io.github.usekaval/kavalai

Kaval

Verified · 24 days ago

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

Install

claude mcp add kaval -- npx -y @usekaval/[email protected]

Requires: KAVAL_API_KEY, KAVAL_BASE_URL

Our take

Kaval is a guardrail server for checking factual premises behind an agent action and returning an allow, review, or block decision. It is aimed at teams building higher-risk agent workflows that need a verification layer before execution. The positioning is clear and the download count suggests some early adoption, but the zero-star footprint makes it look young rather than established.

reviewed by hand · 2026-08-09

Something wrong or dead here? Report it

Verification record

last verified
24 days ago
github stars
0
last commit
2 mo ago
archived
no
license
Apache-2.0
npm
@usekaval/mcp
downloads / wk
117
latest version
0.8.2
in registry since
2026-08-07

github.com/usekaval/kaval-clients

More in ai

browse all →
reaai

REA

Verified · 20 days ago

Reverse engineer anything from your terminal or agent with one CLI and MCP server.

hand-reviewed291k stars232k dl/wkchecked 20 days ago

claude-flowai

claude-flow

Verified · 2 mo ago

AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.

hand-reviewed73k stars19k dl/wkchecked 2 mo ago

tldrawai

tldraw

Verified · 2 mo ago

Draw and visually collaborate with your agents on tldraw's canvas.

hand-reviewed50k starschecked 2 mo ago

codebase-memory-mcpai

Codebase Memory

Verified · 40 days ago

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

hand-reviewed45k stars12k dl/wkchecked 40 days ago

openmetadata-mcpai

OpenMetadata

Verified · 32 days ago

Official OpenMetadata MCP: 21 read and write tools for search, lineage, data quality, governance.

hand-reviewed15k starschecked 32 days ago