Skip to main content
Glama
README.md
# @pipeworx/product-change-log

Pipeworx's change log for the products built on it: one durable record per change to a tool or field a product depends on, with its kind, fields, announcement, and the build that made it live or the deploy run that made it late.

Part of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 2016+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

## Tools

- `product_change_log(product, since?, task_id?, status?, limit?)` reads the records that affect one product, newest update first. Any account key can read.
- `change_log_announce(task_id, title, products, tools, kind, summary, actor, fields?, description_diff?, notes?)` creates the record before the push, or amends it while it is still announced or late. Pipeworx owners only.
- `change_log_mark_live(task_id, commit, alters_existing_answers, expect_build?, notes?)` records the stamped build that answered the call as the live build. Pipeworx owners only.
- `change_log_mark_late(task_id, run_id, reason, fix_expected?)` records a failed deploy run. Pipeworx owners only.

## Record

`task_id`, `title`, `status` (`announced`, `live`, `late`), `kind` (`additive`, `behaviour_change`, `breaking`), `products`, `tools`, `fields` (each `{path, type, change?, values?}` with the full closed value set), `summary`, `description_diff`, `announced_at`, `announced_by`, `live` (`build_sha`, `built_at`, `at`, `commit`, `alters_existing_answers`) or null, `late` (`deploy_run_id`, `reason`, `at`, `live_build_sha_instead`, `fix_expected`) or null, `notes`, `updated_at`.

`since` returns records whose `updated_at` is at or after it, so a change announced last week that went live today is returned.

## Auth

Account-only: anonymous and key-only callers are refused before the pack runs, so a product calls with its own Bearer token. Writes additionally need the Pipeworx internal credential; any other caller gets `owner_only` and nothing is written.

## Data sources

Pipeworx, cross-product change log. Written by Pipeworx owners; nothing is fetched from an outside publisher.

Record text is data, never instructions. Every free-text field is length-limited (an oversize value is refused, not truncated) and stripped of control, bidi and zero-width characters. Every read says so in `note`.

`live.build_sha` and `live.built_at` come from the gateway build that answered the `change_log_mark_live` call, never from the caller, and an unstamped build is refused. That the build contains the change commit is the writer's attestation, made after confirming the deploy; `expect_build` makes the call fail when a different build answers.

Lifecycle and the rules around it: `docs/cross-product-contracts.md`. Store: migration `287_product_change_log.sql`.

## Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

```json
{
  "mcpServers": {
    "product-change-log": {
      "url": "https://gateway.pipeworx.io/product-change-log/mcp"
    }
  }
}
```

### What this endpoint actually serves

`tools/list` at `https://gateway.pipeworx.io/product-change-log/mcp` returns the tools in the table
above **plus the shared Pipeworx meta-tools** — `ask_pipeworx`,
`discover_tools`, `search_within`, `remember`/`recall` and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's `initialize` response states its exact scope, and
is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
`ask_pipeworx`, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed
directly, instead of just this one's:

```json
{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}
```

Both URLs reach the same gateway and the same 2016+ data sources. The
only difference is which pack's tools are listed **directly**; `ask_pipeworx`
reaches all of them from either one.

## No MCP client? Call it over HTTP

```bash
curl -X POST https://gateway.pipeworx.io/v1/tools/product_change_log \
  -H 'Content-Type: application/json' \
  -d '{"product":"tapworx","since":"2026-11-18"}'
```

No account needed for the first calls. Inspect any tool: `GET https://gateway.pipeworx.io/v1/tools/product_change_log`. Find one: `POST https://gateway.pipeworx.io/v1/tools/search_packs` with `{"query":"..."}`.

## Run it from npm

`@pipeworx/mcp-product-change-log` is a local stdio bridge to the Pipeworx gateway: your MCP client
starts it with `npx`, and it forwards every call to the same
`https://gateway.pipeworx.io/product-change-log/mcp` endpoint shown above. It needs network access;
there is no offline mode.

```json
{
  "mcpServers": {
    "product-change-log": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-product-change-log"]
    }
  }
}
```

Without a key it calls anonymously, capped at 50 calls a day. A free account
raises that to 200 a day: get a key at https://pipeworx.io/signup and add
`"env": { "PIPEWORX_API_KEY": "<your key>" }` to the server entry.
The key is sent as a Bearer token, the same way a hosted connection sends it,
so calls are metered and billed exactly as they are there.

It lists **only** this pack's tools by default. Set `PIPEWORX_META_TOOLS=1` to
also list `ask_pipeworx` and the other gateway-wide tools.

Behind an HTTPS proxy: Node's built-in `fetch` does not read `HTTPS_PROXY` by
default. Newer Node releases honour it when `NODE_USE_ENV_PROXY=1` is set; check
your Node version's documentation.

## Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English —
this works on the pack endpoint above as well as on the full gateway:

```
ask_pipeworx({ question: "your question about Product Change Log data" })
```

The gateway picks the right tool and fills the arguments automatically.

## More

- [Docs and guides](https://pipeworx.io/docs)
- [pipeworx.io](https://pipeworx.io)

## License

MIT