Kaval

Name: Kaval
Author: usekaval

by usekavalversion 0.8.2i★ 0iRuns on your computer

Registry nameio.github.usekaval/kaval

How to install

What it does

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

Connects Runs on your computer
Account or key Needs KAVAL_API_KEY
Category Other

Install

Pick the AI app you use, then copy the settings.

Passed 2/2 checks · Runs on your computer

First: which AI do you use?

ClaudeWeb · app · phoneChatGPTWebClaude CodeTerminalCursorCode editorVS CodeCode editorOtherOther apps

Pick your app and the steps appear below.

Works with Claude, with some setup first

You need a Kaval key (create it on the maker’s site) · Install Node.js on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone

Install Node.js
One time only; it works for every server that needs Node.js
Open the Node.js download page ↗
Done
Sign up and create a Kaval key
Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.
Open the Kaval site ↗
Done
Open the Claude desktop app’s settings file
SettingsDeveloperEdit Config
Done

Paste these settings and save the file

{
  "mcpServers": {
    "kaval": {
      "command": "npx",
      "args": [
        "-y",
        "@usekaval/mcp"
      ],
      "env": {
        "KAVAL_API_KEY": "your-value",
        "KAVAL_BASE_URL": "your-value"
      }
    }
  }
}

Paste the key only into the app’s field, never into a chat or to anyone

Done

Quit Claude and open it again
Done
Try it
Use Kaval and tell me what you can do for me, then show me one thing
✓ If Claude says it is using Kaval or shows a Kaval tool in the answer, you are connected

Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version

ChatGPT cannot connect Kaval yet

Kaval runs on your computer, but ChatGPT can only connect servers that run on the web

What you can do instead

A · Use an app that can connect Kaval

Steps for Claude →You need a Kaval key (create it on the maker’s site) · Install Node.js on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone
Steps for Claude Code →You need a Kaval key (create it on the maker’s site) · Install Node.js on your computer first (one time)
Steps for Cursor →You need a Kaval key (create it on the maker’s site) · Install Node.js on your computer first (one time)
Steps for VS Code →You need a Kaval key (create it on the maker’s site) · Install Node.js on your computer first (one time)

B · Others in Other that work with ChatGPT

Picked from the most used in the same category, only ones that connect by address with no key

Hostinger✓ ChatGPT
World Monitor✓ ChatGPT
Svelte MCP✓ ChatGPT

Works with Claude Code, with some setup first

You need a Kaval key (create it on the maker’s site) · Install Node.js on your computer first (one time)

Install Node.js
One time only; it works for every server that needs Node.js
Open the Node.js download page ↗
Done
Sign up and create a Kaval key
Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.
Open the Kaval site ↗
Done
Open Terminal
Mac: press Command+Space and type Terminal · Windows: open PowerShell
Done
4
Paste this command and press Enter
```
claude mcp add --scope user kaval --env KAVAL_API_KEY=your-value --env KAVAL_BASE_URL=your-value -- npx -y @usekaval/mcp
```
Replace “your-value” with your key before pressing Enter
Paste the key only into the app’s field, never into a chat or to anyone
Done
Type /mcp in Claude Code
You should see Kaval listed as connected
Done
Try it
Use Kaval and tell me what you can do for me, then show me one thing
✓ If Claude Code says it is using Kaval or shows a Kaval tool in the answer, you are connected

Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Works with Cursor, with some setup first

You need a Kaval key (create it on the maker’s site) · Install Node.js on your computer first (one time)

Install Node.js
One time only; it works for every server that needs Node.js
Open the Node.js download page ↗
Done
Sign up and create a Kaval key
Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.
Open the Kaval site ↗
Done
Click this button to open Cursor
Open in Cursor
Cursor asks you to confirm; click Install
Done
Fill in your key
In the Kaval settings, KAVAL_API_KEY, KAVAL_BASE_URL is empty; add your key and save
Paste the key only into the app’s field, never into a chat or to anyone
Done
Open the AI chat in Cursor in Agent mode
Done
Try it
Use Kaval and tell me what you can do for me, then show me one thing
✓ If Cursor says it is using Kaval or shows a Kaval tool in the answer, you are connected

