# io.github.mzizi-dev/mzizi-mcp (remote · mcp.mzizi.dev)

Mzizi design system MCP: search and execute over components, tokens, crates, skills and docs. Free.

- Trust score: 61/100 (medium)
- Change this week: −14
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `mcp.mzizi.dev`: 61/100 (this document), [markdown](https://verifymcp.io/servers/mzizi-dev-mzizi-mcp/mcp.md), [page](https://verifymcp.io/servers/mzizi-dev-mzizi-mcp/mcp)
- npm · `@nyuchi/mzizi-mcp`: 67/100, [markdown](https://verifymcp.io/servers/mzizi-dev-mzizi-mcp/nyuchi-mzizi-mcp.md), [page](https://verifymcp.io/servers/mzizi-dev-mzizi-mcp/nyuchi-mzizi-mcp)

## Channel facts

- Endpoint: `https://mcp.mzizi.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.26.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (mzizi_execute).
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 80/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 5090 tokens (~124/item across 41 items; 3 tools + 38 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 7/100
  - Stability check failed: schema churn in the 30 days we've observed: 13 tool removals, 0 breaking changes, 0 auth/transport breaks, 2 additions.
- **Tool Coverage**: 96/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 87% of tool parameters carry a description.
  - Structured output schemas are declared (33% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 5 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).

## Install

### How do I install the io.github.mzizi-dev/mzizi-mcp server?

io.github.mzizi-dev/mzizi-mcp is a hosted endpoint at https://mcp.mzizi.dev/mcp, so there is nothing to install locally. 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 --transport http mzizi-dev-mzizi-mcp 'https://mcp.mzizi.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "mzizi-dev-mzizi-mcp": {
      "url": "https://mcp.mzizi.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "mzizi-dev-mzizi-mcp": {
      "type": "http",
      "url": "https://mcp.mzizi.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.mzizi-dev-mzizi-mcp]
url = "https://mcp.mzizi.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mzizi-dev-mzizi-mcp": {
      "type": "remote",
      "url": "https://mcp.mzizi.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add mzizi-dev-mzizi-mcp --url 'https://mcp.mzizi.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  mzizi-dev-mzizi-mcp:
    url: "https://mcp.mzizi.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "mzizi-dev-mzizi-mcp": {
      "Transport": "http",
      "Url": "https://mcp.mzizi.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add mzizi-dev-mzizi-mcp -t streamable-http -u 'https://mcp.mzizi.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "mzizi-dev-mzizi-mcp": {
      "type": "http",
      "url": "https://mcp.mzizi.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-11-20 (score 61, 0)

- [functional] Server version: 0.25.0 → 0.26.0

### 2026-11-19 (score 61, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional] Server version: 0.24.0 → 0.25.0

### 2026-11-17 (score 61, −14)

- [security regression] Stability: pass → fail
- [security regression] Tool “mzizi_report_issue” was removed
- [security regression] Tool “mzizi_mcp_describe” was removed
- [security regression] Tool “mzizi_list_components” was removed
- [security regression] Tool “mzizi_get_tokens” was removed
- [security regression] Tool “mzizi_get_skills” was removed
- [security regression] Tool “mzizi_get_doctrine” was removed
- [security regression] Tool “mzizi_get_component” was removed
- [security regression] Tool “mzizi_get_architecture” was removed
- [security regression] Tool “mzizi_fundi” was removed
- [security regression] Tool “mzizi_check_accessibility” was removed
- [security regression] Tool “docs_submit_feedback” was removed
- [security regression] Tool “docs_search_mzizi” was removed
- [security regression] Tool “docs_query_docs_filesystem_mzizi” was removed
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] New tool “mzizi_execute”, which the server declares destructive
- [security] Tool “mzizi_search” rewrote its description, which is the text the model reads
- [functional regression] Tool coverage: 93% → 87%
- [functional improvement] Schema quality: 151 → 123
- [functional improvement] Schema quality: 151 → 122
- [functional improvement] Tool coverage: 21% → 33%
- [functional] Schema quality: excellent → good
- [functional] Destructive annotations: pass → 100
- [functional] Server version: 0.22.1 → 0.24.0
- [functional] Server version: 0.21.0 → 0.22.1
- [functional] New tool “mzizi_feedback”
- [cosmetic] “mzizi_search” reworded the description of “query”
- [cosmetic] “mzizi_search” reworded the description of “offset”

