# mcpsteward (npm · mcpsteward)

Grade MCP servers against the 2026-07-28 spec and detect tool drift and poisoning. Local only.

- Trust score: 72/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- npm · `mcpsteward`: 72/100 (this document), [markdown](https://verifymcp.io/servers/itherosolutions-mcpsteward/mcpsteward.md), [page](https://verifymcp.io/servers/itherosolutions-mcpsteward/mcpsteward)

## Channel facts

- Registry: `npm`
- Package: `mcpsteward`
- Version: `0.2.0`
- 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 2026-11-21.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **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 3 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 79/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 644 tokens (~107/item across 6 items; 6 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**: 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 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (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 mcpsteward MCP server?

mcpsteward runs locally as an npm package, launched with npx -y mcpsteward mcp. 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 itherosolutions-mcpsteward -- npx -y mcpsteward mcp
```

### Cursor

```json
{
  "mcpServers": {
    "itherosolutions-mcpsteward": {
      "command": "npx",
      "args": [
        "-y",
        "mcpsteward",
        "mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "itherosolutions-mcpsteward": {
      "command": "npx",
      "args": [
        "-y",
        "mcpsteward",
        "mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add itherosolutions-mcpsteward -- npx -y mcpsteward mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "itherosolutions-mcpsteward": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "mcpsteward",
        "mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add itherosolutions-mcpsteward --command npx --arg -y --arg mcpsteward --arg mcp
```

### Hermes

```yaml
mcp_servers:
  itherosolutions-mcpsteward:
    command: "npx"
    args: ["-y", "mcpsteward", "mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "itherosolutions-mcpsteward": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "mcpsteward",
        "mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add itherosolutions-mcpsteward -t stdio -c npx -a -y mcpsteward mcp
```

### Other

```json
{
  "mcpServers": {
    "itherosolutions-mcpsteward": {
      "command": "npx",
      "args": [
        "-y",
        "mcpsteward",
        "mcp"
      ]
    }
  }
}
```

## 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.

### 2026-11-17 (score 72)

First indexed and scored.

## MCP tools (6)

### `capture_surface` (~96 tokens)

Connect to one configured server and record exactly what it advertises: its tools, prompts, resources and resource templates, with a content hash for each and a merkle root over the whole surface. This starts the server process, so it is slower than discover_servers and has a side effect. Returns the protocol revision actually spoken, which may be older than the one requested.

Input parameters:

- `server` (string, required): Server name as reported by discover_servers.

### `check_conformance` (~105 tokens)

Grade one configured server against the 2026-07-28 MCP specification and return a letter grade with every finding. Each finding carries the specification section or SEP that justifies it and a remediation written for whoever has to fix it, so the result can be checked rather than merely believed. Every rule is deterministic: no model is involved and the same server always grades the same. This starts the server process.

Input parameters:

- `server` (string, required): Server name as reported by discover_servers.

### `check_policy` (~86 tokens)

Evaluate a policy file against the servers configured on this machine and return every violation, each naming the server, what the policy required, what was found, and the next action. Also reports any check that could not run for lack of input, so a passing result cannot be mistaken for a complete one. Reads local files only.

Input parameters:

- `policyPath` (string, required): Path to the policy file.

### `diff_against_trust` (~133 tokens)

Compare a server against the surface that was previously approved for it, and classify every difference: a tool added or removed, a description changed after approval, a schema widened or narrowed, a parameter newly required, a name that collides with another server. A description change on an approved tool is the highest signal event here, because that is how tool poisoning presents. Fails if the server has never been approved. Risk scores are a heuristic, not a guarantee.

Input parameters:

- `pinPath` (string, required): Path to the pin file recording the approval.
- `server` (string, required): Server name as reported by discover_servers.

### `discover_servers` (~82 tokens)

List every MCP server configured on this machine, with its transport, how it authenticates, which clients registered it, and whether any credential is written directly into a configuration file. Reads local configuration only: it connects to nothing and starts nothing, so it is safe to call and cannot wake a server up. Credential values are never returned, only the fact that one exists.

### `verify_ledger` (~96 tokens)

Walk the append-only surface ledger and prove its hash chain is unbroken, reporting the exact sequence number where integrity fails if it does. Reads a local file and connects to nothing. Note the limit honestly: this proves the chain is internally consistent, not that it is authentic. Anyone who can rewrite the file from entry zero can produce a forgery that verifies cleanly.

Input parameters:

- `ledgerPath` (string, required): Path to the ledger file.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/itherosolutions-mcpsteward/mcpsteward#diagnostics

## Score history

- 2026-11-21: 72
- 2026-11-20: 72
- 2026-11-19: 72
- 2026-11-18: 72
- 2026-11-17: 72

## Common questions

### What is the mcpsteward MCP server?

mcpsteward is an MCP server listed in the public MCP registry as io.github.ITheroSolutions/mcpsteward. Grade MCP servers against the 2026-07-28 spec and detect tool drift and poisoning. Local only. This page covers its npm package (mcpsteward).

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

mcpsteward scores 72 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 mcpsteward MCP server expose?

mcpsteward exposes 6 tools: capture_surface, check_conformance, check_policy, diff_against_trust, discover_servers, verify_ledger. Their descriptions and schemas cost roughly 598 tokens of context every time the server is loaded.

### Is the mcpsteward MCP server still maintained?

mcpsteward 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 mcpsteward MCP server under?

mcpsteward 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 mcpsteward MCP server?

VerifyMCP ran 15 checks on mcpsteward, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about mcpsteward: Stability. One category scores 0 for that reason, because we only credit what we can confirm. 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/mcpsteward
- Socket report: https://socket.dev/npm/package/mcpsteward
- Repository: https://github.com/ITheroSolutions/mcpsteward
- Changelog RSS feed: https://verifymcp.io/servers/itherosolutions-mcpsteward/mcpsteward.xml
- Changelog JSON feed: https://verifymcp.io/servers/itherosolutions-mcpsteward/mcpsteward/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/itherosolutions-mcpsteward/mcpsteward.json
- HTML version of this page: https://verifymcp.io/servers/itherosolutions-mcpsteward/mcpsteward
