Skip to main content
ClaudeWave

Conarium AI — self-hosted governance layer between AI assistants and your real data. Deterministic PII masking, allow/deny policy, hash-chained audit, an Ed25519-signed receipt per access verifiable offline, coverage reconciliation against the DB's own query counters to surface gateway bypasses, and conformance vectors. MCP-native. MIT.

MCP ServersOfficial Registry2 stars0 forksTypeScriptMITUpdated today
ClaudeWave Trust Score
95/100
Verified
Passed
  • Open-source license (MIT)
  • Actively maintained (<30d)
  • Clear description
  • Topics declared
  • Documented (README)
Last scanned: 8/20/2026
Install in Claude Code / Claude Desktop
Method: NPX · conarium-verify
Claude Code CLI
claude mcp add conarium -- npx -y conarium-verify
claude_desktop_config.json (Claude Desktop)
{
  "mcpServers": {
    "conarium": {
      "command": "npx",
      "args": ["-y", "conarium-verify"],
      "env": {
        "CONARIUM_AUDIT_SIGNING_KEY": "<conarium_audit_signing_key>"
      }
    }
  }
}
1. Run the command above in your terminal (Claude Code), or paste the JSON config into claude_desktop_config.json (Claude Desktop).
2. Replace any <placeholder> values with your API keys or paths.
3. Restart Claude. The MCP server and its tools appear automatically.
Detected environment variables
CONARIUM_AUDIT_SIGNING_KEY
Use cases

MCP Servers overview

<div align="center">
  <h1>Conarium</h1>
  <p><strong>The Third Eye for Your Company's Data.</strong></p>
  <p>A self-hosted, governed gateway that lets AI coding assistants (Cursor, Copilot, Claude) touch your real data under a policy you write—protected values masked before they leave. When a receipt sink is configured it writes a signed, independently verifiable receipt of every access it mediates; <code>conarium-init</code> sets that sink, so the default layout does.</p>
  
  <p>
    <a href="https://www.npmjs.com/package/@conarium-ai/core"><img src="https://img.shields.io/npm/v/@conarium-ai/core?style=for-the-badge" alt="npm" /></a>
    <a href="https://github.com/dogrucanemek-alt/conarium/actions/workflows/security.yml"><img src="https://img.shields.io/github/actions/workflow/status/dogrucanemek-alt/conarium/security.yml?branch=main&style=for-the-badge&label=CI" alt="CI" /></a>
    <a href="https://securityscorecards.dev/viewer/?uri=github.com/dogrucanemek-alt/conarium"><img src="https://api.securityscorecards.dev/projects/github.com/dogrucanemek-alt/conarium/badge" alt="OpenSSF Scorecard" /></a>
    <a href="https://www.bestpractices.dev/projects/14160"><img src="https://www.bestpractices.dev/projects/14160/badge" alt="OpenSSF Best Practices" /></a>
    <a href="https://conarium.dev"><img src="https://img.shields.io/badge/Website-conarium.dev-5a8cff?style=for-the-badge" alt="Website" /></a>
    <a href="https://github.com/dogrucanemek-alt/conarium/blob/main/LICENSE"><img src="https://img.shields.io/badge/License-MIT-f2d79a?style=for-the-badge" alt="License" /></a>
    <img src="https://img.shields.io/badge/Status-Early%20Access-ff6f80?style=for-the-badge" alt="Early Access" />
  </p>
</div>

<br/>

The site lives at [conarium.dev](https://conarium.dev); this repository is the product.

## Check it before you read the rest

Nothing below has to be taken on trust. There is a live receipt chain; verify it
against its public key on your own machine, with no account and no data of yours:

```bash
npm i @conarium-ai/core
curl -fsS https://demo.conarium.dev/proof/chain.jsonl   -o chain.jsonl
curl -fsS https://demo.conarium.dev/proof/key.pem       -o key.pem
curl -fsS https://demo.conarium.dev/proof/key.pem.keyid -o key.pem.keyid
npx conarium-verify chain.jsonl --pubkey key.pem
```

```
note: tail truncation is not visible — this run did not see receipts deleted from the
end of the file. Pin with --expect-count, --expect-last-hash, or --anchor-check.
ok: 3 receipt(s) verified (3 with undeclared model, 3 with undeclared client)
```

Exit code 0. The three receipts are one ordinary read, one where five email addresses
and a card number were masked before the model saw them, and one refusal. Change any
field and the recomputed hash stops matching the stored one — exit 10. Change the
signature instead — exit 13.