### 2026-11-14 (score 75, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “mzizi_check_accessibility” rewrote its description, which is the text the model reads
- [security] Tool “mzizi_get_tokens” rewrote its description, which is the text the model reads
- [security] Tool “docs_query_docs_filesystem_mzizi” rewrote its description, which is the text the model reads
- [functional] Server version: 0.20.0 → 0.21.0
- [cosmetic] “mzizi_check_accessibility” added an optional parameter “hitRegionPx”
- [cosmetic] “mzizi_check_accessibility” added an optional parameter “context”

### 2026-11-13 (score 75, 0)

- [functional] Server version: 0.19.0 → 0.20.0

### 2026-11-12 (score 75, 0)

- [functional] Server version: 0.18.0 → 0.19.0
- [functional] Server version: 0.17.0 → 0.18.0

### 2026-11-09 (score 75, +1)

- [security] Stability: 0.97 → pass

### 2026-11-08 (score 74, −1)

- [functional] Stability: pass → 0.97

## MCP tools (3)

### `mzizi_search` (~297 tokens)

Search Mzizi

Find anything this server can answer, and the operations that act on it. Searches components, conventions, engineering constraints, AI instruction sets, releases, the Rust crates, the agent skills, the toolchain (the CLI, how to install anything, this server) and, when docs.mzizi.dev answers, the documentation. Returns `results` (hits, paged), `docs` (documentation matches), and `operations`: each with its `arguments` (JSON Schema), the `permission` it needs (free, or sign-in) and `mayRun`, whether you may run it now. Run one with mzizi_execute {operation, arguments}. `allOperations` lists every operation. A component hit with `rustCrate` has a Mzizi Roots (Rust) implementation, which is the lead; at an equal score it ranks first. Paged: up to 50 hits per call and at most 25000 characters; results.meta.has_more and results.meta.next_offset say how to get the rest.

Input parameters:

- `limit` (integer): Hits per call (default 50, at most 200).
- `offset` (integer): Hits to skip, for paging. Use results.meta.next_offset from the previous call.
- `query` (string, required): Free-text search, e.g. 'button', 'install', 'cli', 'contrast', 'crates' or an operation name. Every word must match.

Output parameters:

- `allOperations` (array)
- `operations` (array)
- `query` (string)
- `results` (object)

### `mzizi_execute` (~195 tokens)

Run a Mzizi operation

Run one operation by name with its arguments. mzizi_search lists operations with their arguments, the permission each needs and whether you may run it. Operations: get_component, list_components, get_tokens, get_architecture, get_doctrine, get_skills, check_accessibility, list_crates, fundi, describe, docs_search_mzizi, docs_query_docs_filesystem_mzizi, docs_submit_feedback. Reads need no account; the fundi operation needs sign-in, and a refusal names the permission it needs and how to sign in. The result is the operation's own answer. The earlier tool names (mzizi_get_component and the rest) are accepted as operation names.

Input parameters:

- `arguments` (object): The operation's arguments, as its `arguments` schema in mzizi_search states them. Omit for none.
- `operation` (string, required): The operation's name, e.g. 'get_component'.

