# Sigvara (npm · @sigvara/protocol-sdk)

Read-only checks of an AI agent's Sigvara standing, score, stake and slashes before you rely on it.

- Trust score: 59/100 (low)
- Change this week: −11
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- npm · `@sigvara/protocol-sdk`: 59/100 (this document), [markdown](https://verifymcp.io/servers/runtimeadmin-sigvara/sigvara-protocol-sdk.md), [page](https://verifymcp.io/servers/runtimeadmin-sigvara/sigvara-protocol-sdk)

## Channel facts

- Registry: `npm`
- Package: `@sigvara/protocol-sdk`
- Version: `1.0.0-alpha.23`
- 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 2026-11-21.

- **Supply Chain Security**: 48/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 2 of 10 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 72/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 642 tokens (~128/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 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.

## Install

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

Sigvara runs locally as an npm package, launched with npx -y @sigvara/protocol-sdk. 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 runtimeadmin-sigvara -- npx -y @sigvara/protocol-sdk
```

### Cursor

```json
{
  "mcpServers": {
    "runtimeadmin-sigvara": {
      "command": "npx",
      "args": [
        "-y",
        "@sigvara/protocol-sdk"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "runtimeadmin-sigvara": {
      "command": "npx",
      "args": [
        "-y",
        "@sigvara/protocol-sdk"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add runtimeadmin-sigvara -- npx -y @sigvara/protocol-sdk
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "runtimeadmin-sigvara": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@sigvara/protocol-sdk"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add runtimeadmin-sigvara --command npx --arg -y --arg @sigvara/protocol-sdk
```

### Hermes

```yaml
mcp_servers:
  runtimeadmin-sigvara:
    command: "npx"
    args: ["-y", "@sigvara/protocol-sdk"]
```

### Netclaw

```json
{
  "McpServers": {
    "runtimeadmin-sigvara": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@sigvara/protocol-sdk"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add runtimeadmin-sigvara -t stdio -c npx -a -y @sigvara/protocol-sdk
```

### Other

```json
{
  "mcpServers": {
    "runtimeadmin-sigvara": {
      "command": "npx",
      "args": [
        "-y",
        "@sigvara/protocol-sdk"
      ]
    }
  }
}
```

## 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.

### 2026-11-21 (score 59, −14)

- [security regression] Malware scan: pass → unverified
- [functional] Package version: 1.0.0-alpha.22 → 1.0.0-alpha.23

### 2026-11-19 (score 73, +1)

- [security regression] Tool safety: pass → unverified
- [security regression] Stability: 0.17 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified
- [functional] Package version: 1.0.0-alpha.21 → 1.0.0-alpha.22

### 2026-11-17 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-16 (score 71, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-15 (score 56, −14)

- [security regression] Malware scan: pass → unverified
- [functional improvement] Stability: unverified → 0.07
- [functional] Package version: 1.0.0-alpha.20 → 1.0.0-alpha.21

### 2026-11-14 (score 70, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-13 (score 55)

First indexed and scored.

## MCP tools (5)

### `sigvara_check_agent` (~196 tokens)

Check an agent before paying or relying on it. Reports whether it is registered, Active and holding the minimum stake now; its matured score, the band it is in, and when the score was last written; the stake a slash could take; and anything pending (a slash, a queued withdrawal, a new score). With a threshold it also gives the yes or no SigvaraGate gives, without the proof of identity: use sigvara_challenge for that.

Input parameters:

- `agent` (string, required): The agent, as did:sigvara:<chainId>:<address> or as its 0x address on the chain this server reads.
- `maxScoreAgeSeconds` (integer): Optional. Refuse a score last written longer ago than this many seconds, or never written.
- `threshold` (integer): Optional. The lowest matured score you accept, 0 to 100. With it, the result carries a decision.

### `sigvara_score` (~80 tokens)

The six factors of an agent's score, the earned total, the matured total a threshold is checked against, when it was written, and any proposal waiting out its challenge window.

Input parameters:

- `agent` (string, required): The agent, as did:sigvara:<chainId>:<address> or as its 0x address on the chain this server reads.

### `sigvara_stake` (~89 tokens)

An agent's stake: what it holds, what is queued for withdrawal and when it can leave, the minimum, its most recent slash proposal, and the share of a slash that goes to the victim the committee names.

Input parameters:

- `agent` (string, required): The agent, as did:sigvara:<chainId>:<address> or as its 0x address on the chain this server reads.

### `sigvara_identity` (~70 tokens)

Who operates an agent, its status, when it registered, the Ed25519 key it signs with, and its DID document.

Input parameters:

- `agent` (string, required): The agent, as did:sigvara:<chainId>:<address> or as its 0x address on the chain this server reads.

### `sigvara_verify_evidence` (~138 tokens)

Check the payments behind an agent's score against what the chain committed to. Fetches the payments the oracle lists, rebuilds their Merkle root here (never trusting the oracle's own leaves), finds which of them the finalized root on chain covers, and asks the reputation contract to confirm them with verifyEvidence. Also says whether a pending proposal's root is reproduced. It shows the oracle scored on the set it published; it does not check each transaction itself.

Input parameters:

- `agent` (string, required): The agent, as did:sigvara:<chainId>:<address> or as its 0x address on the chain this server reads.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/runtimeadmin-sigvara/sigvara-protocol-sdk#diagnostics

## Score history

- 2026-11-21: 59
- 2026-11-20: 73
- 2026-11-19: 73
- 2026-11-18: 72
- 2026-11-17: 72
- 2026-11-16: 71
- 2026-11-15: 56
- 2026-11-14: 70
- 2026-11-13: 55

## Common questions

### What is the Sigvara MCP server?

Sigvara is an MCP server listed in the public MCP registry as io.github.RunTimeAdmin/sigvara. Read-only checks of an AI agent's Sigvara standing, score, stake and slashes before you rely on it. This page covers its npm package (@sigvara/protocol-sdk).

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

Sigvara scores 59 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. 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 Sigvara MCP server expose?

Sigvara exposes 5 tools: sigvara_check_agent, sigvara_score, sigvara_stake, sigvara_identity, sigvara_verify_evidence. Their descriptions and schemas cost roughly 573 tokens of context every time the server is loaded.

### Is the Sigvara MCP server still maintained?

Sigvara is still listed as active in the MCP registry. We last reached this channel on 21 November 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 Sigvara MCP server under?

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

### What did VerifyMCP test on the Sigvara MCP server?

VerifyMCP ran 15 checks on Sigvara, covering Known CVEs, Install scripts, Dependency health, Source repository and 11 more. One item could not be completed, a gap on our side rather than a finding about Sigvara: Malware scan. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- npm package: https://www.npmjs.com/package/@sigvara/protocol-sdk
- Socket report: https://socket.dev/npm/package/@sigvara/protocol-sdk
- Repository: https://github.com/RunTimeAdmin/Sigvara
- Website: https://sigvara.xyz/
- Changelog RSS feed: https://verifymcp.io/servers/runtimeadmin-sigvara/sigvara-protocol-sdk.xml
- Changelog JSON feed: https://verifymcp.io/servers/runtimeadmin-sigvara/sigvara-protocol-sdk/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/runtimeadmin-sigvara/sigvara-protocol-sdk.json
- HTML version of this page: https://verifymcp.io/servers/runtimeadmin-sigvara/sigvara-protocol-sdk
