# typeship (remote · typeship.dev)

Generate a typed SDK, CLI, and MCP server from any OpenAPI or GraphQL spec, and keep them current.

- Trust score: 74/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `typeship.dev`: 74/100 (this document), [markdown](https://verifymcp.io/servers/dev-typeship-typeship/mcp-public.md), [page](https://verifymcp.io/servers/dev-typeship-typeship/mcp-public)
- remote · `typeship.dev`: 38/100, [markdown](https://verifymcp.io/servers/dev-typeship-typeship/mcp-readonly.md), [page](https://verifymcp.io/servers/dev-typeship-typeship/mcp-readonly)
- remote · `typeship.dev`: 38/100, [markdown](https://verifymcp.io/servers/dev-typeship-typeship/typeship.md), [page](https://verifymcp.io/servers/dev-typeship-typeship/typeship)
- npm · `@typeship-ax/mcp`: 90/100, [markdown](https://verifymcp.io/servers/dev-typeship-typeship/typeship-ax-mcp.md), [page](https://verifymcp.io/servers/dev-typeship-typeship/typeship-ax-mcp)

## Channel facts

- Endpoint: `https://typeship.dev/mcp/public`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.10.0`

## 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 2026-09-20.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 2 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 68/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 943 tokens (~188/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**: 60/100
  - Stability observed for 18 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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 (20% 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.
  - 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 current MCP spec version (2026-07-28).

## Install

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

typeship is a hosted endpoint at https://typeship.dev/mcp/public, 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 dev-typeship-typeship 'https://typeship.dev/mcp/public'
```

### Cursor

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

### VS Code

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

### Codex

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

### opencode

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

### OpenClaw

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

### Hermes

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

### Netclaw

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

### Vellum

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

### Other

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

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.

### 2026-09-20 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-18 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-16 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 70, 0)

- [security] Tool “generate_run” rewrote its description, which is the text the model reads

### 2026-09-11 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-09 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-07 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (5)

### `generate_run` (~321 tokens)

Generate one Target from a Definition

Generate one Target from a Definition. Returns one generated package without saving a Project or retaining source files or generated files. POST /generate Credential optional.

Input parameters:

- `Idempotency-Key` (string): Identifies one logical write for 24 hours. The key is scoped to the authenticated account and operation; account-less generation uses a hashed network identity. Retrying the same method, path, query,…
- `config` (object): Everything Typeship needs beyond the Definition, in one object: generation customization (globals, retries, pagination, readme) and how the generated tooling behaves (cli, mcp, package, docs_url). Pl…
- `definition` (required): A Definition for stateless generation, provided as exactly one URL or inline entrypoint.
- `fields` (array): Result keys to keep, as dotted paths (e.g. ["id","name"]). Omit for the whole result. Keeps responses small.
- `module_path` (string): Go module path override. Valid only for the Go SDK. Linked projects derive this from the Go destination repository by default.
- `package_name` (string): npm package or Python distribution override. Valid only for the TypeScript and Python SDK targets.
- `target` (object, required): Stateless generator descriptor; no persisted Target is created.

Output parameters:

- `claim`: Anonymous, URL-sourced generations only.
- `files` (array)
- `limits` (object): Present when the generation was capped: by the free plan, or because the call was anonymous.
- `meta` (object)
- `request_id` (string): Server-generated identifier used to correlate this response with Typeship logs.
- `warnings` (array)

### `search_docs` (~65 tokens)

Search this API's reference (operations, parameters) and, when a docs site is configured, its guides. Best matches first; page through with page.

Input parameters:

- `page` (integer): Page of reference matches (15 per page), default 1
- `query` (string, required)

### `read_docs` (~45 tokens)

Read a documentation page: an operation reference (a tool name, or dotted "resource.method") or a docs-site guide page by name or URL.

Input parameters:

- `page` (string, required)

### `query_docs` (~130 tokens)

Grep the typeship docs

Search every typeship docs page and both references with a regular expression (case-insensitive) and get matching lines with their page and a little context. Use when search_docs is too coarse or you need every occurrence of a term, flag, or error message. GET llms-full.txt

Input parameters:

- `context` (integer): Lines of context around each match (0 to 5). Default 1.
- `limit` (integer): Maximum matches to return (1 to 100). Default 30.
- `pattern` (string, required): A JavaScript regular expression, matched case-insensitively line by line.

### `submit_docs_feedback` (~83 tokens)

Report a docs problem

Tell the typeship team a docs page is wrong, missing, or unclear: the page (URL or title) and what you expected. Read by people; no reply comes back through this tool. POST docs feedback

Input parameters:

- `message` (string, required): What is wrong or missing, in one to five sentences.
- `page` (string, required): The page URL or title.

## Diagnostics

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

## Score history

- 2026-09-20: 74
- 2026-09-19: 73
- 2026-09-18: 73
- 2026-09-17: 72
- 2026-09-16: 72
- 2026-09-15: 71
- 2026-09-14: 71
- 2026-09-13: 70
- 2026-09-12: 70
- 2026-09-11: 70
- 2026-09-10: 69
- 2026-09-09: 69
- 2026-09-08: 68
- 2026-09-07: 68
- 2026-09-06: 67
- 2026-09-05: 67
- 2026-09-04: 67
- 2026-09-03: 66
- 2026-09-02: 65

## Common questions

### What is the typeship MCP server?

typeship is an MCP server listed in the public MCP registry as dev.typeship/typeship. Generate a typed SDK, CLI, and MCP server from any OpenAPI or GraphQL spec, and keep them current. This page covers its hosted endpoint (https://typeship.dev/mcp/public).

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

typeship scores 74 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 typeship MCP server expose?

typeship exposes 5 tools: generate_run, search_docs, read_docs, query_docs, submit_docs_feedback. Their descriptions and schemas cost roughly 644 tokens of context every time the server is loaded.

### Does the typeship MCP server require authentication?

No. We connected to typeship without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the typeship MCP server still maintained?

typeship is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://typeship.dev/mcp/public
- Repository: https://github.com/typeship-ax/mcp
- Website: https://typeship.dev/
- Changelog RSS feed: https://verifymcp.io/servers/dev-typeship-typeship/mcp-public.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-typeship-typeship/mcp-public.json
- HTML version of this page: https://verifymcp.io/servers/dev-typeship-typeship/mcp-public