diff_text
utilpeek: Diff two texts: unified line diff, word or character changes. For PDF or Word files use compare_documents. Returns the differences between two texts: similarity ratio, counts and hunks; in line mode a git-compatible unified diff, in word or char mode change records (equal, insert, delet...
This record as markdown: /tools/dev-tanod-tanod/diff-text.md
What diff_text does on Tanod
AI agents call diff_text to permanently remove resources in Tanod, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
| Parameter | Type | Required | Description |
|---|---|---|---|
a | string | Yes | The old text (at most 100,000 characters). |
b | string | Yes | The new text (at most 100,000 characters). |
mode | string | — | line (default; a unified diff), word or char (at most 20,000 characters per side). |
context | integer | — | Unchanged lines around each hunk (0-10, default 3). |
Parameters from the server's own tool schema.
Why diff_text is rated Critical
An AI agent that decides to call diff_text doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Tanod is gone. There is no undo for destructive operations.
Attacks that exploit this kind of access
The rule that runs diff_text safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Tanod, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For diff_text, this is the rule to start with:
diff_text 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 Tanod, apply this rule, and every diff_text call is checked against it from then on.
Questions about diff_text
utilpeek: Diff two texts: unified line diff, word or character changes. For PDF or Word files use compare_documents. Returns the differences between two texts: similarity ratio, counts and hunks; in line mode a git-compatible unified diff, in word or char mode change records (equal, insert, delete, replace) with exact character offsets into a and b. At most 1,000 hunks and 5,000 change records, then truncated. Parsed in an isolated, resource-limited child process without network; input over its limits is a 422 (not charged). Typically under 0.5 s. Price: USD 0.001. Free: 10 utilpeek calls per IP per UTC day. The submitted text is never logged or stored. Docs: https://tanod.dev/learn/text-diff-api.html. It is categorised as a Destructive tool in the Tanod MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
diff_text accepts 4 parameters: a, b, mode, context. Required: a, b. The full parameter table on this page comes from the server's own tool schema.
Register the Tanod MCP server in PolicyLayer and add a rule for diff_text: 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 Tanod. Nothing to install.
diff_text 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 diff_text 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 diff_text. 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.
diff_text is provided by the Tanod MCP server (https://tanod.dev/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Tanod, and thousands of servers like it.
Across the catalogue