### `mzizi_feedback` (~399 tokens)

Report an issue or give feedback

Your issue desk (was mzizi_report_issue): report a problem with a component or the registry. It goes to your own desk, which reproduces it via fundi, drafts an issue body with what the reproduction returned and logs it to fundi; fundi files the GitHub issue and tracks it, so action 'get' shows where yours got to. 'list' shows your reports, 'retry' re-attempts one that drafted but could not be logged. Needs sign-in: the desk belongs to your Mzizi console user; without it, the answer carries the report as a pre-filled GitHub issue for mzizi-dev/mzizi-registry, so it is never lost, and over HTTP the server answers with an OAuth challenge so your client can offer sign-in. With target 'docs', it instead reports a problem with a documentation page on docs.mzizi.dev (give `path` and `message`); that needs no account.

Input parameters:

- `action` (string): What to do. Defaults to filing a new report.
- `component` (string): Component the report concerns.
- `kind` (string): Report kind. Required for action 'file'.
- `limit` (integer)
- `message` (string): What happened. Required for action 'file'.
- `path` (string): For target 'docs': the page's URL path, without .mdx, e.g. /toolchain/cli.
- `reportId` (string): Report id. Required for actions 'get' and 'retry'.
- `severity` (string)
- `skill` (string): fundi skill to run for the reproduction. fundi never infers a skill from text, so omit this to let the report kind choose one.
- `target` (string): Where it goes: 'issue-desk' (default; sign-in) or 'docs' (a docs.mzizi.dev page; free).

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/mzizi-dev-mzizi-mcp/mcp#diagnostics

## Score history

- 2026-11-21: 61
- 2026-11-20: 61
- 2026-11-19: 61
- 2026-11-18: 61
- 2026-11-17: 61
- 2026-11-16: 75
- 2026-11-15: 75
- 2026-11-14: 75
- 2026-11-13: 75
- 2026-11-12: 75
- 2026-11-11: 75
- 2026-11-10: 75
- 2026-11-09: 75
- 2026-11-08: 74
- 2026-11-07: 75
- 2026-11-06: 75
- 2026-11-05: 75
- 2026-11-04: 75
- 2026-11-03: 75
- 2026-11-02: 75
- 2026-11-01: 75
- 2026-10-31: 74
- 2026-10-30: 74
- 2026-10-29: 74
- 2026-10-28: 73
- 2026-10-27: 73
- 2026-10-26: 72
- 2026-10-25: 72
- 2026-10-24: 71
- 2026-10-23: 71

## Common questions

### What is the io.github.mzizi-dev/mzizi-mcp server?

io.github.mzizi-dev/mzizi-mcp is listed in the public MCP registry as io.github.mzizi-dev/mzizi-mcp. Mzizi design system MCP: search and execute over components, tokens, crates, skills and docs. Free. This page covers its hosted endpoint (https://mcp.mzizi.dev/mcp).

### Is the io.github.mzizi-dev/mzizi-mcp server safe to use?

io.github.mzizi-dev/mzizi-mcp scores 61 out of 100 on VerifyMCP. 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.mzizi-dev/mzizi-mcp server expose?

io.github.mzizi-dev/mzizi-mcp exposes 3 tools: mzizi_search, mzizi_execute, mzizi_feedback. Their descriptions and schemas cost roughly 891 tokens of context every time the server is loaded.

### Does the io.github.mzizi-dev/mzizi-mcp server require authentication?

No. We connected to io.github.mzizi-dev/mzizi-mcp without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the io.github.mzizi-dev/mzizi-mcp server still maintained?

io.github.mzizi-dev/mzizi-mcp 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 did VerifyMCP test on the io.github.mzizi-dev/mzizi-mcp server?

VerifyMCP ran 12 checks on io.github.mzizi-dev/mzizi-mcp, covering TLS certificate, Authorization, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about io.github.mzizi-dev/mzizi-mcp: HTTPS. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://mcp.mzizi.dev/mcp
- Website: https://mzizi.dev/
- Changelog RSS feed: https://verifymcp.io/servers/mzizi-dev-mzizi-mcp/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/mzizi-dev-mzizi-mcp/mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/mzizi-dev-mzizi-mcp/mcp.json
- HTML version of this page: https://verifymcp.io/servers/mzizi-dev-mzizi-mcp/mcp