Menu names checked against Cursor’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Works with VS Code, with some setup first

You need a Kaval key (create it on the maker’s site) · Install Node.js on your computer first (one time)

Install Node.js
One time only; it works for every server that needs Node.js
Open the Node.js download page ↗
Done
Sign up and create a Kaval key
Open the maker’s site, sign up and create an API key for the next step. Check the maker’s site for pricing and free plans.
Open the Kaval site ↗
Done
Click this button to open VS Code
Open in VS Code
VS Code asks you to confirm; click Install
Done
Fill in your key
In the Kaval settings, KAVAL_API_KEY, KAVAL_BASE_URL is empty; add your key and save
Paste the key only into the app’s field, never into a chat or to anyone
Done
Open the AI chat in VS Code in Agent mode
Done
Try it
Use Kaval and tell me what you can do for me, then show me one thing
✓ If VS Code says it is using Kaval or shows a Kaval tool in the answer, you are connected

Menu names checked against VS Code’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Other apps that use MCP, such as Windsurf, Zed or Gemini CLI, each add servers differently. See how in the app list.

See every app that uses MCP →

JSON settings are under “For developers” below

Stuck? Ask people who use Kaval💬 Discussion →

For developers: Terminal commands and JSON settings

Installed on your computer

Claude Code

claude mcp add --scope user kaval --env KAVAL_API_KEY=your-value --env KAVAL_BASE_URL=your-value -- npx -y @usekaval/mcp

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "kaval": {
      "command": "npx",
      "args": [
        "-y",
        "@usekaval/mcp"
      ],
      "env": {
        "KAVAL_API_KEY": "your-value",
        "KAVAL_BASE_URL": "your-value"
      }
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "kaval": {
      "command": "npx",
      "args": [
        "-y",
        "@usekaval/mcp"
      ],
      "env": {
        "KAVAL_API_KEY": "your-value",
        "KAVAL_BASE_URL": "your-value"
      }
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "kaval": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@usekaval/mcp"
      ],
      "env": {
        "KAVAL_API_KEY": "your-value",
        "KAVAL_BASE_URL": "your-value"
      }
    }
  }
}

Values you fill in

KAVAL_API_KEY secret required env
Bring-your-own Kaval bearer key (kv_live_…). Create one at https://usekaval.com.
KAVAL_BASE_URL env
Point at a self-hosted or staging Kaval API instead of the hosted one. Defaults to https://api.usekaval.com.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

At a glance

GitHub stars i: 0
Downloads per weeki: 77/wk
Licence i: No licence stated
Connection: Runs on your computer
Transport: stdio
Latest versioni: 0.8.2
Categoryi: Other
Published to registryi: Sep 11, 2026
Code last changedi: Sep 11, 2026
Maker: usekaval
Packages: npm: @usekaval/mcp
Repo: usekaval/kaval-clients
Website: usekaval.com
Registry status: Active

Which apps can use it

Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.

Run on your computer in

Claude Goose LM Studio Msty Studio Cherry Studio Cursor VS Code + GitHub Copilot Visual Studio Windsurf (Devin Desktop)Zed Kiro Cline Continue JetBrains AI Assistant Claude Code Codex CLI Gemini CLI OpenCode nodecode Warp LibreChat Raycast

All apps, with pros and cons →

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 12, 2026

✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account usekaval, which owns the repo
✓ Pass
Still maintained
Code last changed 2 months ago
… Not checked yet
Has a licence
We have not read this repo from GitHub yet
– Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
– Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
… Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints

Discussion

Ask, share a tip or report that it does not work. Sorted by what people marked helpful.

No posts yet. Be the first to ask or share.

Posts here are written by users, not the PopNx team.

User reviews

No reviews yet

Compared with others in Otheri

More stars than 0% of the other 19341 servers in this category
Published to the registry more recently than 38% of the other 19341 servers in this category
Basic checks equal to or better than 100% of the other 19341 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is Kaval safe?

It passed 2 of 2 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

You need to fill in: KAVAL_API_KEY

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed 2 months ago, and the latest version (0.8.2) reached the registry 2 months ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.

What can I use instead?

