Agentvet

io.github.MukundaKattaPublished by GitHub account MukundaKattav0.1.0Updated Oct 24, 2026

Validate tool-call args before execution. Returns LLM-friendly retry hints.

VerifiedSTDIODesktop onlyDeveloper ToolsAI & ML

Overview

AI-generated overview

Lets an assistant validate LLM-generated tool-call arguments against a shape spec and produce retry hints before execution.

What you can do
Exposes three tools from the agentvet library: validate_tool_args checks an arguments object against a small shape spec and returns whether it is valid, an error, and a ready-to-send retry hint; lint_tool_definition sanity-checks a tool definition for common mistakes such as non-snake_case names, missing descriptions, or no required fields; generate_retry_message builds the canonical LLM-facing retry text from a validation error and the attempted arguments.
When to use it
Useful when you want to check whether an arguments object is valid for a tool, audit a set of tool definitions for LLM tool-use accuracy, or prepare retry feedback text outside a live agent loop. For runtime validation inside a Node agent loop, the underlying library is used directly instead.
Requirements
Runs locally over stdio, typically started with npx from the npm package @mukundakatta/agentvet-mcp, so Node.js and network access for the package fetch are needed. No accounts, API keys, environment variables, or headers are declared. Desktop MCP clients only.
Before you install
The server only validates and lints; it does not execute the tools it checks, so a valid result is not a guarantee that the underlying action is safe. Arguments and tool definitions you submit are passed to the local process for checking.

Installation

In SourceWeft

  1. Open Agentvet in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

agentvet-mcp

MCP server for @mukundakatta/agentvet. Lets Claude Desktop, Cursor, Cline, Windsurf, Zed, or any other MCP client validate LLM-generated tool-call args before execution and produce LLM-friendly retry messages when something's wrong.

bash
npx -y @mukundakatta/agentvet-mcp

Three tools:

  • validate_tool_args — check args against a small shape spec; returns { valid, error?, retry_hint? } where retry_hint is a ready-to-send LLM feedback message.
  • lint_tool_definition — sanity-check a tool definition for common mistakes that hurt LLM tool-use accuracy.
  • generate_retry_message — given a validation error, build the canonical LLM-facing retry message using agentvet's ToolArgError.toLLMFeedback() formatting.

Add to your client

Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

json
{  "mcpServers": {    "agentvet": {      "command": "npx",      "args": ["-y", "@mukundakatta/agentvet-mcp"]    }  }}

Same shape for Cursor (~/.cursor/mcp.json), Cline, Windsurf, Zed.

Tool examples

validate_tool_args:

json
{  "tool_name": "send_email",  "args": { "to": "[email protected]" },  "shape": { "to": "string", "subject": "string", "body": "string" }}

Returns:

json
{  "valid": false,  "error": "missing required field: subject",  "retry_hint": "send_email rejected your args: missing required field: subject. Please call again with the corrected arguments."}

lint_tool_definition:

json
{  "tool": {    "name": "BadName",    "inputSchema": { "type": "object", "properties": { "x": { "type": "string" } } }  }}

Returns warnings about non-snake_case name, missing description, missing field descriptions, and no required fields.

generate_retry_message:

json
{  "tool_name": "send_email",  "validation_error": "missing required field: subject",  "attempted_args": { "to": "[email protected]" }}

Returns the canonical retry feedback string the runtime callers see — so you can prepare retry text outside the live agent loop.

Why a separate MCP server

@mukundakatta/agentvet is a zero-dependency JavaScript library. This MCP server makes its validation primitives accessible from any MCP-aware AI assistant. Useful for quickly auditing a registry of tools, or asking the assistant "is this args object valid for my send_email tool?" without leaving the chat.

For runtime arg validation in your agent loop, use @mukundakatta/agentvet directly inside your Node process (it wraps your tool fn and throws ToolArgError synchronously).

Sibling MCP servers

Part of the agent-stack series:

License

MIT

Source: README.md at commit 814875f

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts