Kaval MCP Server

by usekaval Your server? Claim it

local only

Kaval runs on your own machine — the client starts it, so there is no endpoint to ping. 193 installs a week from npm. Last commit 19 Aug 2026.

Verify the facts an agent's action depends on before it acts — ALLOW, REVIEW, or BLOCK.

Installs per day peak 320 · avg 74 · -76% w/w

a month agotoday

193

Installs / week

npm · @usekaval/mcp

Stars

0 open issues

19 Aug 2026

Last commit

0 releases in 90 days

Apache-2.0

License

TypeScript

Nothing serious here today

Today is the operative word: we check Kaval every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add kaval -- npx -y @usekaval/mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "kaval": {
      "args": [
        "-y",
        "@usekaval/mcp"
      ],
      "command": "npx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.kaval]
command = "npx"
args = ["-y", "@usekaval/mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "kaval": {
      "args": [
        "-y",
        "@usekaval/mcp"
      ],
      "command": "npx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "kaval": {
      "args": [
        "-y",
        "@usekaval/mcp"
      ],
      "command": "npx"
    }
  }
}

Alternatives to Kaval

same job, measured the same way

Kaval

by lufemc

Verify the facts an agent's action depends on before it acts — ALLOW, REVIEW, or BLOCK.

local only

The MCP Census

by mcpcensus

Vet any MCP server before you depend on it. Stamp: PASS, REVIEW, or BLOCK.

13 tools answering

Policy Gate

by workers-3labsio-policy-gate

Deterministic allow/require_approval/deny verdicts for agent actions, before they happen.

4 tools answering

Veritap

by veritap

Check whether a real-world fact can be verified before an agent acts on it. Free, no auth.

80 installs/wk 6 tools answering

Fidacy MCP

by lucaslubi

Action firewall for AI agents: blocks the wrong action before it runs, every verdict Ed25519-signed.

845 installs/wk local only

Qorami

by loicfontaine-max

Check an email before an AI agent sends it: send / ask a human / block. Detects prompt injection.

32 installs/wk local only

Agent Output Guard

by agenson-horrowitz

Validate and verify data from other agents before acting on it. Zero LLM costs.

64 installs/wk local only

Agentic Wallet Guardian V3

by rudimentall1

Explainable ALLOW/WARN/BLOCK risk decisions for AI agent actions before execution, signed as OAA.

87 installs/wk local only

Kaval — questions

Answers built from our own checks of this server.

Why is there no uptime for Kaval?

Kaval runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package @usekaval/mcp was installed 193 times last week.

How do I connect Kaval?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls @usekaval/mcp straight from npm; nothing to host, nothing to sign up for.

How many people use Kaval?

The npm package @usekaval/mcp was installed 193 times in the last week. Week over week that is -76%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Kaval open source?

Yes — it is published under the Apache-2.0 licence, written in TypeScript and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.