In the same category: World Monitor, Claude Flow, Windmill

Others in the same category

Servers in the same category from other makers, sorted by stars.

Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

World Monitor

Real-time global intelligence on conflict, markets, energy, trade, shipping and cyber. 104 tools.

by koala73Widely used★ 90.5KUpdated today

Runs in the cloud✓ service owner · worldmonitor.app

Install

Claude Flow

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

by ruvnetWidely used↓ 13.5K/wk★ 81.5KUpdated 14 months ago

Runs on your computer

Install

Windmill

Run Windmill scripts and flows and manage jobs, schedules, resources and variables.

by windmill-labsWidely used★ 18.5KUpdated today

Runs in the cloud

Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

@usekaval/mcp

Before an AI agent acts, Kaval verifies the facts that action depends on and answers ALLOW, REVIEW, or BLOCK with a signed receipt. This package exposes that as an MCP server.

Policy engines decide whether an action is permitted under the rules; Kaval verifies whether the facts those rules depend on are still true.

This package is a thin client over the hosted Kaval API. All compilation, grounding, and retrieval run server-side, so you bring just a Kaval API key — no model or search keys, no local engine.

0.6 was a breaking release. Nine tools became seven (before later portfolio/extraction tools landed), and everything removed folded into check; the

API answers 410 tool_retired for the old routes and this server translates that into an error

that tells the agent to call check. See Migrating from 0.5.

Run it

npx -y @usekaval/mcp

It speaks MCP over stdio. Point any MCP client at it.

Client config

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

Tools

Tool	What it does
`check`	The one that does the work. Send the action you are about to take (or the claims it rests on) → `ALLOW` / `REVIEW` / `BLOCK`, per-fact status, and a signed receipt.
`get_receipt`	The full signed document behind a check's `receipt.id` — per-fact evidence basis, decision-rule version, signing key. What an agent attaches when it blocks.
`prepare_contract_upload`	Create a private PDF upload target.
`ingest_contract`	Queue canonical text, an HTTPS document, or an uploaded PDF for extraction.
`get_contract`	Get contract processing status, candidate counts, and extraction issue state.
`list_contract_claims`	List extracted candidates with exact evidence spans.
`list_contract_extraction_issues`	List deterministic extraction failures that need customer review.
`review_contract_claim`	Approve, correct, or reject one candidate with immutable version control.
`import_facts`	Queue up to 400 reviewed facts for warm checks.
`get_fact_import`	Get one bulk import and every item result.
`list_bulletins`	Soft-deprecated — filter structured bulletins by payer, policy, code, date, or status. Prefer `list_extraction_runs` for new integrations.
`get_bulletin`	Soft-deprecated — get one structured bulletin with field evidence. Prefer `get_extraction_run`.
`list_bulletin_extraction_attempts`	Soft-deprecated — list customer-readable bulletin extraction status and failures. Prefer `list_extraction_runs`.
`get_bulletin_extraction_attempt`	Soft-deprecated — get one bulletin extraction attempt by source-version id. Prefer `get_extraction_run`.
`list_training_jobs`	List read-only training and evaluation status.
`get_training_job`	Get one read-only training job.
`list_training_feedback`	List reviewed feedback and its effective training-use state.
`record_training_feedback_consent`	Record an explicit training-use decision for one reviewed feedback item.
`create_extraction_schema`	Register a JSON Schema Kaval extracts structured records against. Requires `policy-update:manage`.
`list_extraction_schemas`	List the extraction schemas registered in this workspace.
`create_extraction_run`	Request a one-off publisher + period extraction run against a bound schema. Requires `policy-update:manage`.
`get_extraction_run`	Get one extraction run by id — status, schema, and result once it succeeds.
`list_extraction_runs`	List extraction runs with publisher/period/time filters, cursor pagination, and nested `document` chrome (pass `expand_document: false` to omit).
`list_extraction_packages`	List the monthly PDF + manifest rollups extraction runs are packaged into.
`list_publishers`	List org-owned publishers for this workspace's billing account.
`create_publisher`	Create an org-owned publisher (UUID identity; renameable display name).
`get_publisher`	Get one org-owned publisher by UUID.
`update_publisher`	Rename an org-owned publisher. UUID identity is unchanged.
`add_source`	Tell Kaval what to watch — requires `publisher_id` (org publisher UUID). A URL, a named authority to resolve, or a document you will push in.
`list_sources`	What Kaval currently watches for this workspace, including sources it auto-registered after a check cited them.
`remove_source`	Stop watching a source and forget it. The only thing that frees a registered/resolved workspace slot (auto-registered citations count there; discovered children use a separate per-parent ceiling).
`update_source`	Bind (or unbind) an extraction schema and/or set `publisher_id` on a watched source. Pass `reprocess: true` to fill-missing re-extract prior versions. Requires `policy-update:manage`.
`get_source_version_content`	Fetch the captured content of one fetched source version, as raw text or pre-split `sections`.
`report_outcome`	Report what actually happened after a prior check (by `receipt.id`), so Kaval can calibrate.
`verify`	Deprecated pilot alias: one conclusion + explicit `evidence_refs` → a signed ProofPacket receipt. Use `check`.

