# Mandare (npm · @mandarelabs/mcp-server)

Verify an agent fleet's tamper-evident ledger, check budgets, kill a runaway agent. Local-first.

- Trust score: 78/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-04

## Components

- npm · `@mandarelabs/mcp-server`: 78/100 (this document), [markdown](https://verifymcp.io/servers/com-mandarelabs-mandare/mandarelabs-mcp-server.md), [page](https://verifymcp.io/servers/com-mandarelabs-mandare/mandarelabs-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `@mandarelabs/mcp-server`
- Version: `0.1.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-04.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 49 of 197 dependencies flagged as unhealthy (3 deprecated).
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to mandarelabs/mandare).
  - Clear OSI-approved license (AGPL-3.0-only).
  - Actively maintained (last published 3 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 75/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 807 tokens (~100/item across 8 items; 8 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 78/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 35% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "mandare_kill" implies "kill" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Mandare MCP server?

Mandare runs locally as an npm package, launched with npx -y @mandarelabs/mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add com-mandarelabs-mandare -- npx -y @mandarelabs/mcp-server
```

### Cursor

```json
{
  "mcpServers": {
    "com-mandarelabs-mandare": {
      "command": "npx",
      "args": [
        "-y",
        "@mandarelabs/mcp-server"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-mandarelabs-mandare": {
      "command": "npx",
      "args": [
        "-y",
        "@mandarelabs/mcp-server"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add com-mandarelabs-mandare -- npx -y @mandarelabs/mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-mandarelabs-mandare": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@mandarelabs/mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-mandarelabs-mandare --command npx --arg -y --arg @mandarelabs/mcp-server
```

### Hermes

```yaml
mcp_servers:
  com-mandarelabs-mandare:
    command: "npx"
    args: ["-y", "@mandarelabs/mcp-server"]
```

### Netclaw

```json
{
  "McpServers": {
    "com-mandarelabs-mandare": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@mandarelabs/mcp-server"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-mandarelabs-mandare -t stdio -c npx -a -y @mandarelabs/mcp-server
```

### Other

```json
{
  "mcpServers": {
    "com-mandarelabs-mandare": {
      "command": "npx",
      "args": [
        "-y",
        "@mandarelabs/mcp-server"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-01 (score 78)

First indexed and scored.

## MCP tools (8)

### `mandare_verify` (~99 tokens)

Verify the Mandare ledger

Verify the local ledger: hash chain, door signatures, RFC 6962 tree head, spend trail and budget-counter replay, approval trail, and revocation state. With check_witness=true also checks the chain against the externally witnessed head history (catches truncation and rewrites). Returns the machine-readable verification report. Read-only.

Input parameters:

- `check_witness` (boolean): Also verify against the configured witness (detects truncation/rewrites)

### `mandare_budget_status` (~62 tokens)

Budget status

Per-mandate spend from the ledger: settled and reserved amounts (integer micro-units of the ledger currency), intent counts, refusal count, and whether the live budget counters equal a fresh replay of the ledger. Use before starting expensive work. Read-only.

### `mandare_issue_passport` (~108 tokens)

Issue an agent passport

Issue an Agent Delegation Credential (SD-JWT VC) for a NEW agent: owner + local attestation authority keys from the vault, fresh agent did:key, revocation slot registered on the ledger. The credential and the agent private key are written to the operator-configured home directory; the result references them by path and never contains key material.

Input parameters:

- `agent_name` (string, required): Label for the new agent (also the artifact file prefix)
- `valid_days` (integer)

### `mandare_issue_mandate` (~178 tokens)

Issue a mandate

Issue an owner-signed mandate (SD-JWT VC) for an agent: spend caps in WHOLE currency units (per transaction / day / task / total), optional human-approval threshold, validity window. The mandate file path is returned; point the gateway at it (MANDARE_MANDATE_PATH).

Input parameters:

- `agent_did` (string, required): The agent's did:key (from mandare_issue_passport)
- `approval_above` (number): Spends above this wait for an async human approval
- `currency` (string)
- `per_day` (number)
- `per_task` (number)
- `per_tx` (number): Max per single call/transaction, whole currency units
- `purpose` (string)
- `total` (number)
- `valid_hours` (number)

### `mandare_issue_token` (~123 tokens)

Issue a scoped access token

Mint a short-lived proof-of-possession token an agent presents to the gateway (TTL ≤ 30 minutes). The grant INCLUDING ITS ONE-TIME SECRET is written 0600 to the operator-configured home directory; the result references it by path only — hand the FILE to the agent process (e.g. @mandarelabs/sdk tokenCredentialsFromIssueJson), never paste its contents into chat.

Input parameters:

- `actor_did` (string, required): The agent DID the token is scoped to
- `mandate_id` (string, required)
- `ttl_seconds` (integer)

### `mandare_kill` (~129 tokens)

Kill switch

The LOCAL, offline, fail-closed kill: revoke ONE agent, ONE mandate (the agent survives, the permission slip dies), or --all (halts the whole door). Writes the revocation to the ledger; the gateway refuses the subject on its very next request. Bound virtual cards are revoked too. Kills only CLOSE doors — reversing one requires the operator (mandare reinstate).

Input parameters:

- `agent_did` (string)
- `all` (boolean): Revoke the whole door (every subject it governs)
- `mandate_id` (string)
- `reason` (string)

### `mandare_certify` (~63 tokens)

Export an integrity certificate

Build the selective-disclosure integrity certificate (chain valid · witnessed · anchored) a third party can verify WITHOUT ledger access. Optionally disclose specific entries by seq; undisclosed entries stay salted hashes. Requires a configured witness.

Input parameters:

- `disclose_seqs` (array)

### `mandare_gateway_health` (~45 tokens)

Gateway health

Read the running gateway door /healthz (halted state, card rail, witness gating). Requires MANDARE_GATEWAY_URL in the MCP server environment. Read-only.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/com-mandarelabs-mandare/mandarelabs-mcp-server#diagnostics

## Score history

- 2026-10-04: 78
- 2026-10-03: 78
- 2026-10-02: 78
- 2026-10-01: 78

## Common questions

### What is the Mandare MCP server?

Mandare is an MCP server listed in the public MCP registry as com.mandarelabs/mandare. Verify an agent fleet's tamper-evident ledger, check budgets, kill a runaway agent. Local-first. This page covers its npm package (@mandarelabs/mcp-server).

### Is the Mandare MCP server safe to use?

Mandare scores 78 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 October 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Mandare MCP server expose?

Mandare exposes 8 tools: mandare_verify, mandare_budget_status, mandare_issue_passport, mandare_issue_mandate, mandare_issue_token, and 3 more. Their descriptions and schemas cost roughly 807 tokens of context every time the server is loaded.

### Is the Mandare MCP server still maintained?

Mandare is still listed as active in the MCP registry. We last reached this channel on 4 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Mandare MCP server under?

Mandare declares the AGPL-3.0-only licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@mandarelabs/mcp-server
- Socket report: https://socket.dev/npm/package/@mandarelabs/mcp-server
- Repository: https://github.com/mandarelabs/mandare
- Changelog RSS feed: https://verifymcp.io/servers/com-mandarelabs-mandare/mandarelabs-mcp-server.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-mandarelabs-mandare/mandarelabs-mcp-server.json
- HTML version of this page: https://verifymcp.io/servers/com-mandarelabs-mandare/mandarelabs-mcp-server