# io.github.stillmarcus24/stillos-ratings-mcp (mcpb · stillos-ratings-mcp.mcpb)

Check an MCP server before you install it — outside-in trust ratings for 7,000+ operators.

- Trust score: 57/100 (low)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- mcpb · `stillos-ratings-mcp.mcpb`: 57/100 (this document), [markdown](https://verifymcp.io/servers/stillmarcus24-stillos-ratings-mcp/stillos-ratings-mcp.md), [page](https://verifymcp.io/servers/stillmarcus24-stillos-ratings-mcp/stillos-ratings-mcp)

## Channel facts

- Registry: `mcpb`
- Package: `https://github.com/stillmarcus24/stillos-ratings-mcp/releases/download/v1.0.0/stillos-ratings-mcp.mcpb`
- Transport: `stdio`
- SHA-256: `6f048f6a2db6faa962f78aaa7eb87a6c56ded9d33c0fd97ae7fde5bbd3342c9d`

## 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 2026-11-05.

- **Supply Chain Security**: 13/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
  - No install/post-install scripts declared.
  - Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
- **Provenance & Transparency**: 45/100
  - 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 31 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 83/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 337 tokens (~112/item across 3 items; 3 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **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 3 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### How do I install the io.github.stillmarcus24/stillos-ratings-mcp server?

io.github.stillmarcus24/stillos-ratings-mcp ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, 6f048f6a2db6faa962f78aaa7eb87a6c56ded9d33c0fd97ae7fde5bbd3342c9d; the commands to do that are on this page. If it does not match, do not open it.

- Download bundle: `https://github.com/stillmarcus24/stillos-ratings-mcp/releases/download/v1.0.0/stillos-ratings-mcp.mcpb`
- SHA-256: `6f048f6a2db6faa962f78aaa7eb87a6c56ded9d33c0fd97ae7fde5bbd3342c9d`

### Verify on macOS / Linux

```bash
echo "6f048f6a2db6faa962f78aaa7eb87a6c56ded9d33c0fd97ae7fde5bbd3342c9d  stillos-ratings-mcp.mcpb" | shasum -a 256 -c
```

### Verify on Windows (PowerShell)

```powershell
(Get-FileHash -Algorithm SHA256 .\stillos-ratings-mcp.mcpb).Hash -eq "6f048f6a2db6faa962f78aaa7eb87a6c56ded9d33c0fd97ae7fde5bbd3342c9d"
```

## 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.

### 2026-11-04 (score 57, +1)

- [security] Stability: 0.97 → pass

### 2026-11-02 (score 56, +1)

No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 55, +1)

- [functional regression] Security disclosure: unverified → fail

### 2026-10-30 (score 54, 0)

- [functional regression] Security disclosure: fail → unverified

### 2026-10-29 (score 54, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 53, +1)

- [functional improvement] Maintenance: unverified → pass

### 2026-10-27 (score 52, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-26 (score 51, −1)

- [functional regression] Maintenance: pass → unverified

## MCP tools (3)

### `check_mcp_server` (~187 tokens)

Before installing or trusting an MCP server, check it. Returns an outside-in trust rating for that host from a public census of 7,000+ MCP operators refreshed every 6 hours: percentile grade, rank, five scored dimensions, whether it advertises a machine-payable rail, how many other servers its publisher mass-published and whether it shares a boilerplate tool set with a template fleet, and — critically — any DATED finding that its advertised tool set changed while the version string it serves did not. An unrated host is reported as NOT_RATED with an explicit warning that unobserved is not attested safe. Nothing here is self-reported by the operator and every figure is independently recomputable.

Input parameters:

- `host` (string, required): Hostname, endpoint URL, or registry name — e.g. api.mcp.ai, https://api.mcp.ai/mcp

### `list_tool_surface_findings` (~73 tokens)

List every MCP operator currently carrying a dated tool-surface finding — a case where the advertised tool set grew while the served version string stayed identical, meaning clients that pinned that version were never asked to re-approve what it now exposes. Includes when each was first observed and a link to free redacted evidence.

### `compare_mcp_servers` (~77 tokens)

Compare up to 10 candidate MCP servers side by side on rating, rank, rail position and open findings — for choosing between alternatives that do the same job. A host we failed to look up is reported as a lookup failure, never as a clean result.

Input parameters:

- `hosts` (array, required): Hostnames to compare (max 10)

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/stillmarcus24-stillos-ratings-mcp/stillos-ratings-mcp#diagnostics

## Score history

- 2026-11-05: 57
- 2026-11-04: 57
- 2026-11-03: 56
- 2026-11-02: 56
- 2026-11-01: 55
- 2026-10-31: 55
- 2026-10-30: 54
- 2026-10-29: 54
- 2026-10-28: 53
- 2026-10-27: 52
- 2026-10-26: 51
- 2026-10-25: 52
- 2026-10-24: 51
- 2026-10-23: 51
- 2026-10-22: 51
- 2026-10-21: 50
- 2026-10-20: 50
- 2026-10-19: 49
- 2026-10-18: 49
- 2026-10-17: 48
- 2026-10-16: 48
- 2026-10-15: 47
- 2026-10-14: 47
- 2026-10-13: 43
- 2026-10-12: 43
- 2026-10-10: 43
- 2026-10-07: 43
- 2026-10-05: 13

## Common questions

### What is the io.github.stillmarcus24/stillos-ratings-mcp server?

io.github.stillmarcus24/stillos-ratings-mcp is listed in the public MCP registry as io.github.stillmarcus24/stillos-ratings-mcp. Check an MCP server before you install it, outside-in trust ratings for 7,000+ operators. This page covers its MCPB bundle (https://github.com/stillmarcus24/stillos-ratings-mcp/releases/download/v1.0.0/stillos-ratings-mcp.mcpb).

### Is the io.github.stillmarcus24/stillos-ratings-mcp server safe to use?

io.github.stillmarcus24/stillos-ratings-mcp scores 57 out of 100 on VerifyMCP. 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 io.github.stillmarcus24/stillos-ratings-mcp server expose?

io.github.stillmarcus24/stillos-ratings-mcp exposes 3 tools: check_mcp_server, list_tool_surface_findings, compare_mcp_servers. Their descriptions and schemas cost roughly 337 tokens of context every time the server is loaded.

### What licence is the io.github.stillmarcus24/stillos-ratings-mcp server under?

io.github.stillmarcus24/stillos-ratings-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- Repository: https://github.com/stillmarcus24/stillos-ratings-mcp
- Changelog RSS feed: https://verifymcp.io/servers/stillmarcus24-stillos-ratings-mcp/stillos-ratings-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/stillmarcus24-stillos-ratings-mcp/stillos-ratings-mcp.json
- HTML version of this page: https://verifymcp.io/servers/stillmarcus24-stillos-ratings-mcp/stillos-ratings-mcp