The verifier is a single file that imports nothing from the package it is checking, so
a compromised Conarium cannot talk it into a passing result. Note that it volunteers
what it did *not* check, in the first line of its own output, before the good news.

## Limitations

What this repository has **not** done is in [LIMITATIONS.md](LIMITATIONS.md)
([Türkçe](LIMITATIONS.tr.md)). The dated comparison page is
[conarium.dev/compare.html](https://conarium.dev/compare.html) — that is the
only copy; this repo does not keep a second one.

## Standards

[draft-dogru-scitt-disclosure-evidence](https://datatracker.ietf.org/doc/draft-dogru-scitt-disclosure-evidence/)
is an individual submission. Not adopted by an IETF working group, and it
carries no formal standing — an Internet-Draft is a dated public record, not a standard.
It is published so the receipt format can be implemented without us.
Source files live in [`standards/`](standards/).

## 👁️ The Problem

Point Cursor or Copilot at a production database and it drinks the raw stream—SSNs, credit cards, salaries, and live keys. One rogue prompt can expose your most sensitive tables. Security teams simply can't allow that.

## 🛡️ The Solution: Conarium

Conarium acts as a high-performance **MCP (Model Context Protocol) Proxy**. It sits directly between the AI Assistant and your databases, evaluating policies in milliseconds to enforce row limits and mask PII (Personally Identifiable Information) on the wire.

The AI gets the context it needs to write code; the values your policy protects are masked before they reach it. Masking hides a value — it does not make it unlearnable, and where a request language allows predicates over a protected column, an allowed query can still answer questions about one. `protectedColumns` is the narrower answer to that, and the limit is stated in [LIMITATIONS.md](LIMITATIONS.md) rather than left for you to discover.

### Key Features

- **Inline PII Masking:** Emails, IDs, cards, and secrets are redacted in the response stream (`[MASKED_PII]` / `[MASKED_SECRET]`) before the model sees a single character.
- **Allow / Deny Lists:** Whitelist what AI can access. Your `secrets` and `financials` tables stay invisible.
- **Row Caps:** Hard per-query limits. Prevent the silent exfiltration of millions of rows. 
- **Tamper-Evident Audit Ledger:** Every access *through Conarium* is logged (who, what, when, rows, decision). Hash-chained, which makes alteration and mid-chain removal detectable — not impossible: a file on disk can still be deleted or truncated, and catching truncation needs a pin from outside the file (see Coverage & Reconciliation below). PII-safe: no raw PII is written to the logs.
- **Verifiable Receipts:** Ed25519-signed, independently verifiable receipts — see below.
- **Per-person masking profiles:** what to mask for an AI agent is not what to mask for the data controller. A named profile relaxes masking for one identified person, and the receipt records which profile applied — see below.
- **Coverage & Reconciliation:** a signed coverage declaration over the receipt chain (`conarium-coverage`), plus two-sided reconciliation against the database's own query counters (`conarium-reconcile`) — DB-recorded activity that no receipt covers is surfaced instead of staying invisible.
- **100% Self-Hosted:** Runs entirely on your infrastructure. Nothing we ship transmits your data anywhere: raw protected values stay inside your perimeter, and what reaches your AI client is the policy-approved disclosure — whose exact bytes the receipt records (`disclosure.hash`). Saying your data never leaves at all would be the wrong claim: releasing a governed disclosure to an assistant is the job. The gateway makes exactly one outbound request that is not yours: at startup it asks the public npm registry whether a newer version exists, and prints one line to stderr if so. It sends nothing about you — no identifier, no config, no counts — and a remote gateway nobody looks at for weeks is the reason it exists at all. Disable it with `CONARIUM_NO_UPDATE_CHECK=1`, or point it at your internal mirror with `CONARIUM_NPM_REGISTRY`. It has a 2-second timeout and never blocks or fails startup. We list it here because a governance product that makes an undisclosed outbound connection has already lost the argument.
- **MCP-Native:** Works out of the box with **Cursor**, **GitHub Copilot**, **Claude Code**, and **Codex**.

### Verifiable Receipts

Conarium can emit portable **receipts** (Art. 12 / 19 shaped) that a third party
verifies offline with a single file — no Conarium install required.

