfn-tinyfn/array-first.md
- `array_frequency` — Read — https://policylayer.com/tools/io-tinyfn-tinyfn/array-frequency.md
- `array_interleave` — Read — https://policylayer.com/tools/io-tinyfn-tinyfn/array-interleave.md
- `array_intersection` — Read — https://policylayer.com/tools/io-tinyfn-tinyfn/array-intersection.md
- `array_last` — Read — https://policylayer.com/tools/io-tinyfn-tinyfn/array-last.md
- `array_nth` — Read — https://policylayer.com/tools/io-tinyfn-tinyfn/array-nth.md
- `array_partition` — Read — https://policylayer.com/tools/io-tinyfn-tinyfn/array-partition.md
- `array_repeat` — Read — https://policylayer.com/tools/io-tinyfn-tinyfn/array-repeat.md
- `array_reverse` — Read — https://policylayer.com/tools/io-tinyfn-tinyfn/array-reverse.md
- `array_rotate` — Read — https://policylayer.com/tools/io-tinyfn-tinyfn/array-rotate.md
- `array_slice` — Read — https://policylayer.com/tools/io-tinyfn-tinyfn/array-slice.md
- `array_symmetric_difference` — Read — https://policylayer.com/tools/io-tinyfn-tinyfn/array-symmetric-difference.md
- `array_union` — Read — https://policylayer.com/tools/io-tinyfn-tinyfn/array-union.md
- `array_unzip` — Read — https://policylayer.com/tools/io-tinyfn-tinyfn/array-unzip.md
- …and 541 more: https://policylayer.com/tools/io-tinyfn-tinyfn.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=io-tinyfn-tinyfn · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-tinyfn-tinyfn