Resources

The server publishes these JSON resources:

kaval://bulletins
kaval://bulletins/extraction-attempts
kaval://training-jobs
kaval://training-feedback
kaval://contracts/{contract_id}
kaval://contracts/{contract_id}/claims
kaval://contracts/{contract_id}/extraction-issues
kaval://bulletins/{source_version_id}
kaval://bulletins/extraction-attempts/{source_version_id}
kaval://fact-imports/{import_id}
kaval://training-jobs/{job_id}

The training resources are read-only. Feedback review and consent require training:manage.

Bulletin extraction status is read-only. MCP does not expose the operator requeue control.

MCP does not start training or promote a model.

`check`

// arguments

{ "action": "Approve this prior-authorization request at the in-network rate", "context": "payer: Aetna; CPT 12345; plan HMO", "materiality": "critical", }

Or skip extraction entirely by naming the facts:

"claims": [ { "subject": "Aetna", "predicate": "requires_prior_auth_for", "object": "CPT 12345", "scope": { "plan": "HMO", "state": "CA" }, }, "The 2024 IBC is the current edition", ], "mode": "fast", }

The response:

field	meaning

| decision | ALLOW — every material fact still holds on fresh evidence, proceed. REVIEW — something is unknown, mid-re-evaluation, or changed at low/medium materiality. REVIEW is never permission to act. BLOCK — a high/critical fact changed, or a critical fact is unknown. | | reason_codes | one or more of ALL_FACTS_HOLD, FACT_CHANGED, FACT_EXPIRED, FACT_UNKNOWN, SOURCE_UPDATED_PENDING_REVIEW, SOURCE_UNREACHABLE, NEW_FACT_UNVERIFIED, COMPILATION_UNCERTAIN | | facts[] | { fingerprint, text, status: holds \| changed \| unknown, materiality, served_from_state, last_verified_at, sources[] } — this is how you see _which_ belief moved | | receipt | { id, signature, signed_at }. Pass receipt.id to report_outcome, or to get_receipt for the full signed document

Only the beginning is shown; read the rest in the repo

Kaval

What it does

Install

Install Node.js

Sign up and create a Kaval key

Open the Claude desktop app’s settings file

Paste these settings and save the file

Quit Claude and open it again

Try it

What you can do instead

Install Node.js

Sign up and create a Kaval key

Open Terminal

Paste this command and press Enter

Type /mcp in Claude Code

Try it

Install Node.js

Sign up and create a Kaval key

Click this button to open Cursor

Fill in your key

Open the AI chat in Cursor in Agent mode

Try it

Install Node.js

Sign up and create a Kaval key

Click this button to open VS Code

Fill in your key

Open the AI chat in VS Code in Agent mode

Try it

Installed on your computer

Values you fill in

At a glance

Which apps can use it

Related guides

What it can do

Basic checksi

Maker matches the repo

Still maintained

Has a licence

Endpoint responds

Sign-in with OAuth

No hidden instructions in tool descriptions

Discussion

User reviews

Compared with others in Otheri

Common questions

Others in the same category

World Monitor

Claude Flow

Windmill

README from the maker

@usekaval/mcp

Run it

Client config

Tools

Resources

check

`check`