**Official claim (do not widen):** A Conarium Receipt proves that the records
**still in the file** have not been altered, reordered, or backdated after they
were created, and that none were **removed from the middle** of the chain
(`prevHash` / `seq`). It does **not** prove they were correct at the moment of
creation. It also cannot, by itself, prove that records were not **dropped from
the end**: a shorter leftover chain is still internally consistent. Catching
tail truncation needs a pin from outside the file — `--expect-count`,
`--expect-last-hash`, an OpenTimestamps anchor, or `conarium-reconcile` against
the database's own counters.

*(TR)* Conarium Makbuzu, dosyada **hâlâ duran** kayıtların oluşturulduktan sonra
değiştirilmediğini, **ortadan** silinmediğini, yeniden sıralanmadığını ve geriye
dönük tarihlenmediğini kanıtlar. **Oluşturma anında doğru olduğunu kanıtlamaz.**
Sondan kesmeyi tek başına göremez: kalan zincir tutarlıdır, yalnızca kısadır.
*(/TR)*

```bash
# Generate an Ed25519 keypair (private PEM + .pub.pem + .keyid sidecars).
# The .keyid sidecars are not optional: without them the verifier answers 13
# for every receipt, which reads like tampering and is not.
npx conarium-init

export CONARIUM_AUDIT_SIGNING_KEY=./audit-ed25519.pem

# init writes keys and config, not receipts: your own audit file does not exist
# until the gateway has served a query. The three commands below therefore run
# against the demo chain downloaded above, so they work as written — swap in
# your own sink (conarium.config.json → audit.sink) once it has records.

# Verify a receipt chain (exit 0 = the records *in the file* are intact)
npx conarium-verify chain.jsonl --pubkey key.pem

# Pin length / last hash if you need to catch records dropped from the end
npx conarium-verify chain.jsonl --pubkey key.pem --expect-count 3

# Check the OpenTimestamps sidecar. The demo chain ships without one, so this
# answers 14, deliberately not 0: an absent anchor is not a verified anchor.
# A sidecar that exists but is not yet confirmed → exit 0 with a warning.
npx conarium-verify chain.jsonl --pubkey key.pem --anchor-check
```

A second verifier, Go and the standard library only, is in [`verifiers/go`](verifiers/go). `go build -o conarium-verify .` then the same arguments as `conarium-verify`; `test-vectors/` is the contract.

Opt-in anchoring: `CONARIUM_ANCHOR_SINK=opentimestamps`. Upgrade pending proofs later with
`npx conarium-anchor-upgrade ./audit.jsonl.anchors.jsonl`.
The client i
ai-securityaudit-logaudit-reconciliationbypass-detectiondata-governancedata-maskingeu-ai-actgdprkvkkllm-securitymcpmcp-gatewaymcp-serveropen-timestampspii-maskingpostgresscittself-hostedtamper-evidentverifiable-receipts

What people ask about conarium

What is dogrucanemek-alt/conarium?

+

dogrucanemek-alt/conarium is mcp servers for the Claude AI ecosystem. Conarium AI — self-hosted governance layer between AI assistants and your real data. Deterministic PII masking, allow/deny policy, hash-chained audit, an Ed25519-signed receipt per access verifiable offline, coverage reconciliation against the DB's own query counters to surface gateway bypasses, and conformance vectors. MCP-native. MIT. It has 2 GitHub stars and its last recorded update is dated 2026-08-20.

How do I install conarium?

+

You can install conarium by cloning the repository (https://github.com/dogrucanemek-alt/conarium) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.

Is dogrucanemek-alt/conarium safe to use?

+

Our security agent has analyzed dogrucanemek-alt/conarium and assigned a Trust Score of 95/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.

Who maintains dogrucanemek-alt/conarium?

+

dogrucanemek-alt/conarium is maintained by dogrucanemek-alt. The last recorded GitHub activity is dated 2026-08-20, with 4 open issues.

Are there alternatives to conarium?

+

Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.

Deploy conarium to your cloud

Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.

Maintain this repo? Add a badge to your README

Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.

Featured on ClaudeWave: dogrucanemek-alt/conarium
[![Featured on ClaudeWave](https://claudewave.com/api/badge/dogrucanemek-alt-conarium)](https://claudewave.com/repo/dogrucanemek-alt-conarium)
<a href="https://claudewave.com/repo/dogrucanemek-alt-conarium"><img src="https://claudewave.com/api/badge/dogrucanemek-alt-conarium" alt="Featured on ClaudeWave: dogrucanemek-alt/conarium" width="320" height="64" /></a>

More MCP Servers

conarium alternatives